Datasets:

---

librarian-bots

/

dataset_cards_with_metadata

like 12

Follow

Librarian Bots 103

fancyzhx/ag_news

fancyzhx

--- annotations_creators: - found language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 100K<n<1M source_datasets: - original task_categories: - text-classification task_ids: - topic-classification paperswithcode_id: ag-news pretty_name: AG’s News Corpus dataset_info: features: - name: text dtype: string - name: label dtype: class_label: names: '0': World '1': Sports '2': Business '3': Sci/Tech splits: - name: train num_bytes: 29817303 num_examples: 120000 - name: test num_bytes: 1879474 num_examples: 7600 download_size: 19820267 dataset_size: 31696777 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* train-eval-index: - config: default task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for "ag_news" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html](http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 31.33 MB - **Size of the generated dataset:** 31.70 MB - **Total amount of disk used:** 63.02 MB ### Dataset Summary AG is a collection of more than 1 million news articles. News articles have been gathered from more than 2000 news sources by ComeToMyHead in more than 1 year of activity. ComeToMyHead is an academic news search engine which has been running since July, 2004. The dataset is provided by the academic comunity for research purposes in data mining (clustering, classification, etc), information retrieval (ranking, search, etc), xml, data compression, data streaming, and any other non-commercial activity. For more information, please refer to the link http://www.di.unipi.it/~gulli/AG_corpus_of_news_articles.html . The AG's news topic classification dataset is constructed by Xiang Zhang ([email protected]) from the dataset above. It is used as a text classification benchmark in the following paper: Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems 28 (NIPS 2015). ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 31.33 MB - **Size of the generated dataset:** 31.70 MB - **Total amount of disk used:** 63.02 MB An example of 'train' looks as follows. ``` { "label": 3, "text": "New iPad released Just like every other September, this one is no different. Apple is planning to release a bigger, heavier, fatter iPad that..." } ``` ### Data Fields The data fields are the same among all splits. #### default - `text`: a `string` feature. - `label`: a classification label, with possible values including `World` (0), `Sports` (1), `Business` (2), `Sci/Tech` (3). ### Data Splits | name |train |test| |-------|-----:|---:| |default|120000|7600| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @inproceedings{Zhang2015CharacterlevelCN, title={Character-level Convolutional Networks for Text Classification}, author={Xiang Zhang and Junbo Jake Zhao and Yann LeCun}, booktitle={NIPS}, year={2015} } ``` ### Contributions Thanks to [@jxmorris12](https://github.com/jxmorris12), [@thomwolf](https://github.com/thomwolf), [@lhoestq](https://github.com/lhoestq), [@lewtun](https://github.com/lewtun) for adding this dataset.

m-a-p/PIN-100M

m-a-p

--- license: apache-2.0 language: - en - zh configs: - config_name: pin data_files: - split: train path: - data/DocLayNet/DocLayNet.jsonl tags: - multimodal - interleaved size_categories: - 100B<n<1T pretty_name: pin-100m --- # PIN-100M The full version of the dataset, related to the paper "PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents" Paper: https://arxiv.org/abs/2406.13923 This dataset contains 100M samples with PIN format. **Please note that the required storage space exceeds 150TB!!** 🚀 News [ 2024.12.20 ] !NEW! 🔥The currently available version is not the complete version; this project is still ongoing! (It has been released early because we reached the private storage limit on Hugging Face.) <img src="assets/intro.png"> ## 0 Usage Download ALL files ```bash huggingface-cli download m-a-p/PIN-100M --repo-type=dataset --resume-download --local-dir "your_local_path" ``` Download ONLY **Jsonl** files ```bash huggingface-cli download m-a-p/PIN-100M --repo-type=dataset --resume-download --include "*.jsonl" --local-dir "your_local_path" ``` Decompression ```bash cat data.tar.part* > data.tar tar -xvf data.tar ``` ## 1 Dataset statistics **Working** Storage space statistics may have some error, so these values are for reference only. ## 2 Data Structure ### 2.1 Subsets We process 8 subsets, including PIN-PMC, DocLayNet, Linux-CN, chinese-markdown, OBELICS, MMC4, leetcode, and PG19. <img src="assets/dataset-example.png"> Note: We do not release the PIN-arXiv subset in the preview version. ### 2.2 Folder Structure The directory `content images` holds the images mentioned within the markdown text, and `overall images` display the overall visual representation of the markdown files. Moreover, the `JSONL` file encapsulate the textual content along with associated data details. An example subset: ``` example_dataset/ │ ├── content_image/ ├── overall_image/ └── example_dataset.jsonl ``` A subset with multiple parts: ``` example_dataset/ │ ├── part00/ │ ├── content_image/ │ ├── overall_image/ │ └── part00.jsonl │ ├── part01/ │ ├── content_image/ │ ├── overall_image/ │ └── part01.jsonl │ ... - More similar parts ``` ### 2.3 content_image Folder This folder contains all the content images used in the markdown files. Note: All images need to be converted to PNG format. The filename should be unique within the folder. ``` content_image/ │ ├── 1.png ├── 2.png ... ``` ### 2.4 overall_image Folder This folder contains all the overall images for each sample. Note: All images need to be converted to PNG format. The filename should be unique within the folder. ``` overall_image/ │ ├── 1.png ├── 2.png ... ``` #### 2.5 JSON Lines Format we provide a detailed example of the annotations included with each data entry. ``` { "id": 1919, "meta": { "language": "en", "oi_exist": true, "oi_source": "compiling", "source_dataset": "example_source (e.g. OBELICS)", "ori_meta": { "document_url": "https://www.example.com/2022/02/21/example/", ... } }, "doc_id": 1997, "page_id": 0, "date_download": "2024-03-01" }, "license": "CC-BY-4.0", "quality_signals": { "doc_length": 100, ... }, "content_image": [ "content_image/1997-0.png", "content_image/1997-1.png" ], "md": "<img src='content_image/1997-0.png'>\n\nThis is a fake sample data line, just for show.\n\nThis is a fake sample data line, just for show.\n\n<img src='content_image/1997-1.png'>\n\nThis is a fake sample data line, just for show.", "overall_image": "overall_image/1997.png" } ``` Field Descriptions: **Field Descriptions:** - **id**: Unique identifier for each entry. - **meta**: Metadata for each multimodal document entry. - **language**: The document's language, such as Chinese (zh) or English (en). - **source_dataset**: If the document is converted from another dataset, the original dataset name is noted here; otherwise, it is None. - **doc_id**: A unique document identifier providing name and other details. - **page_id**: A unique page identifier indicating the document's page number. If there is only one page, this is None. Page IDs are usually numbered starting from 1 in multi-page documents. - **date_download**: date (download), the date the document was downloaded. - **ori_meta**: Original metadata from the dataset, if available; otherwise, None. - **oi_exist**: Indicates whether an overall image exists. True or False. - **oi_source**: Source of the overall image; 'ori' for images taken from the original dataset and 'compiling' for images generated through code compilation. If this tag is missing, the image is likely compiled. - ... - **quality_signals**: Quality indicators inspired by the design of redpajama v2. - **doc_length**: Length of the document. - ... - **content_image**: List of images mentioned in the document; None if no images are present. - **overall_image**: Path to the corresponding overall image. (A list or a single path) - **md**: Contains the markdown content. - **license**: License information for the current sample. ## 3 Examples of jsonl files We selected samples consisting of short markdown documents. ### 3.1 An example of DocLynet Notably, the dataset's overall images are converted from the original dataset's PDFs into PNG format. ```json { "id": 0, "meta": { "language": "en", "oi_exist": true, "oi_source": "ori", "source_dataset": "DocLayNet", "ori_meta": null, "doc_id": "NYSE_F_2004.pdf", "page_id": "0", "date_download": "2024-3-24" }, "quality_signals": null, "license": "https://cdla.io/permissive-1-0/", "content_image": [ "content_image/34102.jpg" ], "overall_image": "overall_image/3562e47265520f7a72f3eac73aadfe19a78531698c3b50d7670b8ad9b214106b.png", "md": "<img src='content_image/34102.jpg'>\n\n# Ford Motor Company / 2004 Annual Report \n\n# R W A R D F O R W A R D \n\n" } ``` ### 3.2 An example of OBELICS ```json { "id": 466502, "meta": { "language": "en", "oi_exist": true, "oi_source": "compiling", "source_dataset": "OBELICS", "ori_meta": { "document_url": "https://www.donegaldaily.com/2022/02/21/watch-incredible-storm-surge-at-portsalon-golf-club/", "unformatted_src": "https://www.donegaldaily.com/wp-content/uploads/2022/02/Screenshot-2022-02-21-at-17.54.30.jpg", "src": "https://www.donegaldaily.com/wp-content/uploads/2022/02/Screenshot-2022-02-21-at-17.54.30.jpg", "formatted_filename": "Screenshot at", "rendered_width": 817, "rendered_height": 419, "original_width": 817, "original_height": 419, "format": "jpeg", "general_meta": { "url": "https://www.donegaldaily.com/2022/02/21/watch-incredible-storm-surge-at-portsalon-golf-club/", "warc_filename": "crawl-data/CC-MAIN-2022-27/segments/1656103271864.14/warc/CC-MAIN-20220626192142-20220626222142-00308.warc.gz", "warc_record_offset": 795020636, "warc_record_length": 31271 } }, "doc_id": 98496, "page_id": 0, "date_download": "2024-4-22" }, "md": "<img src='content_image/98496-0.png'>\n\nThe golf course at Portsalon Golf Club took a battering today as a result of Storm Franklin.\n\nDonegal had been left battered and bruised overnight after Storm Franklin ripped across the county.\n\nThere were trees down on the approach roads to Donegal Town and in Gartan.\n\nThere were also trees down in Inishowen while there is also heavy water reported along the sides of roads with motorists asked to slow down and not put themselves in danger.\n\nDonegal’s coastline took a huge impact with massive waves reported along the coastline around the county.\n\nThe video, taken by Johnny Shields was taken from the tee box of the third hole.", "license": "CC-BY-4.0", "quality_signals": null, "content_image": [ "content_image/98496-0.png" ], "overall_image": "overall_image/98496-0.png" } ``` ### 3.3 An example of chinese-markdown ```json { "id": 7, "meta": { "language": "zh", "oi_exist": true, "oi_source": "compiling", "source_dataset": "chinese-markdown", "ori_meta": null, "doc_id": 7, "page_id": null, "date_download": "2024-04-30" }, "md": "---\ntitle: 常见问题 QA\ncategory: 其它\norder: 1\n---\n\n> 持续更新中...\n> 如有问题可以到 <https://github.com/alibaba/ice/issues/new> 反馈\n\n## ICE 的浏览器兼容策略是什么\n\n由于 ICE 优先使用 React 16+，其需要的最低 IE 版本为 11，如果您需要在以下的版本使用，您可能需要引入一些 polyfill 来支持 `Map`, `Set` 等特性。参考[React 官网说明](https://reactjs.org/blog/2017/09/26/react-v16.0.html#javascript-environment-requirements)。\n\n以下代码可以帮助你在低版本 IE 下自动跳转到我们提供的提示浏览器升级页面。当然您也可以使用自定义的浏览器升级页面。\n\n```\n<!--[if lt IE 11]>\n<script>location.href = \"//www.taobao.com/markets/tbhome/ali-page-updater\"; </script>\n<![endif]-->\n```\n\n添加如上代码后，如果使用 IE11 及以下浏览器访问页面，则会自动跳转到统一引导升级浏览器的页面。\n\n## WebStorm/IDEA 编辑器卡顿现象\n\n由于项目在安装依赖后，产生文件夹 `node_modules` 含有较多的碎小文件，编辑器在索引文件引起的卡顿。\nWebStorm 中尤为明显，可通过 exclude `node_modules` 目录，不需要检索该文件夹下的内容。\n\n## 如何设置网页在浏览器 Tab 上面的 Icon (favicon)\n\n细心的同学可能会看到页面在浏览器 Tab 上面会有自定义的 Icon：\n\n\n\n如果你想要在自己站点上面加上这个 Icon 可以按照如下步骤添加：\n\n1. 准备一个 Icon，文件格式可以为 `.png` 或者 `.ico`，正方形，分辨率可以是 32x32px 或者 64x64px 文件体积要求尽可能小。\n2. 上传 CDN 拿到一个 url 或者在自己服务器配置静态资源服务\n3. 在 HTML 页面 `<head>` 标签里面添加如下代码：`<link rel=\"shortcut icon\" href=\"your-icon-url\">`\n \n\n这样就添加成功啦！\n\n## 如何在页面显示原始的 HTML 内容\n\n出于安全方面的考虑，React 默认会将节点中 html 代码进行转义，比如：\n\n```jsx\nclass Demo extends Component {\n render() {\n const content = 'hello <span>world</span>';\n return <div>{content}</div>;\n }\n}\n\n// 输出 hello <span>world</span>\n```\n\n如上，`<span>` 标签并不会在页面上被解析，而是被当成字符串输出了。React 提供了 `dangerouslySetInnerHTML` 属性帮助我们进行类似 `innerHTML` 的操作：\n\n```jsx\nclass Demo extends Component {\n render() {\n const content = 'hello <span>world</span>';\n return <div dangerouslySetInnerHTML={{ __html: content }} />;\n }\n}\n\n// 输出 hello world\n```\n\n更多内容请参考 [Dangerously Set innerHTML](https://reactjs.org/docs/dom-elements.html#dangerouslysetinnerhtml)\n\n## 之前创建的项目，遇到如下报错怎么办\n\n\n\n这是由于 ES6 Modules 的标准在物料中不兼容导致的。您可以把 `src/navs.js` 中最后一行修改为：\n\n```js\nexport const headerNavs = transform([\n ...autoGenHeaderNavs,\n ...customHeaderNavs,\n]);\n\nexport const asideNavs = transform([...autoGenAsideNavs, ...customAsideNavs]);\n```", "license": "MIT", "quality_signals": null, "content_image": [ "content_image/7-0.png" ], "overall_image": "overall_image/7.png" } ``` ### 3.4 An example of leetcode ```json { "id": 1, "meta": { "language": "en", "doc_id": 1, "page_id": null, "oi_exist": true, "oi_source": "compiling", "source_dataset": "leetcode", "date_download": "2024-05-05", "ori_meta": { "slug": "two-sum", "difficulty": "Easy" } }, "quality_signals": null, "license": "MIT", "content_image": null, "md": "# Two Sum\n\n- slug: two-sum\n- difficulty: Easy\n\nGiven an array of integers `nums` and an integer `target`, return _indices of the two numbers such that they add up to `target`_.\n\nYou may assume that each input would have **_exactly_ one solution**, and you may not use the _same_ element twice.\n\nYou can return the answer in any order.\n\n**Example 1:**\n\n**Input:** nums = \\[2,7,11,15\\], target = 9\n**Output:** \\[0,1\\]\n**Explanation:** Because nums\\[0\\] + nums\\[1\\] == 9, we return \\[0, 1\\].\n\n**Example 2:**\n\n**Input:** nums = \\[3,2,4\\], target = 6\n**Output:** \\[1,2\\]\n\n**Example 3:**\n\n**Input:** nums = \\[3,3\\], target = 6\n**Output:** \\[0,1\\]\n\n**Constraints:**\n\n* `2 <= nums.length <= 104`\n* `-109 <= nums[i] <= 109`\n* `-109 <= target <= 109`\n* **Only one valid answer exists.**\n\n**Follow-up:** Can you come up with an algorithm that is less than `O(n2)` time complexity?\n\n## A solution in Java\n\n```java\nimport java.util.HashMap;\nimport java.util.Map;\n\npublic int[] twoSum(int[] nums, int target) {\n Map<Integer, Integer> map = new HashMap<>();\n for (int i = 0; i < nums.length; i++) {\n int complement = target - nums[i];\n if (map.containsKey(complement)) {\n return new int[]{map.get(complement), i};\n }\n map.put(nums[i], i);\n }\n throw new IllegalArgumentException(\"No two sum solution\");\n}\n```\nThe algorithm leverages a hash map (unordered_map in C++, HashMap in Java, dictionary in Python, and Map in JavaScript). It iterates through the given 'nums' array and calculates the complementary value (target - current value). If the complementary value is already in the hash map, it means that we found a solution, and we return those indices. If the complement is not in the hash map, we store the current element in the hash map with its index. If the algorithm doesn't find the solution, it returns an empty array or throws an exception (in Java).\n\nThis approach has a time complexity of O(n) and a space complexity of O(n) as well.\n \n\n## A solution in C++\n\n```cpp\n#include <vector>\n#include <unordered_map>\n\nstd::vector<int> twoSum(std::vector<int>& nums, int target) {\n std::unordered_map<int, int> map;\n for (int i = 0; i < nums.size(); i++) {\n int complement = target - nums[i];\n if (map.find(complement) != map.end()) {\n return {map[complement], i};\n }\n map[nums[i]] = i;\n }\n return {};\n}\n```\nThe algorithm leverages a hash map (unordered_map in C++, HashMap in Java, dictionary in Python, and Map in JavaScript). It iterates through the given 'nums' array and calculates the complementary value (target - current value). If the complementary value is already in the hash map, it means that we found a solution, and we return those indices. If the complement is not in the hash map, we store the current element in the hash map with its index. If the algorithm doesn't find the solution, it returns an empty array or throws an exception (in Java).\n\nThis approach has a time complexity of O(n) and a space complexity of O(n) as well.\n \n\n## A solution in Python\n\n```python\ndef twoSum(nums, target):\n map = {}\n for i, num in enumerate(nums):\n complement = target - num\n if complement in map:\n return [map[complement], i]\n map[num] = i\n return []\n```\nThe algorithm leverages a hash map (unordered_map in C++, HashMap in Java, dictionary in Python, and Map in JavaScript). It iterates through the given 'nums' array and calculates the complementary value (target - current value). If the complementary value is already in the hash map, it means that we found a solution, and we return those indices. If the complement is not in the hash map, we store the current element in the hash map with its index. If the algorithm doesn't find the solution, it returns an empty array or throws an exception (in Java).\n\nThis approach has a time complexity of O(n) and a space complexity of O(n) as well.\n \n\n## A solution in Javascript\n\n```javascript\nfunction twoSum(nums, target) {\n const map = new Map();\n for (let i = 0; i < nums.length; i++) {\n const complement = target - nums[i];\n if (map.has(complement)) {\n return [map.get(complement), i];\n }\n map.set(nums[i], i);\n }\n return [];\n}\n```\nThe algorithm leverages a hash map (unordered_map in C++, HashMap in Java, dictionary in Python, and Map in JavaScript). It iterates through the given 'nums' array and calculates the complementary value (target - current value). If the complementary value is already in the hash map, it means that we found a solution, and we return those indices. If the complement is not in the hash map, we store the current element in the hash map with its index. If the algorithm doesn't find the solution, it returns an empty array or throws an exception (in Java).\n\nThis approach has a time complexity of O(n) and a space complexity of O(n) as well.\n \n", "overall_image": "overall_image/1.png" } ``` ### 3.5 An example of linux-cn ```json { "id": 8, "meta": { "language": "zh", "doc_id": 134, "page_id": null, "oi_exist": true, "oi_source": "compiling", "source_dataset": "linux-cn", "date_download": "2024-05-06", "ori_meta": { "title": "Ubuntu 11.04正式发布！", "author": "", "fromurl": "", "summary": "刚才接到的消息，Ubuntu 11.04已经正式发布！\r\n\r\n超快！易用！免费！\r\nUbuntu操作系统为世界上数以百万计的电脑、上网本和服务器提供了动力！\r\nUbuntu可以为你完成各种工作，管理你的文件、打印机、摄像头和MP3！并且它 ...", "pic": "/data/attachment/album/201104/28/193933lnqqwwwn8l64wbn1.jpg.thumb.jpg", "largepic": "/data/attachment/album/201104/28/193933lnqqwwwn8l64wbn1.jpg", "titlepic": false, "thumb": false, "islctt": false, "selector": "", "translator": "", "reviewer": "", "editorchoice": false, "tags": [ "Ubuntu 11.04", "发布" ], "category": "新闻", "count": { "commentnum": 0, "favtimes": 0, "likes": 0, "sharetimes": 1, "viewnum": 6165 }, "comments_data": [ ], "related": [ ], "excerpt": "刚才接到的消息，Ubuntu 11.04已经正式发布！\r\n\r\n超快！易用！免费！\r\nUbuntu操作系统为世界上数以百万计的电脑、上网本和服务器提供了动力！\r\nUbuntu可以为你完成各种工作，管理你的文件、打印机、摄像头和MP3！并且它 ...", "date": "2011-05-09 13:24:00", "updated": "2011-05-09 13:24:00", "id": 134, "permalink": "/article-134-1.html" } }, "quality_signals": null, "license": "CC-BY-NC-4.0", "content_image": [ "content_image/album_201104_28_193933lnqqwwwn8l64wbn1.jpg", "content_image/album_201104_28_193935sy4l3bh4bh1ycbbc.jpg", "content_image/album_201104_28_193936lyvc36fwv91l1359.jpg", "content_image/album_201104_28_19393800rpr8pf0s8p8w0s.jpg" ], "md": "# Ubuntu 11.04正式发布！\n\n刚才接到的消息，Ubuntu 11.04已经正式发布！ \n \n 超快！易用！免费！ \n Ubuntu操作系统为世界上数以百万计的电脑、上网本和服务器提供了动力！ \n Ubuntu可以为你完成各种工作，管理你的文件、打印机、摄像头和MP3！并且它还带有数千个免费程序。 \n \n <img src=\"content_image/album_201104_28_193933lnqqwwwn8l64wbn1.jpg\" alt=\"\" title=\"\"> \n **数千个免费程序** \n \n <img src=\"content_image/album_201104_28_193935sy4l3bh4bh1ycbbc.jpg\" alt=\"\" title=\"\"> \n **终生免费升级** \n \n <img src=\"content_image/album_201104_28_193936lyvc36fwv91l1359.jpg\" alt=\"\" title=\"\"> \n **内建的病毒防护** \n \n <img src=\"content_image/album_201104_28_19393800rpr8pf0s8p8w0s.jpg\" alt=\"\" title=\"\"> \n **云中的音乐** \n \n 下载地址：\n\n\n\n\n> 列表： \n> <http://releases.ubuntu.com/11.04/> \n> 桌面版： \n> <http://www.ubuntu.com/download/ubuntu/download> \n> 服务器版： \n> <http://www.ubuntu.com/download/server/download>\n\n\n\n \n BT种子地址：\n\n\n\n\n> \n> * [ubuntu-11.04-alternate-amd64.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-alternate-amd64.iso.torrent)\n> * [ubuntu-11.04-alternate-i386.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-alternate-i386.iso.torrent)\n> * [ubuntu-11.04-desktop-amd64.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-desktop-amd64.iso.torrent)\n> * [ubuntu-11.04-desktop-i386.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-desktop-i386.iso.torrent)\n> * [ubuntu-11.04-netbook-i386.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-netbook-i386.iso.torrent)\n> * [ubuntu-11.04-server-amd64.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-server-amd64.iso.torrent)\n> * [ubuntu-11.04-server-i386.iso.torrent](http://releases.ubuntu.com/11.04/ubuntu-11.04-server-i386.iso.torrent)\n> \n> \n> \n\n\n\n \n 当前尚无DVD版本出现 \n \n \n \n 该贴已经同步到 [wxy的微博](http://api.t.sina.com.cn/1747813575/statuses/9786340397) \n \n \n \n\n\n \n\n\n*[本文内容由 wxy 提供](thread-7135-1-1.html)*\n \n\n\n\n 已同步至 [wxy的微博](http://api.t.sina.com.cn/1747813575/statuses/10347235925)", "overall_image": "overall_image/134.png" } ``` ### 3.6 An example of mmc-core-ff ```json { "meta": { "language": "en", "oi_exist": true, "oi_source": "compiling", "doc_id": 11, "page_id": 0, "source_dataset": "mmc4-core-ff", "source_jsonl": "mmc4-core-ff/docs_no_face_shard_10375_v3.jsonl", "ori_meta": { "url": "http://position-light.blogspot.com/2015/06/whats-up-with-reading-and-northern.html", "text_list": [ "The Position Light: What's Up with the Reading and Northern?", "The Reading and Northern has been a rare bright spot in the world of signaling.", "A commitment to its Reading heritage has resulted in numerous signaling structures being preserved along with attempts to install \"classic\" signaling where new signaling is being installed on its mostly unsignaled territory.", "The R&N also controls the former Conrail Lehigh Line and for one reason or another has decided not to touch the surviving LVRR signaling along that route.", "Still, I am still not completely clear on the full extent of the R&N's signal preservation efforts as hinted at in a number of photos I have come across.", "We begin near the town of Mach Chunk where the R&N runs a tourist operation in the Lehigh Gorge.", "i have bicycles along the right of way a number of time and I never noticed this cantilever mast and its freshly painted (albeit turned) signals.", "Is this a sign of a new interlocking or signaling project?", "Pottsville is the location of some preserved Reading signal bridges and a tower.", "Both have been out of service for decades, but then I find a photo showing what appears to be a lit Reading US&S three headed signal displaying a restricting indication.", "Could be that the photographer is having some fun with Photoshoppe, or it could be another R&N instance of an \"island\" interlocking designed to eliminate the need for crews to hand throw switches.", "Clearly I need to take another field trip to the area, but if anyone has any information (or photos) please let me know.", "Yes, that dual Signal Cantilever was taken from Schuylkill Haven and refurbished and placed into service as part of the new CP COAL Interlocking aptly named for the nearby town of Coalport.", "This new interlocking controls R&N connector feed track and switch from Nesquehoning Jct onto the NS Lehigh Line.", "Be aware, that R&N is constructing a new Y connector bridge over the Lehigh River.", "The switch at Nesquehoning Jct as well at the Y connecting point northwest along the old CNJ into Nesquehoning and the other apex connecting point at the old Lehigh Valley overpass will make up the new Y along with the new bridge.", "Expect the R&N to make all 3 points new CP Interlockings as NS will also use the new route to get to Reading & Philadelphia directly off the Lehigh Line.", "Coming attractions for 2016.", "Also, R&N is talking about a new signaled controlled passing track siding midway between Port Clinton and Reading.", "Believe they will leverage the siding that's already in place (don't know name of that area, but, between two grade crossings).", "Could see even more new R&N signaling if Distants are added to the mix as well.", "Thank you for the information!", "I knew something was up with them.", "Mike - Have updates with pics for R&N.", "Can share them with you but not sure of best way via e-mail or blog address.", "Can you provide and I can forward what I have?", "You can drop a line to [email protected] Thanks!" ], "image_info": [ { "face_detections": null, "image_id": "11-0.png", "image_name": "338146395110.jpg", "matched_sim": 0.2532651722, "matched_text_index": 12, "raw_url": "http://www.railpictures.net/images/d2/6/0/1/6601.1425352225.jpg" }, { "face_detections": null, "image_id": "11-1.png", "image_name": "75dca5908f72.jpg", "matched_sim": 0.2665729225, "matched_text_index": 18, "raw_url": "http://www.railpictures.net/images/d2/0/3/5/5035.1411414707.jpg" } ], "similarity_matrix": [ [ 0.2208167017, 0.2216126323, 0.2174896896, 0.2322429568, 0.1835552454, 0.1933521628, 0.1114124805, 0.1734878719, 0.1712893993, 0.1681747884, 0.2151062787, 0.1558438838, 0.2532651722, 0.2029514462, 0.1683746874, 0.1972030103, 0.2269551754, 0.1497862041, 0.2076308429, 0.1459720433, 0.1406365782, 0.1131924018, 0.0637710392, 0.1748069972, 0.1665924788, 0.1288469583, 0.1271829307 ], [ 0.2275835425, 0.2447894663, 0.2326766551, 0.2530837059, 0.197981596, 0.1727618128, 0.1842465401, 0.2053450346, 0.2174785137, 0.2176187485, 0.216365099, 0.152155906, 0.2394197732, 0.2332755029, 0.2077463269, 0.2373518944, 0.2454088479, 0.1549753994, 0.2665729225, 0.2099550366, 0.163154155, 0.1208794788, 0.0917887241, 0.1707040668, 0.1544941813, 0.1439596266, 0.1319040358 ] ], "could_have_url_duplicate": 0 }, "date_download": "2024-05-11" }, "md": "The Position Light: What's Up with the Reading and Northern? The Reading and Northern has been a rare bright spot in the world of signaling. A commitment to its Reading heritage has resulted in numerous signaling structures being preserved along with attempts to install \"classic\" signaling where new signaling is being installed on its mostly unsignaled territory. The R&N also controls the former Conrail Lehigh Line and for one reason or another has decided not to touch the surviving LVRR signaling along that route. Still, I am still not completely clear on the full extent of the R&N's signal preservation efforts as hinted at in a number of photos I have come across. We begin near the town of Mach Chunk where the R&N runs a tourist operation in the Lehigh Gorge. i have bicycles along the right of way a number of time and I never noticed this cantilever mast and its freshly painted (albeit turned) signals. Is this a sign of a new interlocking or signaling project? Pottsville is the location of some preserved Reading signal bridges and a tower. Both have been out of service for decades, but then I find a photo showing what appears to be a lit Reading US&S three headed signal displaying a restricting indication. Could be that the photographer is having some fun with Photoshoppe, or it could be another R&N instance of an \"island\" interlocking designed to eliminate the need for crews to hand throw switches. Clearly I need to take another field trip to the area, but if anyone has any information (or photos) please let me know. Yes, that dual Signal Cantilever was taken from Schuylkill Haven and refurbished and placed into service as part of the new CP COAL Interlocking aptly named for the nearby town of Coalport.\n\n\n\n<img src='content_image/11-0.png'>\n\nThis new interlocking controls R&N connector feed track and switch from Nesquehoning Jct onto the NS Lehigh Line. Be aware, that R&N is constructing a new Y connector bridge over the Lehigh River. The switch at Nesquehoning Jct as well at the Y connecting point northwest along the old CNJ into Nesquehoning and the other apex connecting point at the old Lehigh Valley overpass will make up the new Y along with the new bridge. Expect the R&N to make all 3 points new CP Interlockings as NS will also use the new route to get to Reading & Philadelphia directly off the Lehigh Line. Coming attractions for 2016. Also, R&N is talking about a new signaled controlled passing track siding midway between Port Clinton and Reading.\n\n\n\n<img src='content_image/11-1.png'>\n\nBelieve they will leverage the siding that's already in place (don't know name of that area, but, between two grade crossings). Could see even more new R&N signaling if Distants are added to the mix as well. Thank you for the information! I knew something was up with them. Mike - Have updates with pics for R&N. Can share them wi", "license": "ODC-BY", "quality_signals": null, "content_image": [ "content_image/11-0.png", "content_image/11-1.png" ], "overall_image": "overall_image/11-0.png" } ``` ### 3.7 An example of PG19 ```json { "meta": { "language": "en", "oi_exist": true, "oi_source": "compiling", "doc_id": 871, "page_id": 0, "source_dataset": "pg19", "split": "train", "ori_meta": { "url": "http://www.gutenberg.org/ebooks/9304", "short_book_title": "Initiation into Philosophy by Emile Faguet", "publication_date": 1914 }, "date_download": "2024-05-10" }, "md": "# Initiation into Philosophy by Emile Faguet \n\n Produced by Ted Garvin, Thomas Hutchinson and PG Distributed Proofreaders \n\n \n\n \n\n \n\n \n\n INITIATION INTO PHILOSOPHY \n\n \nBy Emile Faguet \n\n Of the French Academy \n\n \nAuthor of \"The Cult Of Incompetence,\" \"Initiation Into Literature,\" etc. \n\n \nTranslated from the French by Sir Homer Gordon, Bart. \n\n 1914 \n\n \n\n \nPREFACE \n\n This volume, as indicated by the title, is designed to show the way to the beginner, to satisfy and more espec ially to excite his initial curiosity. It affords an adequate idea of the march of facts and of ideas. The rea der is led, somewhat rapidly, from the remote origins to the most recent efforts of the human mind. \n\n It should be a convenient repertory to which the mind may revert in order to see broadly the general opinion o f an epoch--and what connected it with those that followed or preceded it. It aims above all at being _a frame _ in which can conveniently be inscribed, in the course of further studies, new conceptions more detailed and more thoroughly examined. \n\n It will have fulfilled its design should it incite to research and meditation, and if it prepares for them cor rectly. \n\n E. FAGUET. \n\n \n\n \nCONTENTS \n\n \nPART I ANTIQUITY \n\n \nCHAPTER I BEFORE SOCRATES \n\n Philosophical Interpreters of the Universe, of the Creation and Constitution of the World. \n\n \nCHAPTER II THE SOPHISTS \n\n Logicians and Professors of Logic, and of the Analysis of Ideas, and of Discussion. \n\n \nCHAPTER III SOCRATES \n\n Philosophy Entirely Reduced to Morality, and Morality Considered as the End of all Intellectual Activity. \n\n \nCHAPTER IV PLATO \n\n Plato, like Socrates, is Pre-eminently a Moralist, but he Reverts to General Consideration of the Universe, an d Deals with Politics and Legislation. \n\n \nCHAPTER V ARISTOTLE", "license": "Apache 2.0", "quality_signals": null, "content_image": null, "overall_image": "overall_image/871-0.png" } ``` ### 3.8 An example of PIN-PMC ```json { "meta": { "language": "en", "doc_id": "PMC3015258", "oi_exist": true, "oi_source": "ori", "source_dataset": "PIN-PMC", "ori_meta": null, "page_id": null, "date_download": "2024-05-28" }, "md": "# A Simple Stereoscopic Endoscope\n\n## Abstract\n\nA very simple method is described for producing and viewing stereoscopic endoscopic images.\nThe addition of two simple prisms to the end of a conventional television-monitored endoscope with a simple viewing device produces a stereoscopic endoscope which appears to be suitable for surgical use......", "license": [ "https://www.ncbi.nlm.nih.gov/pmc/tools/textmining/" ], "quality_signals": { "doc_length": 8269 }, "content_image": [ "content_image/PMC3015258/jsls-2-1-67-g03.jpg", "content_image/PMC3015258/jsls-2-1-67-g04.jpg", "content_image/PMC3015258/jsls-2-1-67-g01.jpg", "content_image/PMC3015258/jsls-2-1-67-g02.jpg", "content_image/PMC3015258/jsls-2-1-67-g05.jpg" ], "overall_image": [ "overall_image/PMC3015258/jsls-2-1-67_3.png", "overall_image/PMC3015258/jsls-2-1-67_0.png", "overall_image/PMC3015258/jsls-2-1-67_1.png", "overall_image/PMC3015258/jsls-2-1-67_2.png" ], "id": 60827 } ``` ## 4 License For data generated or produced by us, please adhere to the Apache 2.0 License. For data sourced from third parties, compliance with the respective third-party licenses is required. ## Citation ``` @misc{2406.13923, Author = {Junjie Wang and Yin Zhang and Yatai Ji and Yuxiang Zhang and Chunyang Jiang and Yubo Wang and Kang Zhu and Zekun Wang and Tiezhen Wang and Wenhao Huang and Jie Fu and Bei Chen and Qunshu Lin and Minghao Liu and Ge Zhang and Wenhu Chen}, Title = {PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents}, Year = {2024}, Eprint = {arXiv:2406.13923}, } ```

MoreTorque/rlogs

MoreTorque

--- license: apache-2.0 --- ## Dataset Overview This dataset consists of bz2 compressed rlogs captured from OpenPilot. These logs do not contain any user-sensitive information. The primary purpose of this dataset is to facilitate data-driven solutions for improving lateral and longitudinal control in community-supported vehicles. # Contents The rlogs are composed of various events as defined in the OpenPilot log schema. To ensure user privacy, many event types have been excluded. The following is the list of events that remain in the log files: ``` * CarState * LiveParameters * CarControl * LateralPlanDEPRECATED * CarOutput * CarParams * ModelV2 * LiveTorqueParameters * LiveCalibration * Sendcan * Can * LongitudinalPlan * LiveLocationKalman ( Only OrientaionNED, CalibratedOrientaionNED, and AngularVelocityCalibrated have been kept )

zy1111/test

zy1111

--- license: apache-2.0 ---

HuggingFaceH4/MATH-500

HuggingFaceH4

--- task_categories: - text-generation language: - en pretty_name: MATH-500 --- # Dataset Card for MATH-500 <!-- Provide a quick summary of the dataset. --> This dataset contains a subset of 500 problems from the MATH benchmark that OpenAI created in their _Let's Verify Step by Step_ paper. See their GitHub repo for the source file: https://github.com/openai/prm800k/tree/main?tab=readme-ov-file#math-splits

GEM/wiki_lingua

GEM

--- annotations_creators: - none language_creators: - unknown language: - ar - cs - de - en - es - fr - hi - id - it - ja - ko - nl - pt - ru - th - tr - vi - zh license: - cc-by-nc-sa-3.0 multilinguality: - multilingual size_categories: - unknown source_datasets: - original task_categories: - summarization task_ids: [] pretty_name: wiki_lingua --- # Dataset Card for GEM/wiki_lingua ## Dataset Description - **Homepage:** None (See Repository) - **Repository:** https://github.com/esdurmus/Wikilingua - **Paper:** https://www.aclweb.org/anthology/2020.findings-emnlp.360/ - **Leaderboard:** N/A - **Point of Contact:** Faisal Ladhak, Esin Durmus ### Link to Main Data Card You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/wiki_lingua). ### Dataset Summary Placeholder You can load the dataset via: ``` import datasets data = datasets.load_dataset('GEM/wiki_lingua') ``` The data loader can be found [here](https://huggingface.co/datasets/GEM/wiki_lingua). #### website None (See Repository) #### paper https://www.aclweb.org/anthology/2020.findings-emnlp.360/ #### authors Faisal Ladhak (Columbia University), Esin Durmus (Stanford University), Claire Cardie (Cornell University), Kathleen McKeown (Columbia University) ## Dataset Overview ### Where to find the Data and its Documentation #### Webpage <!-- info: What is the webpage for the dataset (if it exists)? --> <!-- scope: telescope --> None (See Repository) #### Download <!-- info: What is the link to where the original dataset is hosted? --> <!-- scope: telescope --> https://github.com/esdurmus/Wikilingua #### Paper <!-- info: What is the link to the paper describing the dataset (open access preferred)? --> <!-- scope: telescope --> https://www.aclweb.org/anthology/2020.findings-emnlp.360/ #### BibTex <!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. --> <!-- scope: microscope --> @inproceedings{ladhak-etal-2020-wikilingua, title = "{W}iki{L}ingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization", author = "Ladhak, Faisal and Durmus, Esin and Cardie, Claire and McKeown, Kathleen", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.findings-emnlp.360", doi = "10.18653/v1/2020.findings-emnlp.360", pages = "4034--4048", abstract = "We introduce WikiLingua, a large-scale, multilingual dataset for the evaluation of cross-lingual abstractive summarization systems. We extract article and summary pairs in 18 languages from WikiHow, a high quality, collaborative resource of how-to guides on a diverse set of topics written by human authors. We create gold-standard article-summary alignments across languages by aligning the images that are used to describe each how-to step in an article. As a set of baselines for further studies, we evaluate the performance of existing cross-lingual abstractive summarization methods on our dataset. We further propose a method for direct cross-lingual summarization (i.e., without requiring translation at inference time) by leveraging synthetic data and Neural Machine Translation as a pre-training step. Our method significantly outperforms the baseline approaches, while being more cost efficient during inference.", } #### Contact Name <!-- quick --> <!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. --> <!-- scope: periscope --> Faisal Ladhak, Esin Durmus #### Contact Email <!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. --> <!-- scope: periscope --> [email protected], [email protected] #### Has a Leaderboard? <!-- info: Does the dataset have an active leaderboard? --> <!-- scope: telescope --> no ### Languages and Intended Use #### Multilingual? <!-- quick --> <!-- info: Is the dataset multilingual? --> <!-- scope: telescope --> yes #### Covered Dialects <!-- info: What dialects are covered? Are there multiple dialects per language? --> <!-- scope: periscope --> Dataset does not have multiple dialects per language. #### Covered Languages <!-- quick --> <!-- info: What languages/dialects are covered in the dataset? --> <!-- scope: telescope --> `English`, `Spanish, Castilian`, `Portuguese`, `French`, `German`, `Russian`, `Italian`, `Indonesian`, `Dutch, Flemish`, `Arabic`, `Chinese`, `Vietnamese`, `Thai`, `Japanese`, `Korean`, `Hindi`, `Czech`, `Turkish` #### Whose Language? <!-- info: Whose language is in the dataset? --> <!-- scope: periscope --> No information about the user demographic is available. #### License <!-- quick --> <!-- info: What is the license of the dataset? --> <!-- scope: telescope --> cc-by-nc-sa-3.0: Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) #### Intended Use <!-- info: What is the intended use of the dataset? --> <!-- scope: microscope --> The dataset was intended to serve as a large-scale, high-quality benchmark dataset for cross-lingual summarization. #### Primary Task <!-- info: What primary task does the dataset support? --> <!-- scope: telescope --> Summarization #### Communicative Goal <!-- quick --> <!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. --> <!-- scope: periscope --> Produce a high quality summary for the given input article. ### Credit #### Curation Organization Type(s) <!-- info: In what kind of organization did the dataset curation happen? --> <!-- scope: telescope --> `academic` #### Curation Organization(s) <!-- info: Name the organization(s). --> <!-- scope: periscope --> Columbia University #### Dataset Creators <!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). --> <!-- scope: microscope --> Faisal Ladhak (Columbia University), Esin Durmus (Stanford University), Claire Cardie (Cornell University), Kathleen McKeown (Columbia University) #### Who added the Dataset to GEM? <!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. --> <!-- scope: microscope --> Jenny Chim (Queen Mary University of London), Faisal Ladhak (Columbia University) ### Dataset Structure #### Data Fields <!-- info: List and describe the fields present in the dataset. --> <!-- scope: telescope --> gem_id -- The id for the data instance. source_language -- The language of the source article. target_language -- The language of the target summary. source -- The source document. #### Example Instance <!-- info: Provide a JSON formatted example of a typical instance in the dataset. --> <!-- scope: periscope --> { "gem_id": "wikilingua_crosslingual-train-12345", "gem_parent_id": "wikilingua_crosslingual-train-12345", "source_language": "fr", "target_language": "de", "source": "Document in fr", "target": "Summary in de", } #### Data Splits <!-- info: Describe and name the splits in the dataset if there are more than one. --> <!-- scope: periscope --> The data is split into train/dev/test. In addition to the full test set, there's also a sampled version of the test set. #### Splitting Criteria <!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. --> <!-- scope: microscope --> The data was split to ensure the same document would appear in the same split across languages so as to ensure there's no leakage into the test set. ## Dataset in GEM ### Rationale for Inclusion in GEM #### Why is the Dataset in GEM? <!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? --> <!-- scope: microscope --> This dataset provides a large-scale, high-quality resource for cross-lingual summarization in 18 languages, increasing the coverage of languages for the GEM summarization task. #### Similar Datasets <!-- info: Do other datasets for the high level task exist? --> <!-- scope: telescope --> yes #### Unique Language Coverage <!-- info: Does this dataset cover other languages than other datasets for the same task? --> <!-- scope: periscope --> yes #### Difference from other GEM datasets <!-- info: What else sets this dataset apart from other similar datasets in GEM? --> <!-- scope: microscope --> XSum covers English news articles, and MLSum covers news articles in German and Spanish. In contrast, this dataset has how-to articles in 18 languages, substantially increasing the languages covered. Moreover, it also provides a a different domain than the other two datasets. #### Ability that the Dataset measures <!-- info: What aspect of model ability can be measured with this dataset? --> <!-- scope: periscope --> The ability to generate quality summaries across multiple languages. ### GEM-Specific Curation #### Modificatied for GEM? <!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? --> <!-- scope: telescope --> yes #### GEM Modifications <!-- info: What changes have been made to he original dataset? --> <!-- scope: periscope --> `other` #### Modification Details <!-- info: For each of these changes, described them in more details and provided the intended purpose of the modification --> <!-- scope: microscope --> Previous version had separate data loaders for each language. In this version, we've created a single monolingual data loader, which contains monolingual data in each of the 18 languages. In addition, we've also created a single cross-lingual data loader across all the language pairs in the dataset. #### Additional Splits? <!-- info: Does GEM provide additional splits to the dataset? --> <!-- scope: telescope --> no ### Getting Started with the Task ## Previous Results ### Previous Results #### Measured Model Abilities <!-- info: What aspect of model ability can be measured with this dataset? --> <!-- scope: telescope --> Ability to summarize content across different languages. #### Metrics <!-- info: What metrics are typically used for this task? --> <!-- scope: periscope --> `ROUGE` #### Proposed Evaluation <!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. --> <!-- scope: microscope --> ROUGE is used to measure content selection by comparing word overlap with reference summaries. In addition, the authors of the dataset also used human evaluation to evaluate content selection and fluency of the systems. #### Previous results available? <!-- info: Are previous results available? --> <!-- scope: telescope --> no ## Dataset Curation ### Original Curation #### Original Curation Rationale <!-- info: Original curation rationale --> <!-- scope: telescope --> The dataset was created in order to enable new approaches for cross-lingual and multilingual summarization, which are currently understudied as well as open up inetersting new directions for research in summarization. E.g., exploration of multi-source cross-lingual architectures, i.e. models that can summarize from multiple source languages into a target language, building models that can summarize articles from any language to any other language for a given set of languages. #### Communicative Goal <!-- info: What was the communicative goal? --> <!-- scope: periscope --> Given an input article, produce a high quality summary of the article in the target language. #### Sourced from Different Sources <!-- info: Is the dataset aggregated from different data sources? --> <!-- scope: telescope --> no ### Language Data #### How was Language Data Obtained? <!-- info: How was the language data obtained? --> <!-- scope: telescope --> `Found` #### Where was it found? <!-- info: If found, where from? --> <!-- scope: telescope --> `Single website` #### Language Producers <!-- info: What further information do we have on the language producers? --> <!-- scope: microscope --> WikiHow, which is an online resource of how-to guides (written and reviewed by human authors) is used as the data source. #### Topics Covered <!-- info: Does the language in the dataset focus on specific topics? How would you describe them? --> <!-- scope: periscope --> The articles cover 19 broad categories including health, arts and entertainment, personal care and style, travel, education and communications, etc. The categories cover a broad set of genres and topics. #### Data Validation <!-- info: Was the text validated by a different worker or a data curator? --> <!-- scope: telescope --> not validated #### Was Data Filtered? <!-- info: Were text instances selected or filtered? --> <!-- scope: telescope --> not filtered ### Structured Annotations #### Additional Annotations? <!-- quick --> <!-- info: Does the dataset have additional annotations for each instance? --> <!-- scope: telescope --> none #### Annotation Service? <!-- info: Was an annotation service used? --> <!-- scope: telescope --> no ### Consent #### Any Consent Policy? <!-- info: Was there a consent policy involved when gathering the data? --> <!-- scope: telescope --> yes #### Consent Policy Details <!-- info: What was the consent policy? --> <!-- scope: microscope --> (1) Text Content. All text posted by Users to the Service is sub-licensed by wikiHow to other Users under a Creative Commons license as provided herein. The Creative Commons license allows such text content be used freely for non-commercial purposes, so long as it is used and attributed to the original author as specified under the terms of the license. Allowing free republication of our articles helps wikiHow achieve its mission by providing instruction on solving the problems of everyday life to more people for free. In order to support this goal, wikiHow hereby grants each User of the Service a license to all text content that Users contribute to the Service under the terms and conditions of a Creative Commons CC BY-NC-SA 3.0 License. Please be sure to read the terms of the license carefully. You continue to own all right, title, and interest in and to your User Content, and you are free to distribute it as you wish, whether for commercial or non-commercial purposes. #### Other Consented Downstream Use <!-- info: What other downstream uses of the data did the original data creators and the data curators consent to? --> <!-- scope: microscope --> The data is made freely available under the Creative Commons license, therefore there are no restrictions about downstream uses as long is it's for non-commercial purposes. ### Private Identifying Information (PII) #### Contains PII? <!-- quick --> <!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? --> <!-- scope: telescope --> no PII #### Justification for no PII <!-- info: Provide a justification for selecting `no PII` above. --> <!-- scope: periscope --> Only the article text and summaries were collected. No user information was retained in the dataset. ### Maintenance #### Any Maintenance Plan? <!-- info: Does the original dataset have a maintenance plan? --> <!-- scope: telescope --> no ## Broader Social Context ### Previous Work on the Social Impact of the Dataset #### Usage of Models based on the Data <!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? --> <!-- scope: telescope --> yes - other datasets featuring the same task ### Impact on Under-Served Communities #### Addresses needs of underserved Communities? <!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). --> <!-- scope: telescope --> no ### Discussion of Biases #### Any Documented Social Biases? <!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. --> <!-- scope: telescope --> yes ## Considerations for Using the Data ### PII Risks and Liability ### Licenses #### Copyright Restrictions on the Dataset <!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? --> <!-- scope: periscope --> `non-commercial use only` #### Copyright Restrictions on the Language Data <!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? --> <!-- scope: periscope --> `non-commercial use only` ### Known Technical Limitations

Major-TOM/Core-S2L2A

Major-TOM

--- license: cc-by-sa-4.0 tags: - earth-observation - remote-sensing - sentinel-2 - multi-spectral - satellite - geospatial size_categories: - 1M<n<10M dataset_info: - config_name: default features: - name: product_id dtype: string - name: grid_cell dtype: string - name: product_datetime dtype: string - name: thumbnail dtype: image - name: B01 dtype: binary - name: B02 dtype: binary - name: B03 dtype: binary - name: B04 dtype: binary - name: B05 dtype: binary - name: B06 dtype: binary - name: B07 dtype: binary - name: B08 dtype: binary - name: B8A dtype: binary - name: B09 dtype: binary - name: B11 dtype: binary - name: B12 dtype: binary - name: cloud_mask dtype: binary configs: - config_name: default data_files: images/*.parquet - config_name: metadata data_files: metadata.parquet --- # Core-S2L2A Contains a global coverage of Sentinel-2 (Level 2A) patches, each of size 1,068 x 1,068 pixels. | Source | Sensing Type | Number of Patches | Patch Size | Total Pixels | |--------|--------------|-------------------|------------|--------------| |Sentinel-2 Level-2A |Optical Multispectral|2,245,886|1,068 x 1,068 (10 m) | > 2.564 Trillion | ## Content | Column | Details | Resolution | |--------|---------|------------| | B01 | Coastal aerosol, 442.7 nm (S2A), 442.3 nm (S2B) | 60m | | B02 | Blue, 492.4 nm (S2A), 492.1 nm (S2B) | 10m | | B03 | Green, 559.8 nm (S2A), 559.0 nm (S2B) | 10m | | B04 | Red, 664.6 nm (S2A), 665.0 nm (S2B) | 10m | | B05 | Vegetation red edge, 704.1 nm (S2A), 703.8 nm (S2B) | 20m | | B06 | Vegetation red edge, 740.5 nm (S2A), 739.1 nm (S2B) | 20m | | B07 | Vegetation red edge, 782.8 nm (S2A), 779.7 nm (S2B) | 20m | | B08 | NIR, 832.8 nm (S2A), 833.0 nm (S2B) | 10m | | B8A | Narrow NIR, 864.7 nm (S2A), 864.0 nm (S2B) | 20m | | B09 | Water vapour, 945.1 nm (S2A), 943.2 nm (S2B) | 60m | | B11 | SWIR, 1613.7 nm (S2A), 1610.4 nm (S2B) | 20m | | B12 | SWIR, 2202.4 nm (S2A), 2185.7 nm (S2B) | 20m | | cloud_mask | Cloud Mask produced by SEnSeI | 10m | | thumbnail | RGB composite [B04, B03, B02] saved as png | 10m | ## Spatial Coverage This is a global monotemporal dataset. Nearly every piece of Earth captured by Sentinel-2 is contained at least once in this dataset (and only once, excluding some marginal overlaps). The following figure demonstrates the spatial coverage (only black pixels are absent):  ## Example Use Interface scripts are available at https://github.com/ESA-PhiLab/Major-TOM Here's a sneak peek with a thumbnail image: ```python from fsspec.parquet import open_parquet_file import pyarrow.parquet as pq from io import BytesIO from PIL import Image PARQUET_FILE = 'part_03900' # parquet number ROW_INDEX = 42 # row number (about 500 per parquet) url = "https://huggingface.co/datasets/Major-TOM/Core-S2L2A/resolve/main/images/{}.parquet".format(PARQUET_FILE) with open_parquet_file(url,columns = ["thumbnail"]) as f: with pq.ParquetFile(f) as pf: first_row_group = pf.read_row_group(ROW_INDEX, columns=['thumbnail']) stream = BytesIO(first_row_group['thumbnail'][0].as_py()) image = Image.open(stream) ``` ## Cite [](https://arxiv.org/abs/2402.12095/) ```latex @inproceedings{Major_TOM, title={Major TOM: Expandable Datasets for Earth Observation}, author={Alistair Francis and Mikolaj Czerkawski}, year={2024}, booktitle={IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium}, eprint={2402.12095}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` Powered by [Φ-lab, European Space Agency (ESA) 🛰️](https://huggingface.co/ESA-philab)

mlfoundations/dclm-pool-1b-5x

mlfoundations

--- license: cc-by-4.0 ---

tatsu-lab/alpaca_eval

tatsu-lab

--- license: cc-by-nc-4.0 ---

fixie-ai/covost2

fixie-ai

--- dataset_info: - config_name: ar_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 61607709.192 num_examples: 2283 - name: validation num_bytes: 56223234.024 num_examples: 1758 - name: test num_bytes: 54650910.41 num_examples: 1695 download_size: 160468333 dataset_size: 172481853.626 - config_name: ca_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 4397026262.322 num_examples: 95854 - name: validation num_bytes: 544108371.96 num_examples: 12730 - name: test num_bytes: 604755238.63 num_examples: 12730 download_size: 4957773433 dataset_size: 5545889872.912 - config_name: cy_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 51478765.087 num_examples: 1241 - name: validation num_bytes: 26992697.0 num_examples: 690 - name: test num_bytes: 28772216.0 num_examples: 690 download_size: 102604972 dataset_size: 107243678.087 - config_name: de_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 5680326209.222 num_examples: 127834 - name: validation num_bytes: 631442490.202 num_examples: 13511 - name: test num_bytes: 637042944.685 num_examples: 13511 download_size: 6490850158 dataset_size: 6948811644.108999 - config_name: en_ar features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14105902817.18 num_examples: 289430 - name: validation num_bytes: 718527564.808 num_examples: 15531 - name: test num_bytes: 729114452.301 num_examples: 15531 download_size: 13815709729 dataset_size: 15553544834.289001 - config_name: en_ca features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099092976.18 num_examples: 289430 - name: validation num_bytes: 718171719.808 num_examples: 15531 - name: test num_bytes: 728790610.301 num_examples: 15531 download_size: 13814365593 dataset_size: 15546055306.289001 - config_name: en_cy features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098487703.18 num_examples: 289430 - name: validation num_bytes: 718141953.808 num_examples: 15531 - name: test num_bytes: 728793811.301 num_examples: 15531 download_size: 13813953593 dataset_size: 15545423468.289001 - config_name: en_de features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099886814.18 num_examples: 289430 - name: validation num_bytes: 718219105.808 num_examples: 15531 - name: test num_bytes: 728857067.301 num_examples: 15531 download_size: 13815103686 dataset_size: 15546962987.289001 - config_name: en_et features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14096877545.18 num_examples: 289430 - name: validation num_bytes: 718057559.808 num_examples: 15531 - name: test num_bytes: 728710692.301 num_examples: 15531 download_size: 13813410823 dataset_size: 15543645797.289001 - config_name: en_fa features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14108661241.18 num_examples: 289430 - name: validation num_bytes: 718670909.808 num_examples: 15531 - name: test num_bytes: 729271000.301 num_examples: 15531 download_size: 13816798013 dataset_size: 15556603151.289001 - config_name: en_id features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098627451.18 num_examples: 289430 - name: validation num_bytes: 718144327.808 num_examples: 15531 - name: test num_bytes: 728802322.301 num_examples: 15531 download_size: 13813201260 dataset_size: 15545574101.289001 - config_name: en_ja features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14103911774.18 num_examples: 289430 - name: validation num_bytes: 718409304.808 num_examples: 15531 - name: test num_bytes: 729050991.301 num_examples: 15531 download_size: 13815875328 dataset_size: 15551372070.289001 - config_name: en_lv features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098703097.18 num_examples: 289430 - name: validation num_bytes: 718152571.808 num_examples: 15531 - name: test num_bytes: 728792572.301 num_examples: 15531 download_size: 13814849886 dataset_size: 15545648241.289001 - config_name: en_mn features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14113120657.18 num_examples: 289430 - name: validation num_bytes: 718940418.808 num_examples: 15531 - name: test num_bytes: 729461016.301 num_examples: 15531 download_size: 13819427515 dataset_size: 15561522092.289001 - config_name: en_sl features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097158381.18 num_examples: 289430 - name: validation num_bytes: 718085673.808 num_examples: 15531 - name: test num_bytes: 728705188.301 num_examples: 15531 download_size: 13813603812 dataset_size: 15543949243.289001 - config_name: en_sv-SE features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097728051.18 num_examples: 289430 - name: validation num_bytes: 718093292.808 num_examples: 15531 - name: test num_bytes: 728747422.301 num_examples: 15531 download_size: 13813332908 dataset_size: 15544568766.289001 - config_name: en_ta features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14135489205.18 num_examples: 289430 - name: validation num_bytes: 720191394.808 num_examples: 15531 - name: test num_bytes: 730578783.301 num_examples: 15531 download_size: 13825121271 dataset_size: 15586259383.289001 - config_name: en_tr features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098644786.18 num_examples: 289430 - name: validation num_bytes: 718161996.808 num_examples: 15531 - name: test num_bytes: 728786654.301 num_examples: 15531 download_size: 13814279798 dataset_size: 15545593437.289001 - config_name: en_zh-CN features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14095661460.18 num_examples: 289430 - name: validation num_bytes: 717982705.808 num_examples: 15531 - name: test num_bytes: 728655191.301 num_examples: 15531 download_size: 13812699892 dataset_size: 15542299357.289001 - config_name: es_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 630615357.241 num_examples: 13221 - name: test num_bytes: 666447063.067 num_examples: 13221 - name: train num_bytes: 3769457359.8 num_examples: 79015 download_size: 4531969416 dataset_size: 5066519780.108 - config_name: et_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 97124727.544 num_examples: 1782 - name: validation num_bytes: 80290798.168 num_examples: 1576 - name: test num_bytes: 81970364.51 num_examples: 1571 download_size: 257604448 dataset_size: 259385890.222 - config_name: fa_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1872724297.149 num_examples: 53949 - name: validation num_bytes: 140067911.23 num_examples: 3445 - name: test num_bytes: 149319550.35 num_examples: 3445 download_size: 1679853440 dataset_size: 2162111758.729 - config_name: fr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 632191608.84 num_examples: 14760 - name: test num_bytes: 698178059.08 num_examples: 14760 - name: train num_bytes: 8128016830.77 num_examples: 207374 download_size: 8900934523 dataset_size: 9458386498.69 - config_name: id_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 36136135.768 num_examples: 1243 - name: validation num_bytes: 25058845.0 num_examples: 792 - name: test num_bytes: 26577467.0 num_examples: 844 download_size: 86110062 dataset_size: 87772447.768 - config_name: it_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1517510665.568 num_examples: 31698 - name: validation num_bytes: 422409218.1 num_examples: 8940 - name: test num_bytes: 454569171.595 num_examples: 8951 download_size: 2125529183 dataset_size: 2394489055.2630005 - config_name: ja_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 38181610.624 num_examples: 1119 - name: validation num_bytes: 24623052.0 num_examples: 635 - name: test num_bytes: 25558787.0 num_examples: 684 download_size: 88228548 dataset_size: 88363449.624 - config_name: lv_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 66152116.328 num_examples: 2337 - name: validation num_bytes: 32655276.0 num_examples: 1125 - name: test num_bytes: 50997551.638 num_examples: 1629 download_size: 137700207 dataset_size: 149804943.96600002 - config_name: mn_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 87891433.547 num_examples: 2067 - name: validation num_bytes: 77519039.943 num_examples: 1761 - name: test num_bytes: 83667460.167 num_examples: 1759 download_size: 242638800 dataset_size: 249077933.657 - config_name: nl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 216102081.4 num_examples: 7108 - name: validation num_bytes: 55386349.319 num_examples: 1699 - name: test num_bytes: 60219179.711 num_examples: 1699 download_size: 320267264 dataset_size: 331707610.43 - config_name: pt_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 274723273.528 num_examples: 9158 - name: validation num_bytes: 118345891.704 num_examples: 3318 - name: test num_bytes: 166247624.001 num_examples: 4023 download_size: 540891735 dataset_size: 559316789.233 - config_name: ru_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 557219472.672 num_examples: 12112 - name: validation num_bytes: 290218427.6 num_examples: 6110 - name: test num_bytes: 312622838.0 num_examples: 6300 download_size: 1112848246 dataset_size: 1160060738.272 - config_name: sl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 55992153.0 num_examples: 1843 - name: validation num_bytes: 15074155.0 num_examples: 509 - name: test num_bytes: 10209711.0 num_examples: 360 download_size: 83863293 dataset_size: 81276019.0 - config_name: sv-SE_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 48298330.64 num_examples: 2160 - name: validation num_bytes: 32544646.416 num_examples: 1349 - name: test num_bytes: 46894324.615 num_examples: 1595 download_size: 121860373 dataset_size: 127737301.671 - config_name: ta_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 47757197.616 num_examples: 1358 - name: validation num_bytes: 13670695.0 num_examples: 384 - name: test num_bytes: 29891516.0 num_examples: 786 download_size: 87791516 dataset_size: 91319408.616 - config_name: tr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 119299427.798 num_examples: 3966 - name: validation num_bytes: 52552534.232 num_examples: 1624 - name: test num_bytes: 59106253.862 num_examples: 1629 download_size: 224018260 dataset_size: 230958215.89200002 - config_name: zh-CN_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 231018998.33 num_examples: 4843 - name: test num_bytes: 243850956.45 num_examples: 4898 - name: train num_bytes: 341425113.6 num_examples: 7085 download_size: 766660661 dataset_size: 816295068.38 configs: - config_name: ar_en data_files: - split: train path: ar_en/train-* - split: validation path: ar_en/validation-* - split: test path: ar_en/test-* - config_name: ca_en data_files: - split: train path: ca_en/train-* - split: validation path: ca_en/validation-* - split: test path: ca_en/test-* - config_name: cy_en data_files: - split: train path: cy_en/train-* - split: validation path: cy_en/validation-* - split: test path: cy_en/test-* - config_name: de_en data_files: - split: train path: de_en/train-* - split: validation path: de_en/validation-* - split: test path: de_en/test-* - config_name: en_ar data_files: - split: train path: en_ar/train-* - split: validation path: en_ar/validation-* - split: test path: en_ar/test-* - config_name: en_ca data_files: - split: train path: en_ca/train-* - split: validation path: en_ca/validation-* - split: test path: en_ca/test-* - config_name: en_cy data_files: - split: train path: en_cy/train-* - split: validation path: en_cy/validation-* - split: test path: en_cy/test-* - config_name: en_de data_files: - split: train path: en_de/train-* - split: validation path: en_de/validation-* - split: test path: en_de/test-* - config_name: en_et data_files: - split: train path: en_et/train-* - split: validation path: en_et/validation-* - split: test path: en_et/test-* - config_name: en_fa data_files: - split: train path: en_fa/train-* - split: validation path: en_fa/validation-* - split: test path: en_fa/test-* - config_name: en_id data_files: - split: train path: en_id/train-* - split: validation path: en_id/validation-* - split: test path: en_id/test-* - config_name: en_ja data_files: - split: train path: en_ja/train-* - split: validation path: en_ja/validation-* - split: test path: en_ja/test-* - config_name: en_lv data_files: - split: train path: en_lv/train-* - split: validation path: en_lv/validation-* - split: test path: en_lv/test-* - config_name: en_mn data_files: - split: train path: en_mn/train-* - split: validation path: en_mn/validation-* - split: test path: en_mn/test-* - config_name: en_sl data_files: - split: train path: en_sl/train-* - split: validation path: en_sl/validation-* - split: test path: en_sl/test-* - config_name: en_sv-SE data_files: - split: train path: en_sv-SE/train-* - split: validation path: en_sv-SE/validation-* - split: test path: en_sv-SE/test-* - config_name: en_ta data_files: - split: train path: en_ta/train-* - split: validation path: en_ta/validation-* - split: test path: en_ta/test-* - config_name: en_tr data_files: - split: train path: en_tr/train-* - split: validation path: en_tr/validation-* - split: test path: en_tr/test-* - config_name: en_zh-CN data_files: - split: train path: en_zh-CN/train-* - split: validation path: en_zh-CN/validation-* - split: test path: en_zh-CN/test-* - config_name: es_en data_files: - split: validation path: es_en/validation-* - split: test path: es_en/test-* - split: train path: es_en/train-* - config_name: et_en data_files: - split: train path: et_en/train-* - split: validation path: et_en/validation-* - split: test path: et_en/test-* - config_name: fa_en data_files: - split: train path: fa_en/train-* - split: validation path: fa_en/validation-* - split: test path: fa_en/test-* - config_name: fr_en data_files: - split: validation path: fr_en/validation-* - split: test path: fr_en/test-* - split: train path: fr_en/train-* - config_name: id_en data_files: - split: train path: id_en/train-* - split: validation path: id_en/validation-* - split: test path: id_en/test-* - config_name: it_en data_files: - split: train path: it_en/train-* - split: validation path: it_en/validation-* - split: test path: it_en/test-* - config_name: ja_en data_files: - split: train path: ja_en/train-* - split: validation path: ja_en/validation-* - split: test path: ja_en/test-* - config_name: lv_en data_files: - split: train path: lv_en/train-* - split: validation path: lv_en/validation-* - split: test path: lv_en/test-* - config_name: mn_en data_files: - split: train path: mn_en/train-* - split: validation path: mn_en/validation-* - split: test path: mn_en/test-* - config_name: nl_en data_files: - split: train path: nl_en/train-* - split: validation path: nl_en/validation-* - split: test path: nl_en/test-* - config_name: pt_en data_files: - split: train path: pt_en/train-* - split: validation path: pt_en/validation-* - split: test path: pt_en/test-* - config_name: ru_en data_files: - split: train path: ru_en/train-* - split: validation path: ru_en/validation-* - split: test path: ru_en/test-* - config_name: sl_en data_files: - split: train path: sl_en/train-* - split: validation path: sl_en/validation-* - split: test path: sl_en/test-* - config_name: sv-SE_en data_files: - split: train path: sv-SE_en/train-* - split: validation path: sv-SE_en/validation-* - split: test path: sv-SE_en/test-* - config_name: ta_en data_files: - split: train path: ta_en/train-* - split: validation path: ta_en/validation-* - split: test path: ta_en/test-* - config_name: tr_en data_files: - split: train path: tr_en/train-* - split: validation path: tr_en/validation-* - split: test path: tr_en/test-* - config_name: zh-CN_en data_files: - split: validation path: zh-CN_en/validation-* - split: test path: zh-CN_en/test-* - split: train path: zh-CN_en/train-* --- This is a partial copy of [CoVoST2](https://huggingface.co/datasets/facebook/covost2) dataset. The main difference is that the audio data is included in the dataset, which makes usage easier and allows browsing the samples using HF Dataset Viewer. The limitation of this method is that all audio samples of the `EN_XX` subsets are duplicated, as such the size of the dataset is larger. As such, not all the data is included: Only the `validation` and `test` subsets are available. From the `XX_EN` subsets, only `fr`, `es`, and `zh-CN` are included.

jinzhuoran/RWKU

jinzhuoran

--- language: - en license: cc-by-4.0 pretty_name: RWKU size_categories: - 10K<n<100K task_categories: - text-generation - fill-mask - question-answering tags: - unlearning - knowledge unlearning - NLP - LLM configs: - config_name: forget_target data_files: - split: train path: - "All/intro.json" - config_name: forget_level1 data_files: - split: test path: - "All/forget_level1.json" - config_name: forget_level2 data_files: - split: test path: - "All/forget_level2.json" - config_name: forget_level3 data_files: - split: test path: - "All/forget_level3.json" - config_name: neighbor_level1 data_files: - split: test path: - "All/neighbor_level1.json" - config_name: neighbor_level2 data_files: - split: test path: - "All/neighbor_level2.json" - config_name: mia_forget data_files: - split: test path: - "All/forget_mia.json" - config_name: mia_retain data_files: - split: test path: - "All/retain_mia.json" - config_name: utility_general data_files: - split: test path: - "All/retain_mmlu.json" - config_name: utility_general data_files: - split: test path: - "All/retain_mmlu.json" - config_name: utility_reason data_files: - split: test path: - "All/retain_bbh.json" - config_name: utility_truthfulness data_files: - split: test path: - "All/truthful.json" - config_name: utility_factuality data_files: - split: test path: - "All/triviaqa.json" - config_name: utility_fluency data_files: - split: test path: - "All/fluency.json" - config_name: train_original_passage data_files: - split: train path: - "All/passage.json" - config_name: train_positive_llama3 data_files: - split: train path: - "All/positive.json" - config_name: train_negative_llama3 data_files: - split: train path: - "All/negative.json" - config_name: train_pair_llama3 data_files: - split: train path: - "All/pair.json" - config_name: train_refusal_llama3 data_files: - split: train path: - "All/reject.json" - config_name: train_positive_phi3 data_files: - split: train path: - "All/positive_phi.json" - config_name: train_negative_phi3 data_files: - split: train path: - "All/negative_phi.json" - config_name: train_pair_phi3 data_files: - split: train path: - "All/pair_phi.json" - config_name: train_refusal_phi3 data_files: - split: train path: - "All/reject_phi.json" --- # Dataset Card for Real-World Knowledge Unlearning Benchmark (RWKU) ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://rwku-bench.github.io - **Repository:** https://github.com/jinzhuoran/RWKU - **Paper:** https://arxiv.org/abs/2406.10890 ### Dataset Summary **RWKU is a real-world knowledge unlearning benchmark specifically designed for large language models (LLMs).** This benchmark contains 200 real-world unlearning targets and 13,131 multi-level forget probes, including 3,268 fill-in-the-blank probes, 2,879 question-answer probes, and 6,984 adversarial-attack probes. RWKU is designed based on the following three key factors: 1. For the **task setting**, we consider a more practical and challenging setting, similar to _zero-shot knowledge unlearning_. We provide only the unlearning target and the original model, without offering any forget corpus or retain corpus. In this way, it avoids secondary information leakage caused by the forget corpus and is not affected by the distribution bias of the retain corpus. 2. For the **knowledge source**, we choose real-world famous people from Wikipedia as the unlearning targets and demonstrate that such popular knowledge is widely present in various LLMs through memorization quantification, making it more suitable for knowledge unlearning. Additionally, choosing entities as unlearning targets can well clearly define the unlearning boundaries. 3. For the **evaluation framework**, we carefully design the forget set and the retain set to evaluate the model's capabilities from multiple real-world applications. Regarding the forget set, we evaluate the **efficacy** of knowledge unlearning at both the knowledge memorization (fill-in-the-blank style) and knowledge manipulation (question-answer style) abilities. Specifically, we also evaluate these two abilities through **adversarial attacks** to induce forgotten knowledge in the model. We adopt four membership inference attack (MIA) methods for knowledge memorization on our collected MIA set. We meticulously designed nine types of adversarial-attack probes for knowledge manipulation, including prefix injection, affirmative suffix, role playing, reverse query, and others. Regarding the retain set, we design a neighbor set to test the impact of neighbor perturbation, specifically focusing on the **locality** of unlearning. In addition, we assess the **model utility** on various capabilities, including general ability, reasoning ability, truthfulness, factuality, and fluency. ### Supported Tasks Knowledge unlearning for LLMs. ### Languages English. ## Dataset Structure To evaluate the unlearning efficacy: ```python from datasets import load_dataset forget_level1 = load_dataset("jinzhuoran/RWKU", 'forget_level1') forget_level2 = load_dataset("jinzhuoran/RWKU", 'forget_level2') forget_level2 = load_dataset("jinzhuoran/RWKU", 'forget_level2') ``` To evaluate the locality: ```python from datasets import load_dataset neighbor_level1 = load_dataset("jinzhuoran/RWKU", 'neighbor_level1') neighbor_level2 = load_dataset("jinzhuoran/RWKU", 'neighbor_level2') ``` To evaluate the model utility: ```python from datasets import load_dataset utility_general = load_dataset("jinzhuoran/RWKU", 'utility_general') utility_reason = load_dataset("jinzhuoran/RWKU", 'utility_reason') utility_truthfulness = load_dataset("jinzhuoran/RWKU", 'utility_truthfulness') utility_factuality = load_dataset("jinzhuoran/RWKU", 'utility_factuality') utility_fluency = load_dataset("jinzhuoran/RWKU", 'utility_fluency') ``` To conduct membership inference attacks: ```python from datasets import load_dataset mia_forget = load_dataset("jinzhuoran/RWKU", 'mia_forget') mia_retain = load_dataset("jinzhuoran/RWKU", 'mia_retain') ``` To load the forget corpus: ```python from datasets import load_dataset train_original_passage = load_dataset("jinzhuoran/RWKU", 'train_original_passage') train_positive_llama3 = load_dataset("jinzhuoran/RWKU", 'train_positive_llama3') ``` ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citing Our Work If you find our codebase and dataset beneficial, please cite our work: ```bibtex @misc{jin2024rwku, title={RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models}, author={Zhuoran Jin and Pengfei Cao and Chenhao Wang and Zhitao He and Hongbang Yuan and Jiachun Li and Yubo Chen and Kang Liu and Jun Zhao}, year={2024}, eprint={2406.10890}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

ai4bharat/indic_glue

ai4bharat

--- annotations_creators: - other language_creators: - found language: - as - bn - en - gu - hi - kn - ml - mr - or - pa - ta - te license: - other multilinguality: - multilingual size_categories: - 100K<n<1M source_datasets: - extended|other task_categories: - text-classification - token-classification - multiple-choice task_ids: - topic-classification - natural-language-inference - sentiment-analysis - semantic-similarity-scoring - named-entity-recognition - multiple-choice-qa pretty_name: IndicGLUE tags: - discourse-mode-classification - paraphrase-identification - cross-lingual-similarity - headline-classification dataset_info: - config_name: actsa-sc.te features: - name: text dtype: string - name: label dtype: class_label: names: '0': positive '1': negative splits: - name: train num_bytes: 1370907 num_examples: 4328 - name: validation num_bytes: 166089 num_examples: 541 - name: test num_bytes: 168291 num_examples: 541 download_size: 727630 dataset_size: 1705287 - config_name: bbca.hi features: - name: label dtype: string - name: text dtype: string splits: - name: train num_bytes: 22126205 num_examples: 3467 - name: test num_bytes: 5501148 num_examples: 866 download_size: 10349015 dataset_size: 27627353 - config_name: copa.en features: - name: premise dtype: string - name: choice1 dtype: string - name: choice2 dtype: string - name: question dtype: string - name: label dtype: int32 splits: - name: train num_bytes: 46033 num_examples: 400 - name: validation num_bytes: 11679 num_examples: 100 - name: test num_bytes: 55846 num_examples: 500 download_size: 79431 dataset_size: 113558 - config_name: copa.gu features: - name: premise dtype: string - name: choice1 dtype: string - name: choice2 dtype: string - name: question dtype: string - name: label dtype: int32 splits: - name: train num_bytes: 92097 num_examples: 362 - name: validation num_bytes: 23450 num_examples: 88 - name: test num_bytes: 109997 num_examples: 448 download_size: 107668 dataset_size: 225544 - config_name: copa.hi features: - name: premise dtype: string - name: choice1 dtype: string - name: choice2 dtype: string - name: question dtype: string - name: label dtype: int32 splits: - name: train num_bytes: 93376 num_examples: 362 - name: validation num_bytes: 23559 num_examples: 88 - name: test num_bytes: 112830 num_examples: 449 download_size: 104233 dataset_size: 229765 - config_name: copa.mr features: - name: premise dtype: string - name: choice1 dtype: string - name: choice2 dtype: string - name: question dtype: string - name: label dtype: int32 splits: - name: train num_bytes: 93441 num_examples: 362 - name: validation num_bytes: 23874 num_examples: 88 - name: test num_bytes: 112055 num_examples: 449 download_size: 105962 dataset_size: 229370 - config_name: csqa.as features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 3800523 num_examples: 2942 download_size: 1390423 dataset_size: 3800523 - config_name: csqa.bn features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 54671018 num_examples: 38845 download_size: 19648180 dataset_size: 54671018 - config_name: csqa.gu features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 29131607 num_examples: 22861 download_size: 6027825 dataset_size: 29131607 - config_name: csqa.hi features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 40409347 num_examples: 35140 download_size: 14711258 dataset_size: 40409347 - config_name: csqa.kn features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 21199816 num_examples: 13666 download_size: 7669655 dataset_size: 21199816 - config_name: csqa.ml features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 47220836 num_examples: 26537 download_size: 17382215 dataset_size: 47220836 - config_name: csqa.mr features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 13667174 num_examples: 11370 download_size: 5072738 dataset_size: 13667174 - config_name: csqa.or features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 2562365 num_examples: 1975 download_size: 948046 dataset_size: 2562365 - config_name: csqa.pa features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 5806097 num_examples: 5667 download_size: 2194109 dataset_size: 5806097 - config_name: csqa.ta features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 61868481 num_examples: 38590 download_size: 20789467 dataset_size: 61868481 - config_name: csqa.te features: - name: question dtype: string - name: answer dtype: string - name: category dtype: string - name: title dtype: string - name: options sequence: string - name: out_of_context_options sequence: string splits: - name: test num_bytes: 58784997 num_examples: 41338 download_size: 17447618 dataset_size: 58784997 - config_name: cvit-mkb-clsr.en-bn features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 1990957 num_examples: 5522 download_size: 945551 dataset_size: 1990957 - config_name: cvit-mkb-clsr.en-gu features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 2303377 num_examples: 6463 download_size: 1093313 dataset_size: 2303377 - config_name: cvit-mkb-clsr.en-hi features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 1855989 num_examples: 5169 download_size: 890609 dataset_size: 1855989 - config_name: cvit-mkb-clsr.en-ml features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 1990089 num_examples: 4886 download_size: 868956 dataset_size: 1990089 - config_name: cvit-mkb-clsr.en-mr features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 2130601 num_examples: 5760 download_size: 993961 dataset_size: 2130601 - config_name: cvit-mkb-clsr.en-or features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 274873 num_examples: 752 download_size: 134334 dataset_size: 274873 - config_name: cvit-mkb-clsr.en-ta features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 2565178 num_examples: 5637 download_size: 1091653 dataset_size: 2565178 - config_name: cvit-mkb-clsr.en-te features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 1771129 num_examples: 5049 download_size: 840410 dataset_size: 1771129 - config_name: cvit-mkb-clsr.en-ur features: - name: sentence1 dtype: string - name: sentence2 dtype: string splits: - name: test num_bytes: 288430 num_examples: 1006 download_size: 166129 dataset_size: 288430 - config_name: iitp-mr.hi features: - name: text dtype: string - name: label dtype: class_label: names: '0': negative '1': neutral '2': positive splits: - name: train num_bytes: 6704905 num_examples: 2480 - name: validation num_bytes: 822218 num_examples: 310 - name: test num_bytes: 702373 num_examples: 310 download_size: 3151762 dataset_size: 8229496 - config_name: iitp-pr.hi features: - name: text dtype: string - name: label dtype: class_label: names: '0': negative '1': neutral '2': positive splits: - name: train num_bytes: 945589 num_examples: 4182 - name: validation num_bytes: 120100 num_examples: 523 - name: test num_bytes: 121910 num_examples: 523 download_size: 509822 dataset_size: 1187599 - config_name: inltkh.gu features: - name: text dtype: string - name: label dtype: class_label: names: '0': entertainment '1': business '2': tech '3': sports '4': state '5': spirituality '6': tamil-cinema '7': positive '8': negative '9': neutral splits: - name: train num_bytes: 883063 num_examples: 5269 - name: validation num_bytes: 111201 num_examples: 659 - name: test num_bytes: 110757 num_examples: 659 download_size: 515094 dataset_size: 1105021 - config_name: inltkh.ml features: - name: text dtype: string - name: label dtype: class_label: names: '0': entertainment '1': business '2': tech '3': sports '4': state '5': spirituality '6': tamil-cinema '7': positive '8': negative '9': neutral splits: - name: train num_bytes: 1108145 num_examples: 5036 - name: validation num_bytes: 140055 num_examples: 630 - name: test num_bytes: 138847 num_examples: 630 download_size: 571019 dataset_size: 1387047 - config_name: inltkh.mr features: - name: text dtype: string - name: label dtype: class_label: names: '0': entertainment '1': business '2': tech '3': sports '4': state '5': spirituality '6': tamil-cinema '7': positive '8': negative '9': neutral splits: - name: train num_bytes: 1462614 num_examples: 9672 - name: validation num_bytes: 180306 num_examples: 1210 - name: test num_bytes: 180558 num_examples: 1210 download_size: 840304 dataset_size: 1823478 - config_name: inltkh.ta features: - name: text dtype: string - name: label dtype: class_label: names: '0': entertainment '1': business '2': tech '3': sports '4': state '5': spirituality '6': tamil-cinema '7': positive '8': negative '9': neutral splits: - name: train num_bytes: 2659569 num_examples: 5346 - name: validation num_bytes: 316083 num_examples: 669 - name: test num_bytes: 320465 num_examples: 669 download_size: 1271262 dataset_size: 3296117 - config_name: inltkh.te features: - name: text dtype: string - name: label dtype: class_label: names: '0': entertainment '1': business '2': tech '3': sports '4': state '5': spirituality '6': tamil-cinema '7': positive '8': negative '9': neutral splits: - name: train num_bytes: 1361667 num_examples: 4328 - name: validation num_bytes: 170471 num_examples: 541 - name: test num_bytes: 173149 num_examples: 541 download_size: 726293 dataset_size: 1705287 - config_name: md.hi features: - name: sentence dtype: string - name: discourse_mode dtype: string - name: story_number dtype: int32 - name: id dtype: int32 splits: - name: train num_bytes: 1672109 num_examples: 7974 - name: validation num_bytes: 211187 num_examples: 997 - name: test num_bytes: 210175 num_examples: 997 download_size: 939801 dataset_size: 2093471 - config_name: sna.bn features: - name: text dtype: string - name: label dtype: class_label: names: '0': kolkata '1': state '2': national '3': sports '4': entertainment '5': international splits: - name: train num_bytes: 46070046 num_examples: 11284 - name: validation num_bytes: 5648126 num_examples: 1411 - name: test num_bytes: 5799979 num_examples: 1411 download_size: 21415940 dataset_size: 57518151 - config_name: wiki-ner.as features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 374983 num_examples: 1021 - name: validation num_bytes: 49312 num_examples: 157 - name: test num_bytes: 50456 num_examples: 160 download_size: 72919 dataset_size: 474751 - config_name: wiki-ner.bn features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 7502824 num_examples: 20223 - name: validation num_bytes: 988683 num_examples: 2985 - name: test num_bytes: 985941 num_examples: 2690 download_size: 1278219 dataset_size: 9477448 - config_name: wiki-ner.gu features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 1571588 num_examples: 2343 - name: validation num_bytes: 192804 num_examples: 297 - name: test num_bytes: 197877 num_examples: 255 download_size: 329660 dataset_size: 1962269 - config_name: wiki-ner.hi features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 3762505 num_examples: 9463 - name: validation num_bytes: 468678 num_examples: 1114 - name: test num_bytes: 475253 num_examples: 1256 download_size: 948132 dataset_size: 4706436 - config_name: wiki-ner.kn features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 1352027 num_examples: 2679 - name: validation num_bytes: 179538 num_examples: 412 - name: test num_bytes: 180791 num_examples: 476 download_size: 421877 dataset_size: 1712356 - config_name: wiki-ner.ml features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 7678887 num_examples: 15620 - name: validation num_bytes: 969947 num_examples: 2067 - name: test num_bytes: 991102 num_examples: 2042 download_size: 2390442 dataset_size: 9639936 - config_name: wiki-ner.mr features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 5431489 num_examples: 12151 - name: validation num_bytes: 701637 num_examples: 1498 - name: test num_bytes: 655682 num_examples: 1329 download_size: 1410663 dataset_size: 6788808 - config_name: wiki-ner.or features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 493758 num_examples: 1077 - name: validation num_bytes: 58568 num_examples: 132 - name: test num_bytes: 62211 num_examples: 153 download_size: 102783 dataset_size: 614537 - config_name: wiki-ner.pa features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 520244 num_examples: 1408 - name: validation num_bytes: 61170 num_examples: 186 - name: test num_bytes: 61788 num_examples: 179 download_size: 149727 dataset_size: 643202 - config_name: wiki-ner.ta features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 10117080 num_examples: 20466 - name: validation num_bytes: 1267188 num_examples: 2586 - name: test num_bytes: 1321626 num_examples: 2611 download_size: 2819083 dataset_size: 12705894 - config_name: wiki-ner.te features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': B-LOC '1': B-ORG '2': B-PER '3': I-LOC '4': I-ORG '5': I-PER '6': O - name: additional_info sequence: sequence: string splits: - name: train num_bytes: 3881211 num_examples: 7978 - name: validation num_bytes: 458509 num_examples: 841 - name: test num_bytes: 507806 num_examples: 1110 download_size: 1006881 dataset_size: 4847526 - config_name: wnli.en features: - name: hypothesis dtype: string - name: premise dtype: string - name: label dtype: class_label: names: '0': not_entailment '1': entailment '2': None splits: - name: train num_bytes: 104569 num_examples: 635 - name: validation num_bytes: 11878 num_examples: 71 - name: test num_bytes: 37297 num_examples: 146 download_size: 57667 dataset_size: 153744 - config_name: wnli.gu features: - name: hypothesis dtype: string - name: premise dtype: string - name: label dtype: class_label: names: '0': not_entailment '1': entailment '2': None splits: - name: train num_bytes: 251554 num_examples: 635 - name: validation num_bytes: 28175 num_examples: 71 - name: test num_bytes: 94578 num_examples: 146 download_size: 98032 dataset_size: 374307 - config_name: wnli.hi features: - name: hypothesis dtype: string - name: premise dtype: string - name: label dtype: class_label: names: '0': not_entailment '1': entailment '2': None splits: - name: train num_bytes: 253334 num_examples: 635 - name: validation num_bytes: 28676 num_examples: 71 - name: test num_bytes: 90823 num_examples: 146 download_size: 99450 dataset_size: 372833 - config_name: wnli.mr features: - name: hypothesis dtype: string - name: premise dtype: string - name: label dtype: class_label: names: '0': not_entailment '1': entailment '2': None splits: - name: train num_bytes: 256649 num_examples: 635 - name: validation num_bytes: 29218 num_examples: 71 - name: test num_bytes: 97128 num_examples: 146 download_size: 103774 dataset_size: 382995 - config_name: wstp.as features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 13581336 num_examples: 5000 - name: validation num_bytes: 1698968 num_examples: 625 - name: test num_bytes: 1697650 num_examples: 626 download_size: 6959458 dataset_size: 16977954 - config_name: wstp.bn features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 143340457 num_examples: 47580 - name: validation num_bytes: 17759236 num_examples: 5947 - name: test num_bytes: 17633865 num_examples: 5948 download_size: 69145372 dataset_size: 178733558 - config_name: wstp.gu features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 39353464 num_examples: 10004 - name: validation num_bytes: 4887752 num_examples: 1251 - name: test num_bytes: 4699158 num_examples: 1251 download_size: 19763249 dataset_size: 48940374 - config_name: wstp.hi features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 158529578 num_examples: 44069 - name: validation num_bytes: 19371904 num_examples: 5509 - name: test num_bytes: 19593001 num_examples: 5509 download_size: 77868574 dataset_size: 197494483 - config_name: wstp.kn features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 139950313 num_examples: 35379 - name: validation num_bytes: 17789782 num_examples: 4422 - name: test num_bytes: 17897031 num_examples: 4423 download_size: 67719504 dataset_size: 175637126 - config_name: wstp.ml features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 88360504 num_examples: 27527 - name: validation num_bytes: 11193340 num_examples: 3441 - name: test num_bytes: 11150914 num_examples: 3441 download_size: 42336357 dataset_size: 110704758 - config_name: wstp.mr features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 28302341 num_examples: 10446 - name: validation num_bytes: 3328798 num_examples: 1306 - name: test num_bytes: 3631684 num_examples: 1306 download_size: 13886208 dataset_size: 35262823 - config_name: wstp.or features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 10900006 num_examples: 4015 - name: validation num_bytes: 1264935 num_examples: 502 - name: test num_bytes: 1344652 num_examples: 502 download_size: 5319128 dataset_size: 13509593 - config_name: wstp.pa features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 22189730 num_examples: 8772 - name: validation num_bytes: 2789186 num_examples: 1097 - name: test num_bytes: 2685767 num_examples: 1097 download_size: 11201369 dataset_size: 27664683 - config_name: wstp.ta features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 151929218 num_examples: 48940 - name: validation num_bytes: 18817167 num_examples: 6117 - name: test num_bytes: 18815071 num_examples: 6118 download_size: 68699092 dataset_size: 189561456 - config_name: wstp.te features: - name: sectionText dtype: string - name: correctTitle dtype: string - name: titleA dtype: string - name: titleB dtype: string - name: titleC dtype: string - name: titleD dtype: string - name: url dtype: string splits: - name: train num_bytes: 151696691 num_examples: 80000 - name: validation num_bytes: 19003169 num_examples: 10000 - name: test num_bytes: 18991913 num_examples: 10000 download_size: 50158580 dataset_size: 189691773 configs: - config_name: actsa-sc.te data_files: - split: train path: actsa-sc.te/train-* - split: validation path: actsa-sc.te/validation-* - split: test path: actsa-sc.te/test-* - config_name: bbca.hi data_files: - split: train path: bbca.hi/train-* - split: test path: bbca.hi/test-* - config_name: copa.en data_files: - split: train path: copa.en/train-* - split: validation path: copa.en/validation-* - split: test path: copa.en/test-* - config_name: copa.gu data_files: - split: train path: copa.gu/train-* - split: validation path: copa.gu/validation-* - split: test path: copa.gu/test-* - config_name: copa.hi data_files: - split: train path: copa.hi/train-* - split: validation path: copa.hi/validation-* - split: test path: copa.hi/test-* - config_name: copa.mr data_files: - split: train path: copa.mr/train-* - split: validation path: copa.mr/validation-* - split: test path: copa.mr/test-* - config_name: csqa.as data_files: - split: test path: csqa.as/test-* - config_name: csqa.bn data_files: - split: test path: csqa.bn/test-* - config_name: csqa.gu data_files: - split: test path: csqa.gu/test-* - config_name: csqa.hi data_files: - split: test path: csqa.hi/test-* - config_name: csqa.kn data_files: - split: test path: csqa.kn/test-* - config_name: csqa.ml data_files: - split: test path: csqa.ml/test-* - config_name: csqa.mr data_files: - split: test path: csqa.mr/test-* - config_name: csqa.or data_files: - split: test path: csqa.or/test-* - config_name: csqa.pa data_files: - split: test path: csqa.pa/test-* - config_name: csqa.ta data_files: - split: test path: csqa.ta/test-* - config_name: csqa.te data_files: - split: test path: csqa.te/test-* - config_name: cvit-mkb-clsr.en-bn data_files: - split: test path: cvit-mkb-clsr.en-bn/test-* - config_name: cvit-mkb-clsr.en-gu data_files: - split: test path: cvit-mkb-clsr.en-gu/test-* - config_name: cvit-mkb-clsr.en-hi data_files: - split: test path: cvit-mkb-clsr.en-hi/test-* - config_name: cvit-mkb-clsr.en-ml data_files: - split: test path: cvit-mkb-clsr.en-ml/test-* - config_name: cvit-mkb-clsr.en-mr data_files: - split: test path: cvit-mkb-clsr.en-mr/test-* - config_name: cvit-mkb-clsr.en-or data_files: - split: test path: cvit-mkb-clsr.en-or/test-* - config_name: cvit-mkb-clsr.en-ta data_files: - split: test path: cvit-mkb-clsr.en-ta/test-* - config_name: cvit-mkb-clsr.en-te data_files: - split: test path: cvit-mkb-clsr.en-te/test-* - config_name: cvit-mkb-clsr.en-ur data_files: - split: test path: cvit-mkb-clsr.en-ur/test-* - config_name: iitp-mr.hi data_files: - split: train path: iitp-mr.hi/train-* - split: validation path: iitp-mr.hi/validation-* - split: test path: iitp-mr.hi/test-* - config_name: iitp-pr.hi data_files: - split: train path: iitp-pr.hi/train-* - split: validation path: iitp-pr.hi/validation-* - split: test path: iitp-pr.hi/test-* - config_name: inltkh.gu data_files: - split: train path: inltkh.gu/train-* - split: validation path: inltkh.gu/validation-* - split: test path: inltkh.gu/test-* - config_name: inltkh.ml data_files: - split: train path: inltkh.ml/train-* - split: validation path: inltkh.ml/validation-* - split: test path: inltkh.ml/test-* - config_name: inltkh.mr data_files: - split: train path: inltkh.mr/train-* - split: validation path: inltkh.mr/validation-* - split: test path: inltkh.mr/test-* - config_name: inltkh.ta data_files: - split: train path: inltkh.ta/train-* - split: validation path: inltkh.ta/validation-* - split: test path: inltkh.ta/test-* - config_name: inltkh.te data_files: - split: train path: inltkh.te/train-* - split: validation path: inltkh.te/validation-* - split: test path: inltkh.te/test-* - config_name: md.hi data_files: - split: train path: md.hi/train-* - split: validation path: md.hi/validation-* - split: test path: md.hi/test-* - config_name: sna.bn data_files: - split: train path: sna.bn/train-* - split: validation path: sna.bn/validation-* - split: test path: sna.bn/test-* - config_name: wiki-ner.as data_files: - split: train path: wiki-ner.as/train-* - split: validation path: wiki-ner.as/validation-* - split: test path: wiki-ner.as/test-* - config_name: wiki-ner.bn data_files: - split: train path: wiki-ner.bn/train-* - split: validation path: wiki-ner.bn/validation-* - split: test path: wiki-ner.bn/test-* - config_name: wiki-ner.gu data_files: - split: train path: wiki-ner.gu/train-* - split: validation path: wiki-ner.gu/validation-* - split: test path: wiki-ner.gu/test-* - config_name: wiki-ner.hi data_files: - split: train path: wiki-ner.hi/train-* - split: validation path: wiki-ner.hi/validation-* - split: test path: wiki-ner.hi/test-* - config_name: wiki-ner.kn data_files: - split: train path: wiki-ner.kn/train-* - split: validation path: wiki-ner.kn/validation-* - split: test path: wiki-ner.kn/test-* - config_name: wiki-ner.ml data_files: - split: train path: wiki-ner.ml/train-* - split: validation path: wiki-ner.ml/validation-* - split: test path: wiki-ner.ml/test-* - config_name: wiki-ner.mr data_files: - split: train path: wiki-ner.mr/train-* - split: validation path: wiki-ner.mr/validation-* - split: test path: wiki-ner.mr/test-* - config_name: wiki-ner.or data_files: - split: train path: wiki-ner.or/train-* - split: validation path: wiki-ner.or/validation-* - split: test path: wiki-ner.or/test-* - config_name: wiki-ner.pa data_files: - split: train path: wiki-ner.pa/train-* - split: validation path: wiki-ner.pa/validation-* - split: test path: wiki-ner.pa/test-* - config_name: wiki-ner.ta data_files: - split: train path: wiki-ner.ta/train-* - split: validation path: wiki-ner.ta/validation-* - split: test path: wiki-ner.ta/test-* - config_name: wiki-ner.te data_files: - split: train path: wiki-ner.te/train-* - split: validation path: wiki-ner.te/validation-* - split: test path: wiki-ner.te/test-* - config_name: wnli.en data_files: - split: train path: wnli.en/train-* - split: validation path: wnli.en/validation-* - split: test path: wnli.en/test-* - config_name: wnli.gu data_files: - split: train path: wnli.gu/train-* - split: validation path: wnli.gu/validation-* - split: test path: wnli.gu/test-* - config_name: wnli.hi data_files: - split: train path: wnli.hi/train-* - split: validation path: wnli.hi/validation-* - split: test path: wnli.hi/test-* - config_name: wnli.mr data_files: - split: train path: wnli.mr/train-* - split: validation path: wnli.mr/validation-* - split: test path: wnli.mr/test-* - config_name: wstp.as data_files: - split: train path: wstp.as/train-* - split: validation path: wstp.as/validation-* - split: test path: wstp.as/test-* - config_name: wstp.bn data_files: - split: train path: wstp.bn/train-* - split: validation path: wstp.bn/validation-* - split: test path: wstp.bn/test-* - config_name: wstp.gu data_files: - split: train path: wstp.gu/train-* - split: validation path: wstp.gu/validation-* - split: test path: wstp.gu/test-* - config_name: wstp.hi data_files: - split: train path: wstp.hi/train-* - split: validation path: wstp.hi/validation-* - split: test path: wstp.hi/test-* - config_name: wstp.kn data_files: - split: train path: wstp.kn/train-* - split: validation path: wstp.kn/validation-* - split: test path: wstp.kn/test-* - config_name: wstp.ml data_files: - split: train path: wstp.ml/train-* - split: validation path: wstp.ml/validation-* - split: test path: wstp.ml/test-* - config_name: wstp.mr data_files: - split: train path: wstp.mr/train-* - split: validation path: wstp.mr/validation-* - split: test path: wstp.mr/test-* - config_name: wstp.or data_files: - split: train path: wstp.or/train-* - split: validation path: wstp.or/validation-* - split: test path: wstp.or/test-* - config_name: wstp.pa data_files: - split: train path: wstp.pa/train-* - split: validation path: wstp.pa/validation-* - split: test path: wstp.pa/test-* - config_name: wstp.ta data_files: - split: train path: wstp.ta/train-* - split: validation path: wstp.ta/validation-* - split: test path: wstp.ta/test-* - config_name: wstp.te data_files: - split: train path: wstp.te/train-* - split: validation path: wstp.te/validation-* - split: test path: wstp.te/test-* --- # Dataset Card for "indic_glue" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://ai4bharat.iitm.ac.in/indic-glue - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages](https://aclanthology.org/2020.findings-emnlp.445/) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 3.51 GB - **Size of the generated dataset:** 1.65 GB - **Total amount of disk used:** 5.16 GB ### Dataset Summary IndicGLUE is a natural language understanding benchmark for Indian languages. It contains a wide variety of tasks and covers 11 major Indian languages - as, bn, gu, hi, kn, ml, mr, or, pa, ta, te. The Winograd Schema Challenge (Levesque et al., 2011) is a reading comprehension task in which a system must read a sentence with a pronoun and select the referent of that pronoun from a list of choices. The examples are manually constructed to foil simple statistical methods: Each one is contingent on contextual information provided by a single word or phrase in the sentence. To convert the problem into sentence pair classification, we construct sentence pairs by replacing the ambiguous pronoun with each possible referent. The task is to predict if the sentence with the pronoun substituted is entailed by the original sentence. We use a small evaluation set consisting of new examples derived from fiction books that was shared privately by the authors of the original corpus. While the included training set is balanced between two classes, the test set is imbalanced between them (65% not entailment). Also, due to a data quirk, the development set is adversarial: hypotheses are sometimes shared between training and development examples, so if a model memorizes the training examples, they will predict the wrong label on corresponding development set example. As with QNLI, each example is evaluated separately, so there is not a systematic correspondence between a model's score on this task and its score on the unconverted original task. We call converted dataset WNLI (Winograd NLI). This dataset is translated and publicly released for 3 Indian languages by AI4Bharat. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### actsa-sc.te - **Size of downloaded dataset files:** 0.38 MB - **Size of the generated dataset:** 1.71 MB - **Total amount of disk used:** 2.09 MB An example of 'validation' looks as follows. ``` This example was too long and was cropped: { "label": 0, "text": "\"ప్రయాణాల్లో ఉన్నవారికోసం బస్ స్టేషన్లు, రైల్వే స్టేషన్లలో పల్స్పోలియో బూతులను ఏర్పాటు చేసి చిన్నారులకు పోలియో చుక్కలు వేసేలా ఏర..." } ``` #### bbca.hi - **Size of downloaded dataset files:** 5.77 MB - **Size of the generated dataset:** 27.63 MB - **Total amount of disk used:** 33.40 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "label": "pakistan", "text": "\"नेटिजन यानि इंटरनेट पर सक्रिय नागरिक अब ट्विटर पर सरकार द्वारा लगाए प्रतिबंधों के समर्थन या विरोध में अपने विचार व्यक्त करते है..." } ``` #### copa.en - **Size of downloaded dataset files:** 0.75 MB - **Size of the generated dataset:** 0.12 MB - **Total amount of disk used:** 0.87 MB An example of 'validation' looks as follows. ``` { "choice1": "I swept the floor in the unoccupied room.", "choice2": "I shut off the light in the unoccupied room.", "label": 1, "premise": "I wanted to conserve energy.", "question": "effect" } ``` #### copa.gu - **Size of downloaded dataset files:** 0.75 MB - **Size of the generated dataset:** 0.23 MB - **Total amount of disk used:** 0.99 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "choice1": "\"સ્ત્રી જાણતી હતી કે તેનો મિત્ર મુશ્કેલ સમયમાંથી પસાર થઈ રહ્યો છે.\"...", "choice2": "\"મહિલાને લાગ્યું કે તેના મિત્રએ તેની દયાળુ લાભ લીધો છે.\"...", "label": 0, "premise": "મહિલાએ તેના મિત્રની મુશ્કેલ વર્તન સહન કરી.", "question": "cause" } ``` #### copa.hi - **Size of downloaded dataset files:** 0.75 MB - **Size of the generated dataset:** 0.23 MB - **Total amount of disk used:** 0.99 MB An example of 'validation' looks as follows. ``` { "choice1": "मैंने उसका प्रस्ताव ठुकरा दिया।", "choice2": "उन्होंने मुझे उत्पाद खरीदने के लिए राजी किया।", "label": 0, "premise": "मैंने सेल्समैन की पिच पर शक किया।", "question": "effect" } ``` ### Data Fields The data fields are the same among all splits. #### actsa-sc.te - `text`: a `string` feature. - `label`: a classification label, with possible values including `positive` (0), `negative` (1). #### bbca.hi - `label`: a `string` feature. - `text`: a `string` feature. #### copa.en - `premise`: a `string` feature. - `choice1`: a `string` feature. - `choice2`: a `string` feature. - `question`: a `string` feature. - `label`: a `int32` feature. #### copa.gu - `premise`: a `string` feature. - `choice1`: a `string` feature. - `choice2`: a `string` feature. - `question`: a `string` feature. - `label`: a `int32` feature. #### copa.hi - `premise`: a `string` feature. - `choice1`: a `string` feature. - `choice2`: a `string` feature. - `question`: a `string` feature. - `label`: a `int32` feature. ### Data Splits #### actsa-sc.te | |train|validation|test| |-----------|----:|---------:|---:| |actsa-sc.te| 4328| 541| 541| #### bbca.hi | |train|test| |-------|----:|---:| |bbca.hi| 3467| 866| #### copa.en | |train|validation|test| |-------|----:|---------:|---:| |copa.en| 400| 100| 500| #### copa.gu | |train|validation|test| |-------|----:|---------:|---:| |copa.gu| 362| 88| 448| #### copa.hi | |train|validation|test| |-------|----:|---------:|---:| |copa.hi| 362| 88| 449| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @inproceedings{kakwani-etal-2020-indicnlpsuite, title = "{I}ndic{NLPS}uite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for {I}ndian Languages", author = "Kakwani, Divyanshu and Kunchukuttan, Anoop and Golla, Satish and N.C., Gokul and Bhattacharyya, Avik and Khapra, Mitesh M. and Kumar, Pratyush", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.findings-emnlp.445", doi = "10.18653/v1/2020.findings-emnlp.445", pages = "4948--4961", } @inproceedings{Levesque2011TheWS, title={The Winograd Schema Challenge}, author={H. Levesque and E. Davis and L. Morgenstern}, booktitle={KR}, year={2011} } ``` ### Contributions Thanks to [@sumanthd17](https://github.com/sumanthd17) for adding this dataset.

AISE-TUDelft/MSR_Intermediate

AISE-TUDelft

--- dataset_info: - config_name: ANTLRExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 7557410 num_examples: 541 download_size: 2707259 dataset_size: 7557410 - config_name: AdaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 578367556 num_examples: 35425 download_size: 110673452 dataset_size: 578367556 - config_name: AdaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 578655182 num_examples: 35425 download_size: 111025773 dataset_size: 578655182 - config_name: AgdaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 38226393 num_examples: 5113 download_size: 14182143 dataset_size: 38226393 - config_name: AgdaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 38267937 num_examples: 5113 download_size: 14217347 dataset_size: 38267937 - config_name: AntlrNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 7561706 num_examples: 541 download_size: 2724032 dataset_size: 7561706 - config_name: ApexExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 24569165 num_examples: 7641 download_size: 6353866 dataset_size: 24569165 - config_name: ApexNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool splits: - name: train num_bytes: 24631233 num_examples: 7641 download_size: 6368630 dataset_size: 24631233 - config_name: AssemblyExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 2053432940 num_examples: 104901 download_size: 547495918 dataset_size: 2053432940 - config_name: AssemblyNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 2054324591 num_examples: 104901 download_size: 549503862 dataset_size: 2054324591 - config_name: C#Exact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 26661602730 num_examples: 3770829 download_size: 6588906272 dataset_size: 26661602730 - config_name: C#Near features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 26663488268 num_examples: 3770829 download_size: 6603075859 dataset_size: 26663488268 - config_name: CExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 89736233404 num_examples: 4960192 download_size: 28128090840 dataset_size: 89736233404 - config_name: CNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 89738714139 num_examples: 4960192 download_size: 28299862901 dataset_size: 89738714139 - config_name: COBOLExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 6629054 num_examples: 1208 download_size: 1750557 dataset_size: 6629054 - config_name: CPP2Near features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 58160863267 num_examples: 4811620 download_size: 17129813603 dataset_size: 58160863267 - config_name: CPPExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 58160261610 num_examples: 4811620 download_size: 17076690695 dataset_size: 58160261610 - config_name: CPPNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 58162667758 num_examples: 4811620 download_size: 17132623057 dataset_size: 58162667758 - config_name: ClojureExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 1421032074 num_examples: 273181 download_size: 459309399 dataset_size: 1421032074 - config_name: ClojureNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 1421066089 num_examples: 273181 download_size: 460645609 dataset_size: 1421066089 - config_name: CobolNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 6629000 num_examples: 1208 download_size: 1733668 dataset_size: 6629000 - config_name: CommonLispExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 296677534 num_examples: 16968 download_size: 109149148 dataset_size: 296677534 - config_name: CommonLispNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 296679380 num_examples: 16968 download_size: 110407258 dataset_size: 296679380 - config_name: CoqExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 632649581 num_examples: 26175 download_size: 189961246 dataset_size: 632649581 - config_name: CoqNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 632652578 num_examples: 26175 download_size: 190833648 dataset_size: 632652578 - config_name: CrystalExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 31335756 num_examples: 7300 download_size: 10366475 dataset_size: 31335756 - config_name: CrystalNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 31336434 num_examples: 7300 download_size: 10379390 dataset_size: 31336434 - config_name: CudaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 334592336 num_examples: 13359 download_size: 102491703 dataset_size: 334592336 - config_name: CudaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 334593801 num_examples: 13359 download_size: 102875919 dataset_size: 334593801 - config_name: DExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 3255384976 num_examples: 126111 download_size: 1129728566 dataset_size: 3255384976 - config_name: DNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 3255400520 num_examples: 126111 download_size: 1135463467 dataset_size: 3255400520 - config_name: DartExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 2329045207 num_examples: 413203 download_size: 669869628 dataset_size: 2329045207 - config_name: DartNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 2329096793 num_examples: 413203 download_size: 670901970 dataset_size: 2329096793 - config_name: EJSExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 71531393 num_examples: 12884 download_size: 21195866 dataset_size: 71531393 - config_name: EjsNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStack dtype: bool - name: near_dups_stackv2 dtype: bool splits: - name: train num_bytes: 71635864 num_examples: 12884 download_size: 21210665 dataset_size: 71635864 - config_name: ElixirExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 841135120 num_examples: 127910 download_size: 298160239 dataset_size: 841135120 - config_name: ElixirNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 841151060 num_examples: 127910 download_size: 298816538 dataset_size: 841151060 - config_name: ElmExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 8383 num_examples: 7 download_size: 27695 dataset_size: 8383 - config_name: ElmNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 8354 num_examples: 7 download_size: 22185 dataset_size: 8354 - config_name: EmacsLispExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 250101478 num_examples: 7963 download_size: 86051810 dataset_size: 250101478 - config_name: EmacsLispNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 250102362 num_examples: 7963 download_size: 86437277 dataset_size: 250102362 - config_name: ErlangExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 372175368 num_examples: 32049 download_size: 110494347 dataset_size: 372175368 - config_name: ErlangNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 372179250 num_examples: 32049 download_size: 110899584 dataset_size: 372179250 - config_name: F#Exact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 192500693 num_examples: 16015 download_size: 47297899 dataset_size: 192500693 - config_name: F#Near features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 192502511 num_examples: 16015 download_size: 47470253 dataset_size: 192502511 - config_name: ForthExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 347106780 num_examples: 7932 download_size: 144504016 dataset_size: 347106780 - config_name: ForthNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 347107612 num_examples: 7932 download_size: 146797290 dataset_size: 347107612 - config_name: FortranExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 2847566 num_examples: 63 download_size: 1054373 dataset_size: 2847566 - config_name: FortranNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 2847315 num_examples: 63 download_size: 1062081 dataset_size: 2847315 - config_name: GoExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 26167202808 num_examples: 2355716 download_size: 8138108314 dataset_size: 26167202808 - config_name: GoNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 26168086245 num_examples: 2355716 download_size: 8174167267 dataset_size: 26168086245 - config_name: GraphQLExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 38263 num_examples: 3 download_size: 36182 dataset_size: 38263 - config_name: GraphQLNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 38254 num_examples: 3 download_size: 32912 dataset_size: 38254 - config_name: GroovyExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 248453777 num_examples: 48353 download_size: 78401132 dataset_size: 248453777 - config_name: GroovyNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 248459647 num_examples: 48353 download_size: 78630814 dataset_size: 248459647 - config_name: HackExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 380628718 num_examples: 37405 download_size: 128232166 dataset_size: 380628718 - config_name: HackNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 380633269 num_examples: 37405 download_size: 128649687 dataset_size: 380633269 - config_name: HaskellExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 689851801 num_examples: 111234 download_size: 236120258 dataset_size: 689851801 - config_name: HaskellNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 689893289 num_examples: 111234 download_size: 236739420 dataset_size: 689893289 - config_name: HaskellNearT features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 689893289 num_examples: 111234 download_size: 236739420 dataset_size: 689893289 - config_name: HaskellTest features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: near_duplicates_redpajama dtype: bool splits: - name: train num_bytes: 689865477 num_examples: 111234 download_size: 236693079 dataset_size: 689865477 - config_name: HaskellTest2 features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: near_duplicates_ghcode dtype: bool splits: - name: train num_bytes: 689865477 num_examples: 111234 download_size: 236695867 dataset_size: 689865477 - config_name: JavaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 32486202146 num_examples: 5197338 download_size: 8535677041 dataset_size: 32486202146 - config_name: JavaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 32488151167 num_examples: 5197338 download_size: 8542985524 dataset_size: 32488151167 - config_name: JavaNearF features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_duplicates_githubcode dtype: bool splits: - name: train num_bytes: 32488800842 num_examples: 5197338 download_size: 8543979432 dataset_size: 32488800842 - config_name: JavaScriptExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 88087310969 num_examples: 3393747 download_size: 28914572193 dataset_size: 88087310969 - config_name: JavaScriptNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 88089008184 num_examples: 3393747 download_size: 29083319680 dataset_size: 88089008184 - config_name: JuliaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 967638517 num_examples: 38381 download_size: 246231934 dataset_size: 967638517 - config_name: JuliaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 967652903 num_examples: 38381 download_size: 247077270 dataset_size: 967652903 - config_name: JupyterNotebookExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 11722076020 num_examples: 35313 download_size: 9067703543 dataset_size: 11722076020 - config_name: KotlinExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 3812037093 num_examples: 1045396 download_size: 1110654794 dataset_size: 3812037093 - config_name: KotlinNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 3812167735 num_examples: 1045396 download_size: 1110429592 dataset_size: 3812167735 - config_name: LessExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 95845785 num_examples: 7389 download_size: 26480395 dataset_size: 95845785 - config_name: LessNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 95846529 num_examples: 7389 download_size: 26477572 dataset_size: 95846529 - config_name: LuaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 8353646445 num_examples: 913898 download_size: 2505145950 dataset_size: 8353646445 - config_name: LuaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 8353989182 num_examples: 913898 download_size: 2515603988 dataset_size: 8353989182 - config_name: MathematicaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 7321356594 num_examples: 89853 download_size: 3584669375 dataset_size: 7321356594 - config_name: MathematicaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_duplicates_redpajama dtype: bool splits: - name: train num_bytes: 7321378962 num_examples: 89853 download_size: 3602914923 dataset_size: 7321378962 - config_name: MatlabExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 6903374516 num_examples: 665659 download_size: 2399794447 dataset_size: 6903374516 - config_name: MatlabNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 6903540783 num_examples: 665659 download_size: 2414346658 dataset_size: 6903540783 - config_name: NetLogoExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 41827450 num_examples: 863 download_size: 11620917 dataset_size: 41827450 - config_name: NetLogoNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 41827458 num_examples: 863 download_size: 11679805 dataset_size: 41827458 - config_name: NewLispExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 52918884 num_examples: 5148 download_size: 14039770 dataset_size: 52918884 - config_name: NewLispNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool splits: - name: train num_bytes: 52918764 num_examples: 5148 download_size: 14074385 dataset_size: 52918764 - config_name: NixExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 203855711 num_examples: 71199 download_size: 78575477 dataset_size: 203855711 - config_name: NixNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 203864476 num_examples: 71199 download_size: 78726489 dataset_size: 203864476 - config_name: OCamlExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 648064551 num_examples: 69171 download_size: 222300297 dataset_size: 648064551 - config_name: OCamlNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 648072984 num_examples: 69171 download_size: 222952991 dataset_size: 648072984 - config_name: Objective-CExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 9602633568 num_examples: 698137 download_size: 3703274717 dataset_size: 9602633568 - config_name: Objective-CNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 9602720799 num_examples: 698137 download_size: 3719903322 dataset_size: 9602720799 - config_name: PHPExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 25438710903 num_examples: 3363040 download_size: 7613380934 dataset_size: 25438710903 - config_name: PHPNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 25440392419 num_examples: 3363040 download_size: 7635635671 dataset_size: 25440392419 - config_name: PascalExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 7655488388 num_examples: 225749 download_size: 2498908413 dataset_size: 7655488388 - config_name: PascalNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 7655516624 num_examples: 225749 download_size: 2517922393 dataset_size: 7655516624 - config_name: PerlExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 16870280664 num_examples: 629769 download_size: 5734951211 dataset_size: 16870280664 - config_name: PerlNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 16870516978 num_examples: 629769 download_size: 5771999455 dataset_size: 16870516978 - config_name: ProcessingExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 84096293 num_examples: 20343 download_size: 29270300 dataset_size: 84096293 - config_name: ProcessingNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 84098751 num_examples: 20343 download_size: 29246387 dataset_size: 84098751 - config_name: PrologExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool splits: - name: train num_bytes: 691824350 num_examples: 20279 download_size: 191072651 dataset_size: 691824350 - config_name: PrologNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 691829302 num_examples: 20279 download_size: 192117293 dataset_size: 691829302 - config_name: PythonExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_CodeParrot dtype: bool splits: - name: train num_bytes: 25545914243 num_examples: 1792451 download_size: 10130671538 dataset_size: 25545914243 - config_name: PythonNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool - name: near_dups_codeparrot dtype: bool - name: near_dups_ghcode dtype: bool splits: - name: train num_bytes: 25546586522 num_examples: 1792451 download_size: 10170421542 dataset_size: 25546586522 - config_name: PythonParrot features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_CodeParrot dtype: bool - name: near_duplicates_codeparrot dtype: bool splits: - name: train num_bytes: 25546138378 num_examples: 1792451 download_size: 10169529284 dataset_size: 25546138378 - config_name: PythonTest features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool - name: exact_dupe_CodeParrot dtype: bool - name: near_duplicates_redpajama dtype: bool splits: - name: train num_bytes: 25546138386 num_examples: 1792451 download_size: 10169495473 dataset_size: 25546138386 - config_name: RExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 21442634265 num_examples: 374812 download_size: 8600403423 dataset_size: 21442634265 - config_name: RNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 21445679622 num_examples: 374812 download_size: 8727132044 dataset_size: 21445679622 - config_name: RakuExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 4553176 num_examples: 1299 download_size: 1377473 dataset_size: 4553176 - config_name: RakuNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool splits: - name: train num_bytes: 4553060 num_examples: 1299 download_size: 1372440 dataset_size: 4553060 - config_name: RubyExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 2981769330 num_examples: 794364 download_size: 1009215918 dataset_size: 2981769330 - config_name: RubyNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 2982067120 num_examples: 794364 download_size: 1010741791 dataset_size: 2982067120 - config_name: RustExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 8834624371 num_examples: 844258 download_size: 2619167582 dataset_size: 8834624371 - config_name: RustNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 8834835442 num_examples: 844258 download_size: 2628770077 dataset_size: 8834835442 - config_name: SQLExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 392804973 num_examples: 41178 download_size: 87660816 dataset_size: 392804973 - config_name: SQLNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 392820273 num_examples: 41178 download_size: 87888246 dataset_size: 392820273 - config_name: ScalaExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 1121907877 num_examples: 224021 download_size: 357412683 dataset_size: 1121907877 - config_name: ScalaNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_ghcode dtype: bool - name: near_dups_stackv1 dtype: bool - name: near_dups_redpajama dtype: bool splits: - name: train num_bytes: 1121963752 num_examples: 224021 download_size: 358048356 dataset_size: 1121963752 - config_name: SchemeExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 1666453613 num_examples: 54226 download_size: 609833105 dataset_size: 1666453613 - config_name: SchemeNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 1666453595 num_examples: 54226 download_size: 615428052 dataset_size: 1666453595 - config_name: ScilabExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 40724888 num_examples: 4084 download_size: 19426798 dataset_size: 40724888 - config_name: ScilabNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 40724883 num_examples: 4084 download_size: 19424804 dataset_size: 40724883 - config_name: StarlarkExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 3457635 num_examples: 498 download_size: 1347364 dataset_size: 3457635 - config_name: StarlarkNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool splits: - name: train num_bytes: 3457631 num_examples: 498 download_size: 1352131 dataset_size: 3457631 - config_name: SwiftExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 2713542331 num_examples: 439565 download_size: 854140622 dataset_size: 2713542331 - config_name: SwiftNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 2713542195 num_examples: 439565 download_size: 855986444 dataset_size: 2713542195 - config_name: TurtleExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 3442516 num_examples: 17 download_size: 799325 dataset_size: 3442516 - config_name: TypeScriptExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 14176972339 num_examples: 2837126 download_size: 4433625232 dataset_size: 14176972339 - config_name: VueExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 2137815900 num_examples: 323672 download_size: 674476397 dataset_size: 2137815900 - config_name: VueNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_TheStackV1 dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 2137815643 num_examples: 323672 download_size: 676642096 dataset_size: 2137815643 - config_name: WebAssemblyExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: exact_dupe_GithubCode dtype: bool splits: - name: train num_bytes: 120184637 num_examples: 585 download_size: 39377515 dataset_size: 120184637 - config_name: WebAssemblyNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: exact_dupe_TheStackV2 dtype: bool - name: exact_dupe_TheStack dtype: bool - name: exact_dupe_RedPajama dtype: bool - name: near_dups_stackv2 dtype: bool - name: near_dups_stackv1 dtype: bool splits: - name: train num_bytes: 120184495 num_examples: 585 download_size: 39587423 dataset_size: 120184495 configs: - config_name: ANTLRExact data_files: - split: train path: data/ANTLR_Exact/train-* - config_name: AdaExact data_files: - split: train path: data/Ada_Exact/train-* - config_name: AdaNear data_files: - split: train path: data/Ada_Near/train-* - config_name: AgdaExact data_files: - split: train path: data/Agda_Exact/train-* - config_name: AgdaNear data_files: - split: train path: data/Agda_Near/train-* - config_name: AntlrNear data_files: - split: train path: data/Antlr_Near/train-* - config_name: ApexExact data_files: - split: train path: data/Apex_Exact/train-* - config_name: ApexNear data_files: - split: train path: data/Apex_Near/train-* - config_name: AssemblyExact data_files: - split: train path: data/Assembly_Exact/train-* - config_name: AssemblyNear data_files: - split: train path: data/Assembly_Near/train-* - config_name: C#Exact data_files: - split: train path: data/C#_Exact/train-* - config_name: C#Near data_files: - split: train path: data/C#_Near/train-* - config_name: CExact data_files: - split: train path: data/C_Exact/train-* - config_name: CNear data_files: - split: train path: data/C_Near/train-* - config_name: COBOLExact data_files: - split: train path: data/COBOL_Exact/train-* - config_name: CPP2Near data_files: - split: train path: data/CPP2_Near/train-* - config_name: CPPExact data_files: - split: train path: data/CPP_Exact/train-* - config_name: CPPNear data_files: - split: train path: data/CPP_Near/train-* - config_name: ClojureExact data_files: - split: train path: data/Clojure_Exact/train-* - config_name: ClojureNear data_files: - split: train path: data/Clojure_Near/train-* - config_name: CobolNear data_files: - split: train path: data/Cobol_Near/train-* - config_name: CommonLispExact data_files: - split: train path: data/CommonLisp_Exact/train-* - config_name: CommonLispNear data_files: - split: train path: data/CommonLisp_Near/train-* - config_name: CoqExact data_files: - split: train path: data/Coq_Exact/train-* - config_name: CoqNear data_files: - split: train path: data/Coq_Near/train-* - config_name: CrystalExact data_files: - split: train path: data/Crystal_Exact/train-* - config_name: CrystalNear data_files: - split: train path: data/Crystal_Near/train-* - config_name: CudaExact data_files: - split: train path: data/Cuda_Exact/train-* - config_name: CudaNear data_files: - split: train path: data/Cuda_Near/train-* - config_name: DExact data_files: - split: train path: data/D_Exact/train-* - config_name: DNear data_files: - split: train path: data/D_Near/train-* - config_name: DartExact data_files: - split: train path: data/Dart_Exact/train-* - config_name: DartNear data_files: - split: train path: data/Dart_Near/train-* - config_name: EJSExact data_files: - split: train path: data/EJS_Exact/train-* - config_name: EjsNear data_files: - split: train path: data/Ejs_Near/train-* - config_name: ElixirExact data_files: - split: train path: data/Elixir_Exact/train-* - config_name: ElixirNear data_files: - split: train path: data/Elixir_Near/train-* - config_name: ElmExact data_files: - split: train path: data/Elm_Exact/train-* - config_name: ElmNear data_files: - split: train path: data/Elm_Near/train-* - config_name: EmacsLispExact data_files: - split: train path: data/EmacsLisp_Exact/train-* - config_name: EmacsLispNear data_files: - split: train path: data/EmacsLisp_Near/train-* - config_name: ErlangExact data_files: - split: train path: data/Erlang_Exact/train-* - config_name: ErlangNear data_files: - split: train path: data/Erlang_Near/train-* - config_name: F#Exact data_files: - split: train path: data/F#_Exact/train-* - config_name: F#Near data_files: - split: train path: data/F#_Near/train-* - config_name: ForthExact data_files: - split: train path: data/Forth_Exact/train-* - config_name: ForthNear data_files: - split: train path: data/Forth_Near/train-* - config_name: FortranExact data_files: - split: train path: data/Fortran_Exact/train-* - config_name: FortranNear data_files: - split: train path: data/Fortran_Near/train-* - config_name: GoExact data_files: - split: train path: data/Go_Exact/train-* - config_name: GoNear data_files: - split: train path: data/Go_Near/train-* - config_name: GraphQLExact data_files: - split: train path: data/GraphQL_Exact/train-* - config_name: GraphQLNear data_files: - split: train path: data/GraphQL_Near/train-* - config_name: GroovyExact data_files: - split: train path: data/Groovy_Exact/train-* - config_name: GroovyNear data_files: - split: train path: data/Groovy_Near/train-* - config_name: HackExact data_files: - split: train path: data/Hack_Exact/train-* - config_name: HackNear data_files: - split: train path: data/Hack_Near/train-* - config_name: HaskellExact data_files: - split: train path: data/Haskell_Exact/train-* - config_name: HaskellNear data_files: - split: train path: data/Haskell_Near/train-* - config_name: HaskellNearT data_files: - split: train path: data/Haskell_NearT/train-* - config_name: HaskellTest data_files: - split: train path: data/Haskell_Test/train-* - config_name: HaskellTest2 data_files: - split: train path: data/Haskell_Test2/train-* - config_name: JavaExact data_files: - split: train path: data/Java_Exact/train-* - config_name: JavaNear data_files: - split: train path: data/Java_Near/train-* - config_name: JavaNearF data_files: - split: train path: data/Java_NearF/train-* - config_name: JavaScriptExact data_files: - split: train path: data/JavaScript_Exact/train-* - config_name: JavaScriptNear data_files: - split: train path: data/JavaScript_Near/train-* - config_name: JuliaExact data_files: - split: train path: data/Julia_Exact/train-* - config_name: JuliaNear data_files: - split: train path: data/Julia_Near/train-* - config_name: JupyterNotebookExact data_files: - split: train path: data/JupyterNotebook_Exact/train-* - config_name: KotlinExact data_files: - split: train path: data/Kotlin_Exact/train-* - config_name: KotlinNear data_files: - split: train path: data/Kotlin_Near/train-* - config_name: LessExact data_files: - split: train path: data/Less_Exact/train-* - config_name: LessNear data_files: - split: train path: data/Less_Near/train-* - config_name: LuaExact data_files: - split: train path: data/Lua_Exact/train-* - config_name: LuaNear data_files: - split: train path: data/Lua_Near/train-* - config_name: MathematicaExact data_files: - split: train path: data/Mathematica_Exact/train-* - config_name: MathematicaNear data_files: - split: train path: data/Mathematica_Near/train-* - config_name: MatlabExact data_files: - split: train path: data/Matlab_Exact/train-* - config_name: MatlabNear data_files: - split: train path: data/Matlab_Near/train-* - config_name: NetLogoExact data_files: - split: train path: data/NetLogo_Exact/train-* - config_name: NetLogoNear data_files: - split: train path: data/NetLogo_Near/train-* - config_name: NewLispExact data_files: - split: train path: data/NewLisp_Exact/train-* - config_name: NewLispNear data_files: - split: train path: data/NewLisp_Near/train-* - config_name: NixExact data_files: - split: train path: data/Nix_Exact/train-* - config_name: NixNear data_files: - split: train path: data/Nix_Near/train-* - config_name: OCamlExact data_files: - split: train path: data/OCaml_Exact/train-* - config_name: OCamlNear data_files: - split: train path: data/OCaml_Near/train-* - config_name: Objective-CExact data_files: - split: train path: data/Objective-C_Exact/train-* - config_name: Objective-CNear data_files: - split: train path: data/Objective-C_Near/train-* - config_name: PHPExact data_files: - split: train path: data/PHP_Exact/train-* - config_name: PHPNear data_files: - split: train path: data/PHP_Near/train-* - config_name: PascalExact data_files: - split: train path: data/Pascal_Exact/train-* - config_name: PascalNear data_files: - split: train path: data/Pascal_Near/train-* - config_name: PerlExact data_files: - split: train path: data/Perl_Exact/train-* - config_name: PerlNear data_files: - split: train path: data/Perl_Near/train-* - config_name: ProcessingExact data_files: - split: train path: data/Processing_Exact/train-* - config_name: ProcessingNear data_files: - split: train path: data/Processing_Near/train-* - config_name: PrologExact data_files: - split: train path: data/Prolog_Exact/train-* - config_name: PrologNear data_files: - split: train path: data/Prolog_Near/train-* - config_name: PythonExact data_files: - split: train path: data/Python_Exact/train-* - config_name: PythonNear data_files: - split: train path: data/Python_Near/train-* - config_name: PythonParrot data_files: - split: train path: data/Python_Parrot/train-* - config_name: PythonTest data_files: - split: train path: data/Python_Test/train-* - config_name: RExact data_files: - split: train path: data/R_Exact/train-* - config_name: RNear data_files: - split: train path: data/R_Near/train-* - config_name: RakuExact data_files: - split: train path: data/Raku_Exact/train-* - config_name: RakuNear data_files: - split: train path: data/Raku_Near/train-* - config_name: RubyExact data_files: - split: train path: data/Ruby_Exact/train-* - config_name: RubyNear data_files: - split: train path: data/Ruby_Near/train-* - config_name: RustExact data_files: - split: train path: data/Rust_Exact/train-* - config_name: RustNear data_files: - split: train path: data/Rust_Near/train-* - config_name: SQLExact data_files: - split: train path: data/SQL_Exact/train-* - config_name: SQLNear data_files: - split: train path: data/SQL_Near/train-* - config_name: ScalaExact data_files: - split: train path: data/Scala_Exact/train-* - config_name: ScalaNear data_files: - split: train path: data/Scala_Near/train-* - config_name: SchemeExact data_files: - split: train path: data/Scheme_Exact/train-* - config_name: SchemeNear data_files: - split: train path: data/Scheme_Near/train-* - config_name: ScilabExact data_files: - split: train path: data/Scilab_Exact/train-* - config_name: ScilabNear data_files: - split: train path: data/Scilab_Near/train-* - config_name: StarlarkExact data_files: - split: train path: data/Starlark_Exact/train-* - config_name: StarlarkNear data_files: - split: train path: data/Starlark_Near/train-* - config_name: SwiftExact data_files: - split: train path: data/Swift_Exact/train-* - config_name: SwiftNear data_files: - split: train path: data/Swift_Near/train-* - config_name: TurtleExact data_files: - split: train path: data/Turtle_Exact/train-* - config_name: TypeScriptExact data_files: - split: train path: data/TypeScript_Exact/train-* - config_name: VueExact data_files: - split: train path: data/Vue_Exact/train-* - config_name: VueNear data_files: - split: train path: data/Vue_Near/train-* - config_name: WebAssemblyExact data_files: - split: train path: data/WebAssembly_Exact/train-* - config_name: WebAssemblyNear data_files: - split: train path: data/WebAssembly_Near/train-* ---

CropNet/CropNet

CropNet

--- license: cc-by-4.0 language: - en tags: - agriculture - climate size_categories: - n>1T --- # An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions  The CropNet dataset is an open, large-scale, and deep learning-ready dataset, specifically targeting climate change-aware crop yield predictions for the contiguous United States (U.S.) continent at the county level. It is composed of three modalities of data, i.e., Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, aligned in both the spatial and temporal domains, for over 2200 U.S. counties spanning 6 years (2017-2022). It is expected to facilitate researchers in developing deep learning models for timely and precisely predicting crop yields at the county level, by accounting for the effects of both short-term growing season weather variations and long-term climate change on crop yields. Although our initial goal of crafting the CropNet dataset is for precise crop yield prediction, we believe its future applicability is broad and can benefit the deep learning, agriculture, and meteorology communities, for exploring more interesting, critical, and climate change-related applications, by using one or more modalities of data. ## Citation If you use our dataset, please cite [our paper](https://dl.acm.org/doi/10.1145/3637528.3671536): ``` @inproceedings{fudong:kdd24:crop_net, author = {Fudong Lin and Kaleb Guillot and Summer Crawford and Yihe Zhang and Xu Yuan and Nian{-}Feng Tzeng}, title = {An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions}, booktitle = {Proceedings of the 30th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining (KDD)}, pages = {5375--5386}, year = {2024} } ``` [Our MMST-ViT model](https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_MMST-ViT_Climate_Change-aware_Crop_Yield_Prediction_via_Multi-Modal_Spatial-Temporal_Vision_ICCV_2023_paper.pdf) demonstrates how to develop deep-learning models for climate change-aware crop yield predictions. If you use MMST-ViT in your research, please cite our paper: ``` @inproceedings{fudong:iccv23:mmst_vit, title={MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer}, author={Lin, Fudong and Crawford, Summer and Guillot, Kaleb and Zhang, Yihe and Chen, Yan and Yuan, Xu and others}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={5774--5784}, year={2023} } ``` ## Contributions #### The `CropNet` dataset - The first *terabyte-sized*, publicly available, and multi-modal dataset for climate change-aware crop yield predictions #### The `CropNet` package - A *deep learning-ready* Python package for facilitating researchers in downloading the CropNet data on the fly over the time and region of interest, and developing deep neural networks (DNNs) for climate change-aware crop yield predictions - The `CropNet` package is available at [Python Package Index (PyPI)](https://pypi.org/project/cropnet/) ## Tutorials The tutorials for the CropNet dataset are available at Google Colab, with their links listed below - [Sentinel-2 Imagery Tutorial](https://colab.research.google.com/drive/1Tj69JdhO7aX8ks-4UWYvHrFm9GB1PNCd?usp=sharing) - [WRF-HRRR Computed Dataset Tutorial](https://colab.research.google.com/drive/14l-JSNHtelawNu3kVG_ukTd2WUJpaZEc?usp=sharing) - [USDA Crop Dataset Tutorial](https://colab.research.google.com/drive/1U-vFoRyLSb2l2Q67LeGbkUKTeRaHDkkK?usp=sharing) ## The CropNet Dataset 0ur CropNet dataset is composed of three modalities of data, i.e., Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, spanning from 2017 to 2022 (i.e., 6 years) across 2291 U.S. counties, with its geographic distribution illustrated below. We also include the number of counties corresponding to each crop type in the USDA Crop Dataset (see the rightmost bar chart in the figure) since crop planting is highly geography-dependent.  ### Sentinel-2 Imagery The Sentinel-2 Imagery, obtained from the Sentinel-2 mission, provides high-resolution satellite images for monitoring crop growth on the ground. It contains two types of 224x224 RGB satellite images, agriculture imagery (AG) and normalized difference vegetation index (NDVI), both with a spatial resolution of 9x9 km, and a revisit frequency of 14 days. Examples of AG and NDVI images are depicted as follows. - **Agriculture Imagery (AG)**  - **Normalized Difference Vegetation Index (NDVI)**  ### WRF-HRRR Computed Dataset The WRF-HRRR Computed Dataset, sourced from the WRF-HRRR model, contains daily and monthly meteorological parameters, with the former and the latter designed for capturing direct effects of short-term growing season weather variations on crop growth, and for learning indirect impacts of long-term climate change on crop yields, respectively. It contains 9 meteorological parameters gridded at 9 km in a one-day (and one-month) interval. The figures show the temperature in the spring, the summer, the fall, and the winter, respectively.  ### USDA Crop Dataset The USDA Crop Dataset, collected from the USDA Quick Statistic website, offers valuable information, such as production, yield, etc., for crops grown at each available county. It offers crop information for four types of crops, i.e., corn, cotton, soybeans, and winter wheat, at a county-level basis, with a temporal resolution of one year. The figure illustrates the 2022 Corn Yield across the United States.  ### The CropNet Package Beyond the contribution of our CropNet dataset, we also release the CropNet package in the Python Package Index (PyPI) for facilitating researchers in downloading the CropNet data based on the time and region of interest, and flexibly building their deep learning models for accurate crop yield predictions. In particular, the CropNet package includes three types of APIs, listed as follows: - **DataDownloader**: This API allows users to download the CropNet data over the time/region of interest on the fly. - **DataRetriever**: With this API, users can conveniently obtain the CropNet data stored in the local machine (e.g., if you have downloaded our curated CropNet from Google Drive) over the time/region of interest. - **DataLoader**: This API is designed to facilitate researchers in developing their DNNs for accurate crop yield predictions. Specifically, the code in this API ( 1) combines all three modalities of data to create $(\mathbf{x}, \mathbf{y_{s}}, \mathbf{y_{l}}, \mathbf{z})$ tuples, with $\mathbf{x}, \mathbf{y_{s}}, \mathbf{y_{l}}, \text{and}~ \mathbf{z}$, respectively representing satellite images, short-term daily whether parameters, long-term monthly meteorological parameters, and ground-truth crop yield (or production) information, and then (2) exposes those tuples via a `Dataset` object after appropriate data pre-processing techniques. ### Installation Researchers and practitioners can install the latest version of CropNet with the following commands: ```python # Create and activate a conda environment conda create -n cropnet_api python=3.10 conda activate cropnet_api # Install the latest version of CropNet pip install cropnet # Slove the ecCodes library dependency issue pip install ecmwflibs ``` ### CropNet API Examples - **Example 1: A DataDownloader Example for Downloading the Up-to-date CropNet Data** Given the time and region (i.e., the FIPS codes for two U.S. counties) of interest, the following code presents how to utilize the **DataDownloader** to download the up-to-date CropNet data: ```python from cropnet.data_downloader import DataDownloader # Use the "target_dir" to specify where the data should be downloaded to downloader = DataDownloader(target_dir="./data") # Download 2022 USDA Soybean data # Note that most of the 2023 USDA data are not yet available downloader.download_USDA("Soybean", fips_codes=["10003", "22007"], years=["2022"]) # Download the 2023 (the 1st and 2nd quarters) Sentinel-2 Imagery downloader.download_Sentinel2(fips_codes=["10003", "22007"], years=["2023"], image_type="AG") downloader.download_Sentinel2(fips_codes=["10003", "22007"], years=["2023"], image_type="NDVI") # Download the 2023 (January to July) WRF-HRRR data downloader.download_HRRR(fips_codes=["10003", "22007"], years=["2023"]) ``` - **Example 2: A DataRetriever Example for Obtaining Our Curated CropNet Data** Given the time and region of interest, the following code shows how to use the **DataRetriever** to obtain the CropNet data stored in the local machine in a user-friendly format: ```python # Use the "base_fir" to specify where the CropNet data is stored retriever = DataRetriever(base_dir="/mnt/data/CropNet") # Retrieve the 2022 USDA Soybean data usda_data = retriever.retrieve_USDA(crop_type="Soybean", fips_codes=["10003", "22007"], years=["2022"]) # Retrieve the 2022 Sentinel-2 Imagery data sentinel2_data = retriever.retrieve_Sentinel2(fips_codes=["10003", "22007"], years=["2022"], image_type="AG") sentinel2_data = retriever.retrieve_Sentinel2(fips_codes=["10003", "22007"], years=["2022"], image_type="NDVI") # Retrieve the 2022 WRF-HRRR data hrrr_data = retriever.retrieve_HRRR(fips_codes=["10003","22007"], years=["2022"]) ``` - **Example 3: A PyTorch Example for Using the DataLoader API for Training DNNs** The following code presents a PyTorch example of training a deep learning model (i.e., MMST-ViT) for climate change-aware crop yield predictions, by utilizing the DataLoader APIs: ```python import torch from torch.utils.data import DataLoader from models_mmst_vit import MMST_ViT from cropnet.dataset.hrrr_computed_dataset import HRRRComputedDataset from cropnet.dataset.sentinel2_imagery import Sentinel2Imagery from cropnet.dataset.usda_crop_dataset import USDACropDataset # The base directory for the CropNet dataset base_dir = "/mnt/data/CropNet" # The JSON configuration file config_file = "data/soybeans_train.json" # The dataloaders for each modality of data sentinel2_loader = DataLoader(Sentinel2Imagery(base_dir, config_file), batch_size=1) hrrr_loader = DataLoader(HRRRComputedDataset(base_dir, config_file), batch_size=1) usda_loader = DataLoader(USDACropDataset(base_dir, config_file), batch_size=1) # The model, the optimizer, and the loss function model = MMST_ViT() optimizer = torch.optim.AdamW(model.parameters(), lr=1e-3, betas=(0.9, 0.999)) criterion = torch.nn.MSELoss() # Traning the model for one epoch for s, h, u in zip(sentinel2_loader, hrrr_loader, usda_loader): # x: satellite images # ys (or yl): short-term daily (or long-term monthly) weather parameters # z: ground-truth crop yield (or production) information x, ys, yl, z, = s[0], h[0], h[1], u[0] optimizer.zero_grad() z_hat = model(x, ys, yl) loss = criterion(z, z_hat) loss.backward() optimizer.step() ``` ## License CropNet has a [Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/) license. ## Dataset Terms of Use This dataset is available for research purposes only. By downloading, you agree to these terms. We are aware that unauthorized copies of our dataset have been republished on HuggingFace. Please note that any republication or distribution of this dataset without permission is prohibited and constitutes copyright infringement.

OpenGVLab/MVBench

OpenGVLab

--- license: mit extra_gated_prompt: >- You agree to not use the dataset to conduct experiments that cause harm to human subjects. Please note that the data in this dataset may be subject to other agreements. Before using the data, be sure to read the relevant agreements carefully to ensure compliant use. Video copyrights belong to the original video creators or platforms and are for academic research use only. task_categories: - visual-question-answering - video-classification extra_gated_fields: Name: text Company/Organization: text Country: text E-Mail: text modalities: - Video - Text configs: - config_name: action_sequence data_files: json/action_sequence.json - config_name: moving_count data_files: json/moving_count.json - config_name: action_prediction data_files: json/action_prediction.json - config_name: episodic_reasoning data_files: json/episodic_reasoning.json - config_name: action_antonym data_files: json/action_antonym.json - config_name: action_count data_files: json/action_count.json - config_name: scene_transition data_files: json/scene_transition.json - config_name: object_shuffle data_files: json/object_shuffle.json - config_name: object_existence data_files: json/object_existence.json - config_name: fine_grained_pose data_files: json/fine_grained_pose.json - config_name: unexpected_action data_files: json/unexpected_action.json - config_name: moving_direction data_files: json/moving_direction.json - config_name: state_change data_files: json/state_change.json - config_name: object_interaction data_files: json/object_interaction.json - config_name: character_order data_files: json/character_order.json - config_name: action_localization data_files: json/action_localization.json - config_name: counterfactual_inference data_files: json/counterfactual_inference.json - config_name: fine_grained_action data_files: json/fine_grained_action.json - config_name: moving_attribute data_files: json/moving_attribute.json - config_name: egocentric_navigation data_files: json/egocentric_navigation.json language: - en size_categories: - 1K<n<10K --- # MVBench ## Dataset Description - **Repository:** [MVBench](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb) - **Paper:** [2311.17005](https://arxiv.org/abs/2311.17005) - **Point of Contact:** mailto:[kunchang li]([email protected]) ## <span style="color: red;">Important Update</span> [18/10/2024] Due to NTU RGB+D License, 320 videos from NTU RGB+D need to be downloaded manually. Please visit [ROSE Lab](https://rose1.ntu.edu.sg/dataset/actionRecognition/) to access the data. We also provide a [list of the 320 videos](https://huggingface.co/datasets/OpenGVLab/MVBench/blob/main/video/MVBench_videos_ntu.txt) used in MVBench for your reference.  We introduce a novel static-to-dynamic method for defining temporal-related tasks. By converting static tasks into dynamic ones, we facilitate systematic generation of video tasks necessitating a wide range of temporal abilities, from perception to cognition. Guided by task definitions, we then **automatically transform public video annotations into multiple-choice QA** for task evaluation. This unique paradigm enables efficient creation of MVBench with minimal manual intervention while ensuring evaluation fairness through ground-truth video annotations and avoiding biased LLM scoring. The **20** temporal task examples are as follows.  ## Evaluation An evaluation example is provided in [mvbench.ipynb](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/mvbench.ipynb). Please follow the pipeline to prepare the evaluation code for various MLLMs. - **Preprocess**: We preserve the raw video (high resolution, long duration, etc.) along with corresponding annotations (start, end, subtitles, etc.) for future exploration; hence, the decoding of some raw videos like Perception Test may be slow. - **Prompt**: We explore effective system prompts to encourage better temporal reasoning in MLLM, as well as efficient answer prompts for option extraction. ## Leadrboard While an [Online leaderboard]() is under construction, the current standings are as follows: 

deepghs/wd14_tagger_inversion

deepghs

--- license: apache-2.0 task_categories: - feature-extraction language: - en tags: - art --- ## What's this This is the dataset for inversing the embeddings of the given prediction result. We can get the embedding dataset with some tag combinations, and search images like this. ## How is this dataset made This dataset is generated with anime images in danbooru (webp ones, based on [KBlueLeaf/danbooru2023-webp-4Mpixel](https://huggingface.co/datasets/KBlueLeaf/danbooru2023-webp-4Mpixel)), extracting the prediction results and the embeddings of each images. ## Model's goal Train a model to inverse prediction result to embeddings. Maybe a MLP can be used? I don't know, just try them.

AI-MO/NuminaMath-TIR

AI-MO

--- language: - en license: apache-2.0 task_categories: - text-generation pretty_name: NuminaMath TIR dataset_info: features: - name: problem dtype: string - name: solution dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 327147067 num_examples: 72441 - name: test num_bytes: 461331 num_examples: 99 download_size: 147557990 dataset_size: 327608398 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* tags: - math - aimo --- # Dataset Card for NuminaMath CoT ## Dataset Description - **Homepage:** https://projectnumina.ai - **Repository:** https://github.com/project-numina/aimo-progress-prize - **Paper:** https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf - **Leaderboard:** - **Point of Contact:** [Jia Li]([email protected]) ### Dataset Summary Tool-integrated reasoning (TIR) plays a crucial role in this competition. However, collecting and annotating such data is both costly and time-consuming. To address this, we selected approximately 70k problems from the NuminaMath-CoT dataset, focusing on those with numerical outputs, most of which are integers. We then utilized a pipeline leveraging GPT-4 to generate TORA-like reasoning paths, executing the code and producing results until the solution was complete. We filtered out solutions where the final answer did not match the reference and repeated this process three times to ensure accuracy and consistency. This iterative approach allowed us to generate high-quality TORA data efficiently. ### Licensing Information The dataset is available under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @misc{numina_math_datasets, author = {Jia LI, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Costa Huang, Kashif Rasul, Longhui Yu, Albert Jiang, Ziju Shen, Zihan Qin, Bin Dong, Li Zhou, Yann Fleureau, Guillaume Lample, and Stanislas Polu}, title = {NuminaMath TIR}, year = {2024}, publisher = {Numina}, journal = {Hugging Face repository}, howpublished = {\url{[https://huggingface.co/AI-MO/NuminaMath-TIR](https://github.com/project-numina/aimo-progress-prize/blob/main/report/numina_dataset.pdf)}} } ```

picollect/danbooru_1024

picollect

--- license: other language: - en tags: - danbooru - anime - bucket pretty_name: Danbooru 2024 Dataset size_categories: - 1M<n<10M --- # Danbooru 1024 Dataset # Danbooru 1024 数据集 A curated collection of high-quality images from Danbooru website, processed and resized to specific bucket dimensions. This dataset is for research and learning purposes only. 这是一个精选的高质量 Danbooru 网站图像集合，经过处理并调整为特定的桶尺寸。该数据集仅用于研究和学习目的。 ## Dataset Description ## 数据集描述 This dataset contains processed image resources from Danbooru website, starting from ID 3,000,000. All images are resized to specific bucket dimensions and meet minimum resolution requirements. 本数据集包含来自 Danbooru 网站的处理后图像资源，从 ID 3,000,000 开始。所有图像都调整为特定的桶尺寸，并满足最小分辨率要求。 ### Data Organization ### 数据组织 - Images are packaged into compressed files, 1000 images per archive - File naming format: `{start_id}.tar` - Example: `3000.tar` contains images with IDs from 3,000,000 to 3,000,999 - 图像打包为压缩文件，每个存档包含 1000 张图像 - 文件命名格式：`{start_id}.tar` - 示例：`3000.tar` 包含 ID 从 3,000,000 到 3,000,999 的图像 ### Technical Details ### 技术细节 - Image Format: WebP (lossless) for >1MB files, JPG (quality 92) for others - Resolution: Minimum area of 1024²×0.95 pixels - ID Range: >3,000,000 - Bucket Dimensions (width, height): - (512, 2048) - (576, 1792) - (640, 1664) - (704, 1472) - (768, 1344) - (832, 1280) - (896, 1152) - (960, 1088) - (1024, 1024) - (1088, 960) - (1152, 896) - (1280, 832) - (1344, 768) - (1472, 704) - (1664, 640) - (1792, 576) - (2048, 512) - 图像格式：>1MB 文件使用无损 WebP，其他使用质量 92 的 JPG - 分辨率：最小面积为 1024²×0.95 像素 - ID 范围：>3,000,000 - 桶尺寸（宽，高）： - (512, 2048) - (576, 1792) - (640, 1664) - (704, 1472) - (768, 1344) - (832, 1280) - (896, 1152) - (960, 1088) - (1024, 1024) - (1088, 960) - (1152, 896) - (1280, 832) - (1344, 768) - (1472, 704) - (1664, 640) - (1792, 576) - (2048, 512) ### Image Processing Details ### 图像处理细节 - All images are resized to the nearest bucket dimensions - Images with area smaller than 1024²×0.95 pixels are excluded - Files >1MB are stored as lossless WebP for optimal quality - Other files are stored as JPG (quality 92) for better color reproduction compared to WebP quality 90 - 所有图像都调整为最接近的桶尺寸 - 面积小于 1024²×0.95 像素的图像被排除 - 大于 1MB 的文件以无损 WebP 格式存储以保证最佳质量 - 其他文件以 JPG 格式（质量 92）存储，相比 WebP 质量 90 具有更好的色彩还原度 ## Usage Instructions ## 使用说明 1. Images within each archive are named by their IDs 2. Metadata can be queried from Danbooru database using corresponding IDs 1. 存档中的图像以其 ID 命名 2. 可使用相应的 ID 从 Danbooru 数据库查询元数据 ## License ## 许可证 This dataset is released under the following terms: 本数据集在以下条款下发布： 1. Academic and Research Use 学术和研究使用 - This dataset may only be used for academic research, learning, and non-commercial purposes - 本数据集仅可用于学术研究、学习和非商业目的 2. Restrictions 限制条款 - Commercial use is strictly prohibited - Redistribution or resale of the dataset is not permitted - Any derivative works must be shared under the same terms - 严格禁止商业使用 - 不允许重新分发或转售数据集 - 任何衍生作品必须在相同条款下共享 3. Attribution 署名要求 - Users must cite this dataset when used in research or publications - Any derivative works must acknowledge the original source - 在研究或出版物中使用时必须引用本数据集 - 任何衍生作品必须注明原始来源 4. Disclaimer 免责声明 - The dataset is provided "as is" without any warranty - The creators are not liable for any damages or losses arising from its use - Users are solely responsible for ensuring compliance with local laws and regulations - 数据集按"原样"提供，不提供任何保证 - 创建者不对使用过程中产生的任何损害或损失负责 - 用户需自行负责确保符合当地法律法规 5. Termination 终止条款 - This license automatically terminates if you violate any of these terms - Upon termination, you must cease all use of the dataset - 如果违反任何这些条款，本许可证将自动终止 - 终止后，您必须停止使用本数据集 By using this dataset, you agree to be bound by these terms. 使用本数据集即表示您同意受这些条款的约束。 ## Important Notes ## 重要提示 - Ensure legal compliance when using the dataset - Review relevant data usage policies and guidelines before use - Consult legal professionals if you have questions about usage rights - 使用数据集时确保遵守法律 - 使用前请查看相关数据使用政策和指南 - 如对使用权有疑问，请咨询法律专业人士 ### Contributions ### 贡献 Thanks to the Danbooru community for maintaining the source database that made this dataset possible. 感谢 Danbooru 社区维护使本数据集成为可能的源数据库。 --- **Notice:** Users must strictly comply with local laws and regulations when using this dataset. Users bear full responsibility for any issues arising from improper use. **注意：** 用户在使用本数据集时必须严格遵守当地法律法规。用户对因不当使用而产生的任何问题承担全部责任。

Avelina/smollm-corpus

Avelina

--- license: odc-by dataset_info: - config_name: default features: - name: text dtype: string configs: - config_name: default data_files: - split: train path: data*/train-* task_categories: - text-generation language: - en size_categories: - 100M<n<1B --- # SmolLM-Corpus: Now shuffled and sharded! This is a version of the SmolLM-Corpus where the 3 subsets have been interleved, shuffled and sharded as 23698 `jsonl.zst` files for easy streaming! The dataset is comprised of the `cosmopedia-v2` and `fineweb-edu-dedup` subsets from the original [SmolLM-Corpus repo](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus), with the `python-edu` subset being pulled from my [python-edu repo](https://huggingface.co/datasets/Avelina/python-edu). ## Dataset Structure The dataset is split into 24 subdirectories, with the first 23 containing 1000 shards and the 24th containing the final 698. The repository is structured as follows: ``` data00/ ├── train-00000-of-23698.jsonl.zst ├── ... └── train-00999-of-23698.jsonl.zst data01/ ├── train-01000-of-23698.jsonl.zst ├── ... └── train-01999-of-23698.jsonl.zst ... data22/ ├── train-22000-of-23698.jsonl.zst ├── ... └── train-22999-of-23698.jsonl.zst data23/ ├── train-23000-of-23698.jsonl.zst ├── ... └── train-23697-of-23698.jsonl.zst ``` In general, you can obtain the exact download URL for all shards using the following python function: ```py def get_url_from_shard( index: int ) -> str: if index >= 23_698: raise ValueError( f'Shard index must be less than 23,698 but received {index}' ) group = index // 1000 return f'https://huggingface.co/datasets/Avelina/smollm-corpus/resolve/main/data{group:02d}/train-{index:05d}-of-23698.jsonl.zst' ``` ## Generation Code Here is the code which was used to generate the shuffled shards. Note the use of non-contiguous interleaving in attempt to uniformly pull documents from across entire subsets to loosely decouple shard index from original document position. Please make sure you `pip install zstandard`!!! ```py import tqdm import datasets from datasets import load_dataset # Output directory and file format. Note that the file extension enforces zst compression is used. OUTPUT_FMT = '/YOUR/FILE/PATH/HERE/data/train-{index:05d}-of-{num_shards:05d}.jsonl.zst' # Total number of shards giving approximately 10,000 documents per shard OUTPUT_NUM_SHARDS = 23698 # Grab the three datasets ds_python = load_dataset( 'Avelina/python-edu' ) ds_cosmo = load_dataset( 'HuggingFaceTB/smollm-corpus', 'cosmopedia-v2' ) ds_edu = load_dataset( 'HuggingFaceTB/smollm-corpus', 'fineweb-edu-dedup' ) # Retain only the text columns and the train splits ds_python = ds_python.select_columns( 'text' )[ 'train' ] ds_cosmo = ds_cosmo.select_columns( 'text' )[ 'train' ] ds_edu = ds_edu.select_columns( 'text' )[ 'train' ] # Iterate over all shards with a nice progbar for index in tqdm.tqdm( range( OUTPUT_NUM_SHARDS ) ): # Get non-contiguous in-memory sub-shards for the three datasets curr_python = ds_python.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_cosmo = ds_cosmo.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_edu = ds_edu.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) # Concatenate the sub-shards curr_shard = datasets.concatenate_datasets( [ curr_python, curr_cosmo, curr_edu ] ) # Deterministically shuffle using the current shard index for reproducibility curr_shard = curr_shard.shuffle( seed=index, keep_in_memory=True ) # Dump the shards to .jsonl.zst curr_shard.to_json( OUTPUT_FMT.format( index=index, num_shards=OUTPUT_NUM_SHARDS ) ) ``` ## In-Memory Decompression Zstandard was chosen as it enables trivial in-memory decompression to minimise the storage impact of the dataset. Here is some example code which creates a python generator that yields each json line from a compressed shard stored at `file_name`, and a second function which creates a python generator that parses and yields the compressed shard. ```py import json from json import JSONDecodeError import zstandard def read_lines_zst( file_name ): # Open the file for reading in binary mode with open( file_name, 'rb' ) as file_handle: # Initialise an empty buffer buffer = '' # Create a reader for the opened file reader = zstandard.ZstdDecompressor( max_window_size=2**31 ).stream_reader( file_handle ) while True: # Read a chunk of up to 128MB chunk = reader.read( 2**27 ).decode() # If chunk is empty we've reached the end of the file and can break out if not chunk: break # Combine any prior buffer with the current chunk and split by newline lines = ( buffer + chunk ).split( '\n' ) # Yield the full lines so far for line in lines[ : -1 ]: yield line # The last 'line' is incomplete, so place in buffer for next chunk buffer = lines[ -1 ] # Always remember to close your reader! reader.close() def parse_jsonl_zst( file_name ): # Iterate over the yielded lines of the compressed shard for i, line in enumerate( read_lines_zst( file_name ) ): try: # Convert the line into a python dict and yield the text field yield json.loads( line )[ 'text' ] except ( KeyError, JSONDecodeError ): # Catch KeyError for 'text' not present in dict # Catch JSONDecodeError for malformed line print( f'JSON error @ shard={file_name}, line={i}' ) ``` Of course you *could* use HuggingFace's in-built streaming mechanics to handle things for you, but in my experience that approach is less reliable, doesn't handle `JSONDecodeError`s if there are malformed lines, can cause memory leaks, and has forced sharding behaviour when used inside a multi-worker PyTorch `DataLoader` which I've not yet found a way to disable!

asahi417/seamless-align-enA-esA.speaker-embedding.xlsr-2b

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17615486614 num_examples: 2178 download_size: 17671956372 dataset_size: 17615486614 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16927334118 num_examples: 2220 download_size: 16981705853 dataset_size: 16927334118 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13270315892 num_examples: 2091 download_size: 13316774841 dataset_size: 13270315892 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13259634937 num_examples: 2089 download_size: 13305926124 dataset_size: 13259634937 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12870979863 num_examples: 2015 download_size: 12915729898 dataset_size: 12870979863 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13380071688 num_examples: 2061 download_size: 13426181130 dataset_size: 13380071688 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13344159869 num_examples: 2100 download_size: 13390587699 dataset_size: 13344159869 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13328330644 num_examples: 2098 download_size: 13374926961 dataset_size: 13328330644 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13096062318 num_examples: 2048 download_size: 13142156831 dataset_size: 13096062318 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13034952356 num_examples: 2059 download_size: 13081006606 dataset_size: 13034952356 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13404917635 num_examples: 2105 download_size: 13451465897 dataset_size: 13404917635 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13141422631 num_examples: 2069 download_size: 13187287737 dataset_size: 13141422631 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16951209374 num_examples: 2233 download_size: 17005518613 dataset_size: 16951209374 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13040115701 num_examples: 2055 download_size: 13086087673 dataset_size: 13040115701 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12931440533 num_examples: 2051 download_size: 12976152367 dataset_size: 12931440533 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12686272722 num_examples: 2025 download_size: 12730618021 dataset_size: 12686272722 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13190310595 num_examples: 2097 download_size: 13236739071 dataset_size: 13190310595 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13285434302 num_examples: 2046 download_size: 13331320055 dataset_size: 13285434302 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13120000810 num_examples: 2083 download_size: 13166227875 dataset_size: 13120000810 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12704630141 num_examples: 2029 download_size: 12749446486 dataset_size: 12704630141 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12859255799 num_examples: 2036 download_size: 12904092383 dataset_size: 12859255799 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12860464458 num_examples: 2064 download_size: 12905429560 dataset_size: 12860464458 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13131625042 num_examples: 2062 download_size: 13177824920 dataset_size: 13131625042 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16686439189 num_examples: 2201 download_size: 16740713100 dataset_size: 16686439189 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12674395327 num_examples: 2051 download_size: 12719575500 dataset_size: 12674395327 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12650742527 num_examples: 2033 download_size: 12695314327 dataset_size: 12650742527 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12677130233 num_examples: 2043 download_size: 12722174432 dataset_size: 12677130233 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12951044389 num_examples: 2075 download_size: 12995988239 dataset_size: 12951044389 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12478574614 num_examples: 2031 download_size: 12522233390 dataset_size: 12478574614 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12737934749 num_examples: 2056 download_size: 12783009884 dataset_size: 12737934749 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12611960900 num_examples: 2027 download_size: 12656298794 dataset_size: 12611960900 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12659981403 num_examples: 2066 download_size: 12705053455 dataset_size: 12659981403 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12459304658 num_examples: 2049 download_size: 12502474622 dataset_size: 12459304658 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12607835653 num_examples: 2040 download_size: 12652679590 dataset_size: 12607835653 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16721034298 num_examples: 2222 download_size: 16775558307 dataset_size: 16721034298 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12785684138 num_examples: 2068 download_size: 12830446989 dataset_size: 12785684138 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12670698438 num_examples: 2040 download_size: 12715508711 dataset_size: 12670698438 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12809517823 num_examples: 2043 download_size: 12854435983 dataset_size: 12809517823 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12525070129 num_examples: 2026 download_size: 12569746196 dataset_size: 12525070129 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12640468818 num_examples: 2030 download_size: 12685034517 dataset_size: 12640468818 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12416679976 num_examples: 2030 download_size: 12460253194 dataset_size: 12416679976 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12060270981 num_examples: 2005 download_size: 12103559155 dataset_size: 12060270981 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12198793495 num_examples: 2043 download_size: 12242429964 dataset_size: 12198793495 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12581073257 num_examples: 2052 download_size: 12625957335 dataset_size: 12581073257 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12394780937 num_examples: 2035 download_size: 12438493328 dataset_size: 12394780937 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16816831041 num_examples: 2227 download_size: 16871222861 dataset_size: 16816831041 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12261053851 num_examples: 2005 download_size: 12304654233 dataset_size: 12261053851 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12206176867 num_examples: 2031 download_size: 12249761397 dataset_size: 12206176867 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12708681785 num_examples: 2056 download_size: 12753610542 dataset_size: 12708681785 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12366711105 num_examples: 2033 download_size: 12410442360 dataset_size: 12366711105 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12308965549 num_examples: 2028 download_size: 12352637851 dataset_size: 12308965549 - config_name: subset_145 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12284207499 num_examples: 2026 download_size: 12327846424 dataset_size: 12284207499 - config_name: subset_146 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12150428192 num_examples: 2016 download_size: 12193880909 dataset_size: 12150428192 - config_name: subset_147 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11970898169 num_examples: 2003 download_size: 12013130854 dataset_size: 11970898169 - config_name: subset_148 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12450465858 num_examples: 2022 download_size: 12493377483 dataset_size: 12450465858 - config_name: subset_149 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12022596641 num_examples: 2009 download_size: 12065732125 dataset_size: 12022596641 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16785335075 num_examples: 2236 download_size: 16839822407 dataset_size: 16785335075 - config_name: subset_150 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12104930674 num_examples: 2009 download_size: 12148469368 dataset_size: 12104930674 - config_name: subset_151 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12148398553 num_examples: 2003 download_size: 12191904417 dataset_size: 12148398553 - config_name: subset_152 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12265322777 num_examples: 2058 download_size: 12309190901 dataset_size: 12265322777 - config_name: subset_153 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12097094889 num_examples: 2032 download_size: 12141069579 dataset_size: 12097094889 - config_name: subset_154 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11954386540 num_examples: 2019 download_size: 11996860087 dataset_size: 11954386540 - config_name: subset_155 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12409993216 num_examples: 2010 download_size: 12453257259 dataset_size: 12409993216 - config_name: subset_156 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11897538098 num_examples: 1991 download_size: 11939655250 dataset_size: 11897538098 - config_name: subset_157 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11809939547 num_examples: 1980 download_size: 11852053250 dataset_size: 11809939547 - config_name: subset_158 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11975300465 num_examples: 1995 download_size: 12017653945 dataset_size: 11975300465 - config_name: subset_159 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11916840461 num_examples: 1993 download_size: 11958923329 dataset_size: 11916840461 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16674848074 num_examples: 2251 download_size: 16729606555 dataset_size: 16674848074 - config_name: subset_160 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11908485692 num_examples: 1966 download_size: 11950586090 dataset_size: 11908485692 - config_name: subset_161 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11981004468 num_examples: 2026 download_size: 12023475986 dataset_size: 11981004468 - config_name: subset_162 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12044526424 num_examples: 2005 download_size: 12088064513 dataset_size: 12044526424 - config_name: subset_163 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11557729492 num_examples: 2004 download_size: 11600363984 dataset_size: 11557729492 - config_name: subset_164 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11547632894 num_examples: 2005 download_size: 11590183152 dataset_size: 11547632894 - config_name: subset_165 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11789148049 num_examples: 1997 download_size: 11831588345 dataset_size: 11789148049 - config_name: subset_166 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11630894583 num_examples: 1979 download_size: 11673192156 dataset_size: 11630894583 - config_name: subset_167 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11569365938 num_examples: 1944 download_size: 11611215022 dataset_size: 11569365938 - config_name: subset_168 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12081411178 num_examples: 2024 download_size: 12125052871 dataset_size: 12081411178 - config_name: subset_169 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11856744061 num_examples: 1996 download_size: 11898961527 dataset_size: 11856744061 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16618546236 num_examples: 2237 download_size: 16673261997 dataset_size: 16618546236 - config_name: subset_170 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11757966530 num_examples: 1999 download_size: 11800176442 dataset_size: 11757966530 - config_name: subset_171 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11566140383 num_examples: 1965 download_size: 11608235310 dataset_size: 11566140383 - config_name: subset_172 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11632843665 num_examples: 1947 download_size: 11674886291 dataset_size: 11632843665 - config_name: subset_173 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11696838547 num_examples: 1978 download_size: 11738400669 dataset_size: 11696838547 - config_name: subset_174 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11796900755 num_examples: 1992 download_size: 11839031804 dataset_size: 11796900755 - config_name: subset_175 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11522497802 num_examples: 1997 download_size: 11564866792 dataset_size: 11522497802 - config_name: subset_176 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11494892805 num_examples: 1946 download_size: 11535501682 dataset_size: 11494892805 - config_name: subset_177 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11686128349 num_examples: 1994 download_size: 11728436974 dataset_size: 11686128349 - config_name: subset_178 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11669254181 num_examples: 1992 download_size: 11711755317 dataset_size: 11669254181 - config_name: subset_179 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11651052491 num_examples: 2013 download_size: 11693353876 dataset_size: 11651052491 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16254521068 num_examples: 2195 download_size: 16307512664 dataset_size: 16254521068 - config_name: subset_180 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11366092414 num_examples: 1932 download_size: 11406917340 dataset_size: 11366092414 - config_name: subset_181 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11793512948 num_examples: 2002 download_size: 11835985714 dataset_size: 11793512948 - config_name: subset_182 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11176721435 num_examples: 1947 download_size: 11217656997 dataset_size: 11176721435 - config_name: subset_183 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11504599850 num_examples: 1973 download_size: 11546621630 dataset_size: 11504599850 - config_name: subset_184 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11340991023 num_examples: 1959 download_size: 11381767318 dataset_size: 11340991023 - config_name: subset_185 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10958038927 num_examples: 1904 download_size: 10997093007 dataset_size: 10958038927 - config_name: subset_186 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11236510649 num_examples: 1947 download_size: 11277036944 dataset_size: 11236510649 - config_name: subset_187 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11243650468 num_examples: 1964 download_size: 11284454904 dataset_size: 11243650468 - config_name: subset_188 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11631939495 num_examples: 1978 download_size: 11674186442 dataset_size: 11631939495 - config_name: subset_189 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11430091702 num_examples: 2017 download_size: 11470976839 dataset_size: 11430091702 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16339477172 num_examples: 2217 download_size: 16392637784 dataset_size: 16339477172 - config_name: subset_190 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11398504836 num_examples: 1948 download_size: 11439304594 dataset_size: 11398504836 - config_name: subset_191 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10983850878 num_examples: 1921 download_size: 11023019749 dataset_size: 10983850878 - config_name: subset_192 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11392234972 num_examples: 1951 download_size: 11432586306 dataset_size: 11392234972 - config_name: subset_193 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11271488922 num_examples: 1956 download_size: 11312405664 dataset_size: 11271488922 - config_name: subset_194 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11357335026 num_examples: 1961 download_size: 11398377938 dataset_size: 11357335026 - config_name: subset_195 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11086034665 num_examples: 1945 download_size: 11126998403 dataset_size: 11086034665 - config_name: subset_196 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11043203344 num_examples: 1936 download_size: 11084004919 dataset_size: 11043203344 - config_name: subset_197 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10949319896 num_examples: 1932 download_size: 10988727473 dataset_size: 10949319896 - config_name: subset_198 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11139775714 num_examples: 1934 download_size: 11180699957 dataset_size: 11139775714 - config_name: subset_199 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11243712969 num_examples: 1977 download_size: 11284563965 dataset_size: 11243712969 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17867926870 num_examples: 2245 download_size: 17924763168 dataset_size: 17867926870 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15329766438 num_examples: 2093 download_size: 15379836725 dataset_size: 15329766438 - config_name: subset_200 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11202233370 num_examples: 1960 download_size: 11242825203 dataset_size: 11202233370 - config_name: subset_201 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11088324458 num_examples: 1944 download_size: 11129210075 dataset_size: 11088324458 - config_name: subset_202 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11276024599 num_examples: 1982 download_size: 11317146502 dataset_size: 11276024599 - config_name: subset_203 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10852830882 num_examples: 1919 download_size: 10891763738 dataset_size: 10852830882 - config_name: subset_204 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10819852765 num_examples: 1939 download_size: 10859654400 dataset_size: 10819852765 - config_name: subset_205 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11166848309 num_examples: 1957 download_size: 11207893657 dataset_size: 11166848309 - config_name: subset_206 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10885465898 num_examples: 1932 download_size: 10925154959 dataset_size: 10885465898 - config_name: subset_207 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10610213231 num_examples: 1882 download_size: 10649574288 dataset_size: 10610213231 - config_name: subset_208 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10810223800 num_examples: 1928 download_size: 10849596885 dataset_size: 10810223800 - config_name: subset_209 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10739546598 num_examples: 1931 download_size: 10779380292 dataset_size: 10739546598 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15119185509 num_examples: 2083 download_size: 15168901402 dataset_size: 15119185509 - config_name: subset_210 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10674367098 num_examples: 1884 download_size: 10713595910 dataset_size: 10674367098 - config_name: subset_211 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10671831916 num_examples: 1891 download_size: 10711269789 dataset_size: 10671831916 - config_name: subset_212 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10714648825 num_examples: 1911 download_size: 10754277168 dataset_size: 10714648825 - config_name: subset_213 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10792102434 num_examples: 1897 download_size: 10831439770 dataset_size: 10792102434 - config_name: subset_214 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10736126167 num_examples: 1918 download_size: 10775692263 dataset_size: 10736126167 - config_name: subset_215 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10468090665 num_examples: 1891 download_size: 10506413098 dataset_size: 10468090665 - config_name: subset_216 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10328309433 num_examples: 1871 download_size: 10366449044 dataset_size: 10328309433 - config_name: subset_217 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10364340655 num_examples: 1883 download_size: 10402491036 dataset_size: 10364340655 - config_name: subset_218 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10772691113 num_examples: 1878 download_size: 10812133060 dataset_size: 10772691113 - config_name: subset_219 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10311356207 num_examples: 1843 download_size: 10348785373 dataset_size: 10311356207 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14581297681 num_examples: 1987 download_size: 14629521379 dataset_size: 14581297681 - config_name: subset_220 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10523637560 num_examples: 1882 download_size: 10563027688 dataset_size: 10523637560 - config_name: subset_221 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10565854425 num_examples: 1894 download_size: 10605243718 dataset_size: 10565854425 - config_name: subset_222 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10547035702 num_examples: 1886 download_size: 10586386817 dataset_size: 10547035702 - config_name: subset_223 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10566185502 num_examples: 1902 download_size: 10605790532 dataset_size: 10566185502 - config_name: subset_224 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10686340635 num_examples: 1907 download_size: 10725415925 dataset_size: 10686340635 - config_name: subset_225 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10407100675 num_examples: 1865 download_size: 10445116148 dataset_size: 10407100675 - config_name: subset_226 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10247852666 num_examples: 1900 download_size: 10286330263 dataset_size: 10247852666 - config_name: subset_227 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10600702309 num_examples: 1905 download_size: 10640293635 dataset_size: 10600702309 - config_name: subset_228 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10410552726 num_examples: 1889 download_size: 10448706879 dataset_size: 10410552726 - config_name: subset_229 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10227043199 num_examples: 1886 download_size: 10265311634 dataset_size: 10227043199 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14707964791 num_examples: 2037 download_size: 14756622646 dataset_size: 14707964791 - config_name: subset_230 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10977312976 num_examples: 1935 download_size: 11015836294 dataset_size: 10977312976 - config_name: subset_231 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10354006940 num_examples: 1898 download_size: 10392292630 dataset_size: 10354006940 - config_name: subset_232 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10359630853 num_examples: 1889 download_size: 10397910351 dataset_size: 10359630853 - config_name: subset_233 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10318214003 num_examples: 1888 download_size: 10356479989 dataset_size: 10318214003 - config_name: subset_234 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10153869118 num_examples: 1894 download_size: 10192086672 dataset_size: 10153869118 - config_name: subset_235 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10451531268 num_examples: 1887 download_size: 10489548838 dataset_size: 10451531268 - config_name: subset_236 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10423323169 num_examples: 1885 download_size: 10461230101 dataset_size: 10423323169 - config_name: subset_237 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10111542830 num_examples: 1860 download_size: 10149678003 dataset_size: 10111542830 - config_name: subset_238 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10209968615 num_examples: 1877 download_size: 10248106680 dataset_size: 10209968615 - config_name: subset_239 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10335208989 num_examples: 1863 download_size: 10373126755 dataset_size: 10335208989 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15110768889 num_examples: 2050 download_size: 15160503523 dataset_size: 15110768889 - config_name: subset_240 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10121403869 num_examples: 1890 download_size: 10159836061 dataset_size: 10121403869 - config_name: subset_241 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10186760412 num_examples: 1846 download_size: 10224695949 dataset_size: 10186760412 - config_name: subset_242 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10325305357 num_examples: 1876 download_size: 10363420683 dataset_size: 10325305357 - config_name: subset_243 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9905932594 num_examples: 1838 download_size: 9942639569 dataset_size: 9905932594 - config_name: subset_244 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10091589671 num_examples: 1886 download_size: 10130048735 dataset_size: 10091589671 - config_name: subset_245 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10253380616 num_examples: 1845 download_size: 10291311175 dataset_size: 10253380616 - config_name: subset_246 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9776749280 num_examples: 1839 download_size: 9813691334 dataset_size: 9776749280 - config_name: subset_247 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10156286081 num_examples: 1851 download_size: 10194287310 dataset_size: 10156286081 - config_name: subset_248 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10293648296 num_examples: 1889 download_size: 10332006484 dataset_size: 10293648296 - config_name: subset_249 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10077132419 num_examples: 1842 download_size: 10115148550 dataset_size: 10077132419 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14939407431 num_examples: 2043 download_size: 14987934926 dataset_size: 14939407431 - config_name: subset_250 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9859274992 num_examples: 1834 download_size: 9896107919 dataset_size: 9859274992 - config_name: subset_251 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9932351426 num_examples: 1854 download_size: 9969187608 dataset_size: 9932351426 - config_name: subset_252 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10142478129 num_examples: 1854 download_size: 10180659893 dataset_size: 10142478129 - config_name: subset_253 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10123622721 num_examples: 1867 download_size: 10161912632 dataset_size: 10123622721 - config_name: subset_254 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10010038438 num_examples: 1875 download_size: 10048246100 dataset_size: 10010038438 - config_name: subset_255 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9677910385 num_examples: 1844 download_size: 9714855044 dataset_size: 9677910385 - config_name: subset_256 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10274666423 num_examples: 1860 download_size: 10312795912 dataset_size: 10274666423 - config_name: subset_257 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9894060407 num_examples: 1833 download_size: 9930923035 dataset_size: 9894060407 - config_name: subset_258 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10002283709 num_examples: 1856 download_size: 10040147359 dataset_size: 10002283709 - config_name: subset_259 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9954421477 num_examples: 1873 download_size: 9991605810 dataset_size: 9954421477 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14688110120 num_examples: 2046 download_size: 14736907487 dataset_size: 14688110120 - config_name: subset_260 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9251403580 num_examples: 1766 download_size: 9286487592 dataset_size: 9251403580 - config_name: subset_261 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8906186422 num_examples: 1695 download_size: 8939749379 dataset_size: 8906186422 - config_name: subset_262 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9005322912 num_examples: 1665 download_size: 9039903011 dataset_size: 9005322912 - config_name: subset_263 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8957935304 num_examples: 1660 download_size: 8991043579 dataset_size: 8957935304 - config_name: subset_264 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9005781922 num_examples: 1640 download_size: 9040003299 dataset_size: 9005781922 - config_name: subset_265 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8885453225 num_examples: 1674 download_size: 8918493432 dataset_size: 8885453225 - config_name: subset_266 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9008549939 num_examples: 1662 download_size: 9042942529 dataset_size: 9008549939 - config_name: subset_267 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9343968850 num_examples: 1718 download_size: 9378652964 dataset_size: 9343968850 - config_name: subset_268 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9630757415 num_examples: 1796 download_size: 9667100998 dataset_size: 9630757415 - config_name: subset_269 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9982374644 num_examples: 1858 download_size: 10019389762 dataset_size: 9982374644 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14706735358 num_examples: 2036 download_size: 14755314793 dataset_size: 14706735358 - config_name: subset_270 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9482266334 num_examples: 1823 download_size: 9517999637 dataset_size: 9482266334 - config_name: subset_271 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9602528097 num_examples: 1816 download_size: 9639460882 dataset_size: 9602528097 - config_name: subset_272 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9849753853 num_examples: 1826 download_size: 9886412516 dataset_size: 9849753853 - config_name: subset_273 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9658015564 num_examples: 1832 download_size: 9694957017 dataset_size: 9658015564 - config_name: subset_274 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9549175962 num_examples: 1791 download_size: 9585620341 dataset_size: 9549175962 - config_name: subset_275 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9540749598 num_examples: 1827 download_size: 9577339695 dataset_size: 9540749598 - config_name: subset_276 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9447286696 num_examples: 1798 download_size: 9482749217 dataset_size: 9447286696 - config_name: subset_277 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9649155191 num_examples: 1824 download_size: 9685881332 dataset_size: 9649155191 - config_name: subset_278 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9778025788 num_examples: 1852 download_size: 9815037575 dataset_size: 9778025788 - config_name: subset_279 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9773965831 num_examples: 1817 download_size: 9810744560 dataset_size: 9773965831 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14919139004 num_examples: 2067 download_size: 14968257960 dataset_size: 14919139004 - config_name: subset_280 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9394162223 num_examples: 1831 download_size: 9429593445 dataset_size: 9394162223 - config_name: subset_281 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9562033469 num_examples: 1818 download_size: 9598793999 dataset_size: 9562033469 - config_name: subset_282 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9625372743 num_examples: 1818 download_size: 9662150366 dataset_size: 9625372743 - config_name: subset_283 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9630374197 num_examples: 1808 download_size: 9667159020 dataset_size: 9630374197 - config_name: subset_284 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9070359285 num_examples: 1747 download_size: 9105502122 dataset_size: 9070359285 - config_name: subset_285 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9505440183 num_examples: 1809 download_size: 9542237457 dataset_size: 9505440183 - config_name: subset_286 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9616111622 num_examples: 1795 download_size: 9652676512 dataset_size: 9616111622 - config_name: subset_287 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8256889317 num_examples: 1612 download_size: 8288680929 dataset_size: 8256889317 - config_name: subset_288 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6640007028 num_examples: 1335 download_size: 6666439022 dataset_size: 6640007028 - config_name: subset_289 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9672423557 num_examples: 1839 download_size: 9709457896 dataset_size: 9672423557 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15234832048 num_examples: 2111 download_size: 15285154066 dataset_size: 15234832048 - config_name: subset_290 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9458067491 num_examples: 1800 download_size: 9493104286 dataset_size: 9458067491 - config_name: subset_291 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9370100008 num_examples: 1787 download_size: 9405424811 dataset_size: 9370100008 - config_name: subset_292 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9423575157 num_examples: 1813 download_size: 9459072789 dataset_size: 9423575157 - config_name: subset_293 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9596121647 num_examples: 1841 download_size: 9633046444 dataset_size: 9596121647 - config_name: subset_294 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9509336675 num_examples: 1818 download_size: 9546218752 dataset_size: 9509336675 - config_name: subset_295 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9503628008 num_examples: 1825 download_size: 9540439521 dataset_size: 9503628008 - config_name: subset_296 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9499785375 num_examples: 1817 download_size: 9535465416 dataset_size: 9499785375 - config_name: subset_297 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9486624475 num_examples: 1840 download_size: 9522420706 dataset_size: 9486624475 - config_name: subset_298 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9611963960 num_examples: 1816 download_size: 9648063415 dataset_size: 9611963960 - config_name: subset_299 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9165943098 num_examples: 1778 download_size: 9201250523 dataset_size: 9165943098 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17564492490 num_examples: 2234 download_size: 17621332507 dataset_size: 17564492490 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15691430060 num_examples: 2197 download_size: 15743673970 dataset_size: 15691430060 - config_name: subset_300 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9609773492 num_examples: 1809 download_size: 9646496750 dataset_size: 9609773492 - config_name: subset_301 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9508175993 num_examples: 1814 download_size: 9544852618 dataset_size: 9508175993 - config_name: subset_302 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9152773379 num_examples: 1786 download_size: 9188137438 dataset_size: 9152773379 - config_name: subset_303 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9479298193 num_examples: 1797 download_size: 9514405163 dataset_size: 9479298193 - config_name: subset_304 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9388356289 num_examples: 1776 download_size: 9423438274 dataset_size: 9388356289 - config_name: subset_305 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9439211353 num_examples: 1805 download_size: 9474779869 dataset_size: 9439211353 - config_name: subset_306 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9341703478 num_examples: 1830 download_size: 9377307637 dataset_size: 9341703478 - config_name: subset_307 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9556548323 num_examples: 1833 download_size: 9593234545 dataset_size: 9556548323 - config_name: subset_308 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9351488776 num_examples: 1780 download_size: 9386455164 dataset_size: 9351488776 - config_name: subset_309 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9546867649 num_examples: 1847 download_size: 9583895956 dataset_size: 9546867649 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15655576113 num_examples: 2192 download_size: 15707667505 dataset_size: 15655576113 - config_name: subset_310 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9360988039 num_examples: 1802 download_size: 9395714050 dataset_size: 9360988039 - config_name: subset_311 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9312716340 num_examples: 1792 download_size: 9348081921 dataset_size: 9312716340 - config_name: subset_312 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9052758958 num_examples: 1793 download_size: 9088326883 dataset_size: 9052758958 - config_name: subset_313 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9094529036 num_examples: 1791 download_size: 9130202452 dataset_size: 9094529036 - config_name: subset_314 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8962637266 num_examples: 1747 download_size: 8996516727 dataset_size: 8962637266 - config_name: subset_315 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9550414333 num_examples: 1806 download_size: 9587049840 dataset_size: 9550414333 - config_name: subset_316 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9329875364 num_examples: 1800 download_size: 9365540807 dataset_size: 9329875364 - config_name: subset_317 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9339795411 num_examples: 1800 download_size: 9375304413 dataset_size: 9339795411 - config_name: subset_318 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9231095503 num_examples: 1775 download_size: 9266214850 dataset_size: 9231095503 - config_name: subset_319 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9434425340 num_examples: 1818 download_size: 9469524793 dataset_size: 9434425340 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15921659855 num_examples: 2219 download_size: 15974195919 dataset_size: 15921659855 - config_name: subset_320 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9469785770 num_examples: 1802 download_size: 9505117938 dataset_size: 9469785770 - config_name: subset_321 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9650736453 num_examples: 1804 download_size: 9687032265 dataset_size: 9650736453 - config_name: subset_322 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9212596034 num_examples: 1819 download_size: 9248412374 dataset_size: 9212596034 - config_name: subset_323 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9108779905 num_examples: 1755 download_size: 9144169306 dataset_size: 9108779905 - config_name: subset_324 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9044220745 num_examples: 1777 download_size: 9079400568 dataset_size: 9044220745 - config_name: subset_325 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9395796601 num_examples: 1803 download_size: 9431300325 dataset_size: 9395796601 - config_name: subset_326 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9064906889 num_examples: 1787 download_size: 9100339782 dataset_size: 9064906889 - config_name: subset_327 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9281203011 num_examples: 1777 download_size: 9316568721 dataset_size: 9281203011 - config_name: subset_328 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9210702320 num_examples: 1777 download_size: 9245987863 dataset_size: 9210702320 - config_name: subset_329 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9223773915 num_examples: 1790 download_size: 9259307876 dataset_size: 9223773915 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15611416602 num_examples: 2198 download_size: 15663791470 dataset_size: 15611416602 - config_name: subset_330 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9296502175 num_examples: 1781 download_size: 9331855519 dataset_size: 9296502175 - config_name: subset_331 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9148377912 num_examples: 1783 download_size: 9183768848 dataset_size: 9148377912 - config_name: subset_332 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9230881649 num_examples: 1791 download_size: 9266359032 dataset_size: 9230881649 - config_name: subset_333 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9487368178 num_examples: 1819 download_size: 9522947865 dataset_size: 9487368178 - config_name: subset_334 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9083416926 num_examples: 1778 download_size: 9118375759 dataset_size: 9083416926 - config_name: subset_335 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9139849081 num_examples: 1788 download_size: 9175346746 dataset_size: 9139849081 - config_name: subset_336 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9275532884 num_examples: 1785 download_size: 9311143350 dataset_size: 9275532884 - config_name: subset_337 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9114459631 num_examples: 1770 download_size: 9149875698 dataset_size: 9114459631 - config_name: subset_338 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9193061609 num_examples: 1798 download_size: 9228634184 dataset_size: 9193061609 - config_name: subset_339 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9061657947 num_examples: 1804 download_size: 9097148076 dataset_size: 9061657947 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15432387170 num_examples: 2199 download_size: 15484263220 dataset_size: 15432387170 - config_name: subset_340 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9179922247 num_examples: 1802 download_size: 9215341652 dataset_size: 9179922247 - config_name: subset_341 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8936121108 num_examples: 1763 download_size: 8970077579 dataset_size: 8936121108 - config_name: subset_342 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9089440940 num_examples: 1775 download_size: 9124985463 dataset_size: 9089440940 - config_name: subset_343 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9056805540 num_examples: 1757 download_size: 9092015615 dataset_size: 9056805540 - config_name: subset_344 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9131233374 num_examples: 1765 download_size: 9166469291 dataset_size: 9131233374 - config_name: subset_345 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8840205902 num_examples: 1720 download_size: 8874028549 dataset_size: 8840205902 - config_name: subset_346 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8728873809 num_examples: 1737 download_size: 8762891017 dataset_size: 8728873809 - config_name: subset_347 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8931364937 num_examples: 1766 download_size: 8964815188 dataset_size: 8931364937 - config_name: subset_348 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9024910784 num_examples: 1776 download_size: 9060436900 dataset_size: 9024910784 - config_name: subset_349 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8991465479 num_examples: 1720 download_size: 9025201371 dataset_size: 8991465479 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14996383276 num_examples: 2125 download_size: 15046409293 dataset_size: 14996383276 - config_name: subset_350 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8971469012 num_examples: 1782 download_size: 9005732119 dataset_size: 8971469012 - config_name: subset_351 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8800425959 num_examples: 1722 download_size: 8834285273 dataset_size: 8800425959 - config_name: subset_352 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8836136950 num_examples: 1764 download_size: 8870360600 dataset_size: 8836136950 - config_name: subset_353 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9031718626 num_examples: 1774 download_size: 9067053272 dataset_size: 9031718626 - config_name: subset_354 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8797219039 num_examples: 1783 download_size: 8831487024 dataset_size: 8797219039 - config_name: subset_355 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8840747107 num_examples: 1761 download_size: 8874859913 dataset_size: 8840747107 - config_name: subset_356 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8577410322 num_examples: 1686 download_size: 8610812449 dataset_size: 8577410322 - config_name: subset_357 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9074273275 num_examples: 1782 download_size: 9109695863 dataset_size: 9074273275 - config_name: subset_358 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9227959994 num_examples: 1770 download_size: 9263216847 dataset_size: 9227959994 - config_name: subset_359 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8776143678 num_examples: 1711 download_size: 8809888634 dataset_size: 8776143678 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15044709570 num_examples: 2145 download_size: 15095548862 dataset_size: 15044709570 - config_name: subset_360 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8820259705 num_examples: 1738 download_size: 8854303067 dataset_size: 8820259705 - config_name: subset_361 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9145072997 num_examples: 1774 download_size: 9180586755 dataset_size: 9145072997 - config_name: subset_362 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8462258469 num_examples: 1693 download_size: 8494690158 dataset_size: 8462258469 - config_name: subset_363 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8581569826 num_examples: 1716 download_size: 8615493990 dataset_size: 8581569826 - config_name: subset_364 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9011936285 num_examples: 1728 download_size: 9047013145 dataset_size: 9011936285 - config_name: subset_365 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8881614976 num_examples: 1720 download_size: 8915230397 dataset_size: 8881614976 - config_name: subset_366 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8845062437 num_examples: 1723 download_size: 8878662664 dataset_size: 8845062437 - config_name: subset_367 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8828104700 num_examples: 1733 download_size: 8862105074 dataset_size: 8828104700 - config_name: subset_368 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8502283986 num_examples: 1688 download_size: 8535977291 dataset_size: 8502283986 - config_name: subset_369 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8959660863 num_examples: 1714 download_size: 8993371357 dataset_size: 8959660863 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15098383698 num_examples: 2162 download_size: 15149327432 dataset_size: 15098383698 - config_name: subset_370 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8574185282 num_examples: 1713 download_size: 8608126100 dataset_size: 8574185282 - config_name: subset_371 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9020735695 num_examples: 1743 download_size: 9055944350 dataset_size: 9020735695 - config_name: subset_372 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8723449670 num_examples: 1746 download_size: 8756102489 dataset_size: 8723449670 - config_name: subset_373 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8747375432 num_examples: 1719 download_size: 8780806765 dataset_size: 8747375432 - config_name: subset_374 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8364764553 num_examples: 1701 download_size: 8396204390 dataset_size: 8364764553 - config_name: subset_375 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8595821349 num_examples: 1688 download_size: 8629313871 dataset_size: 8595821349 - config_name: subset_376 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8522125538 num_examples: 1705 download_size: 8555855028 dataset_size: 8522125538 - config_name: subset_377 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8800733888 num_examples: 1729 download_size: 8834228490 dataset_size: 8800733888 - config_name: subset_378 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8670894909 num_examples: 1699 download_size: 8704612631 dataset_size: 8670894909 - config_name: subset_379 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8630111423 num_examples: 1738 download_size: 8664239699 dataset_size: 8630111423 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14876990171 num_examples: 2136 download_size: 14927068671 dataset_size: 14876990171 - config_name: subset_380 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8494123212 num_examples: 1683 download_size: 8526418095 dataset_size: 8494123212 - config_name: subset_381 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8744503288 num_examples: 1740 download_size: 8778567058 dataset_size: 8744503288 - config_name: subset_382 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8360475176 num_examples: 1681 download_size: 8392795152 dataset_size: 8360475176 - config_name: subset_383 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8789107737 num_examples: 1726 download_size: 8823019733 dataset_size: 8789107737 - config_name: subset_384 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8698941573 num_examples: 1700 download_size: 8731786773 dataset_size: 8698941573 - config_name: subset_385 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8543623069 num_examples: 1677 download_size: 8576413868 dataset_size: 8543623069 - config_name: subset_386 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8492516757 num_examples: 1677 download_size: 8524829527 dataset_size: 8492516757 - config_name: subset_387 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8611028245 num_examples: 1691 download_size: 8644582313 dataset_size: 8611028245 - config_name: subset_388 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8312473366 num_examples: 1683 download_size: 8344751119 dataset_size: 8312473366 - config_name: subset_389 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8357627397 num_examples: 1717 download_size: 8390511072 dataset_size: 8357627397 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15044435370 num_examples: 2174 download_size: 15095948164 dataset_size: 15044435370 - config_name: subset_390 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8748406479 num_examples: 1736 download_size: 8782272242 dataset_size: 8748406479 - config_name: subset_391 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8985872554 num_examples: 1733 download_size: 9019426916 dataset_size: 8985872554 - config_name: subset_392 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8296682807 num_examples: 1683 download_size: 8329215790 dataset_size: 8296682807 - config_name: subset_393 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8678142035 num_examples: 1712 download_size: 8712037235 dataset_size: 8678142035 - config_name: subset_394 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8608830930 num_examples: 1695 download_size: 8642217218 dataset_size: 8608830930 - config_name: subset_395 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8580225855 num_examples: 1725 download_size: 8614251890 dataset_size: 8580225855 - config_name: subset_396 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8579462633 num_examples: 1694 download_size: 8613251526 dataset_size: 8579462633 - config_name: subset_397 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8430739696 num_examples: 1705 download_size: 8463357738 dataset_size: 8430739696 - config_name: subset_398 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8713963571 num_examples: 1697 download_size: 8747816742 dataset_size: 8713963571 - config_name: subset_399 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8704077389 num_examples: 1735 download_size: 8738064326 dataset_size: 8704077389 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17686238305 num_examples: 2240 download_size: 17743084363 dataset_size: 17686238305 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14950642814 num_examples: 2154 download_size: 15000900506 dataset_size: 14950642814 - config_name: subset_400 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8550939961 num_examples: 1698 download_size: 8584298446 dataset_size: 8550939961 - config_name: subset_401 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8585540313 num_examples: 1690 download_size: 8619085637 dataset_size: 8585540313 - config_name: subset_402 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8798509365 num_examples: 1776 download_size: 8832157307 dataset_size: 8798509365 - config_name: subset_403 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8682989481 num_examples: 1698 download_size: 8716618540 dataset_size: 8682989481 - config_name: subset_404 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8993741789 num_examples: 1743 download_size: 9027647720 dataset_size: 8993741789 - config_name: subset_405 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8228817018 num_examples: 1674 download_size: 8261288381 dataset_size: 8228817018 - config_name: subset_406 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8404929447 num_examples: 1709 download_size: 8437467645 dataset_size: 8404929447 - config_name: subset_407 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8863105467 num_examples: 1735 download_size: 8896978741 dataset_size: 8863105467 - config_name: subset_408 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8514664885 num_examples: 1712 download_size: 8548503653 dataset_size: 8514664885 - config_name: subset_409 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8840066744 num_examples: 1710 download_size: 8873764622 dataset_size: 8840066744 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14925154015 num_examples: 2142 download_size: 14974821031 dataset_size: 14925154015 - config_name: subset_410 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8781033463 num_examples: 1745 download_size: 8815013438 dataset_size: 8781033463 - config_name: subset_411 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8530771583 num_examples: 1725 download_size: 8562781837 dataset_size: 8530771583 - config_name: subset_412 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8807643953 num_examples: 1755 download_size: 8841689470 dataset_size: 8807643953 - config_name: subset_413 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8562934741 num_examples: 1699 download_size: 8596738808 dataset_size: 8562934741 - config_name: subset_414 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8577346796 num_examples: 1755 download_size: 8610989603 dataset_size: 8577346796 - config_name: subset_415 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8529392107 num_examples: 1675 download_size: 8562915561 dataset_size: 8529392107 - config_name: subset_416 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8445269930 num_examples: 1703 download_size: 8476865155 dataset_size: 8445269930 - config_name: subset_417 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8619958787 num_examples: 1712 download_size: 8653700824 dataset_size: 8619958787 - config_name: subset_418 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8289958485 num_examples: 1673 download_size: 8322319634 dataset_size: 8289958485 - config_name: subset_419 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8744172660 num_examples: 1737 download_size: 8778194526 dataset_size: 8744172660 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14788933635 num_examples: 2161 download_size: 14839309849 dataset_size: 14788933635 - config_name: subset_420 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8564886346 num_examples: 1698 download_size: 8598617429 dataset_size: 8564886346 - config_name: subset_421 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8869185294 num_examples: 1757 download_size: 8903265406 dataset_size: 8869185294 - config_name: subset_422 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9034329328 num_examples: 1751 download_size: 9069380368 dataset_size: 9034329328 - config_name: subset_423 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8819599057 num_examples: 1740 download_size: 8853605288 dataset_size: 8819599057 - config_name: subset_424 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8915111476 num_examples: 1744 download_size: 8949141122 dataset_size: 8915111476 - config_name: subset_425 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8818699104 num_examples: 1729 download_size: 8852508680 dataset_size: 8818699104 - config_name: subset_426 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8568761227 num_examples: 1724 download_size: 8602654585 dataset_size: 8568761227 - config_name: subset_427 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8688732426 num_examples: 1735 download_size: 8722735777 dataset_size: 8688732426 - config_name: subset_428 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8369697429 num_examples: 1698 download_size: 8402208849 dataset_size: 8369697429 - config_name: subset_429 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8646092223 num_examples: 1714 download_size: 8679967503 dataset_size: 8646092223 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15170697432 num_examples: 2157 download_size: 15221698675 dataset_size: 15170697432 - config_name: subset_430 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8525584317 num_examples: 1718 download_size: 8559600637 dataset_size: 8525584317 - config_name: subset_431 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8858450126 num_examples: 1750 download_size: 8892566030 dataset_size: 8858450126 - config_name: subset_432 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8849913220 num_examples: 1749 download_size: 8883882148 dataset_size: 8849913220 - config_name: subset_433 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8613746890 num_examples: 1767 download_size: 8648026859 dataset_size: 8613746890 - config_name: subset_434 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8645653840 num_examples: 1709 download_size: 8679363337 dataset_size: 8645653840 - config_name: subset_435 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8560099829 num_examples: 1705 download_size: 8594037043 dataset_size: 8560099829 - config_name: subset_436 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8832125948 num_examples: 1764 download_size: 8866309735 dataset_size: 8832125948 - config_name: subset_437 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8946255398 num_examples: 1752 download_size: 8980417376 dataset_size: 8946255398 - config_name: subset_438 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8591328909 num_examples: 1721 download_size: 8625199762 dataset_size: 8591328909 - config_name: subset_439 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8702440609 num_examples: 1734 download_size: 8736551929 dataset_size: 8702440609 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14640698517 num_examples: 2124 download_size: 14690783226 dataset_size: 14640698517 - config_name: subset_440 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8819446067 num_examples: 1749 download_size: 8853463814 dataset_size: 8819446067 - config_name: subset_441 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8689763275 num_examples: 1749 download_size: 8723897261 dataset_size: 8689763275 - config_name: subset_442 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8950550291 num_examples: 1746 download_size: 8984372825 dataset_size: 8950550291 - config_name: subset_443 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8711707457 num_examples: 1733 download_size: 8745701357 dataset_size: 8711707457 - config_name: subset_444 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8866910369 num_examples: 1752 download_size: 8901070769 dataset_size: 8866910369 - config_name: subset_445 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8840346071 num_examples: 1743 download_size: 8874378560 dataset_size: 8840346071 - config_name: subset_446 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8547114263 num_examples: 1710 download_size: 8581022971 dataset_size: 8547114263 - config_name: subset_447 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8630549726 num_examples: 1742 download_size: 8664416874 dataset_size: 8630549726 - config_name: subset_448 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8590967840 num_examples: 1722 download_size: 8624834801 dataset_size: 8590967840 - config_name: subset_449 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8838711861 num_examples: 1773 download_size: 8872898762 dataset_size: 8838711861 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14888049488 num_examples: 2161 download_size: 14938566293 dataset_size: 14888049488 - config_name: subset_450 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8853978164 num_examples: 1751 download_size: 8888120395 dataset_size: 8853978164 - config_name: subset_451 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8539713353 num_examples: 1695 download_size: 8573419201 dataset_size: 8539713353 - config_name: subset_452 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8394169575 num_examples: 1681 download_size: 8426611041 dataset_size: 8394169575 - config_name: subset_453 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8439007345 num_examples: 1701 download_size: 8471603668 dataset_size: 8439007345 - config_name: subset_454 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8531852056 num_examples: 1688 download_size: 8564919565 dataset_size: 8531852056 - config_name: subset_455 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8368812772 num_examples: 1686 download_size: 8401247371 dataset_size: 8368812772 - config_name: subset_456 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8651295246 num_examples: 1726 download_size: 8685379201 dataset_size: 8651295246 - config_name: subset_457 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8447069870 num_examples: 1725 download_size: 8479977920 dataset_size: 8447069870 - config_name: subset_458 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8572604338 num_examples: 1738 download_size: 8606819062 dataset_size: 8572604338 - config_name: subset_459 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8790645711 num_examples: 1740 download_size: 8824783568 dataset_size: 8790645711 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14931332728 num_examples: 2152 download_size: 14981163156 dataset_size: 14931332728 - config_name: subset_460 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8664419556 num_examples: 1726 download_size: 8698428184 dataset_size: 8664419556 - config_name: subset_461 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8595501889 num_examples: 1728 download_size: 8629353061 dataset_size: 8595501889 - config_name: subset_462 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8255221647 num_examples: 1704 download_size: 8287903828 dataset_size: 8255221647 - config_name: subset_463 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8850459383 num_examples: 1757 download_size: 8883064365 dataset_size: 8850459383 - config_name: subset_464 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8641729323 num_examples: 1734 download_size: 8675162555 dataset_size: 8641729323 - config_name: subset_465 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8480408848 num_examples: 1703 download_size: 8512339282 dataset_size: 8480408848 - config_name: subset_466 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8463711538 num_examples: 1703 download_size: 8494986677 dataset_size: 8463711538 - config_name: subset_467 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8820781508 num_examples: 1729 download_size: 8854667990 dataset_size: 8820781508 - config_name: subset_468 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8297529694 num_examples: 1703 download_size: 8329518158 dataset_size: 8297529694 - config_name: subset_469 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8335255754 num_examples: 1674 download_size: 8367587978 dataset_size: 8335255754 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14733661735 num_examples: 2150 download_size: 14784007748 dataset_size: 14733661735 - config_name: subset_470 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8677813347 num_examples: 1733 download_size: 8711504703 dataset_size: 8677813347 - config_name: subset_471 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8025824740 num_examples: 1625 download_size: 8057638520 dataset_size: 8025824740 - config_name: subset_472 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8412479577 num_examples: 1669 download_size: 8444758288 dataset_size: 8412479577 - config_name: subset_473 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8353690938 num_examples: 1689 download_size: 8385666223 dataset_size: 8353690938 - config_name: subset_474 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8593303832 num_examples: 1723 download_size: 8627266289 dataset_size: 8593303832 - config_name: subset_475 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8491558230 num_examples: 1701 download_size: 8524198543 dataset_size: 8491558230 - config_name: subset_476 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8452866881 num_examples: 1672 download_size: 8485234629 dataset_size: 8452866881 - config_name: subset_477 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8704398386 num_examples: 1714 download_size: 8738159122 dataset_size: 8704398386 - config_name: subset_478 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8284525589 num_examples: 1669 download_size: 8316981929 dataset_size: 8284525589 - config_name: subset_479 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8282788425 num_examples: 1662 download_size: 8315213911 dataset_size: 8282788425 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14438094478 num_examples: 2123 download_size: 14487015492 dataset_size: 14438094478 - config_name: subset_480 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8576390099 num_examples: 1708 download_size: 8609651781 dataset_size: 8576390099 - config_name: subset_481 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8507463443 num_examples: 1693 download_size: 8541308945 dataset_size: 8507463443 - config_name: subset_482 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8255501088 num_examples: 1644 download_size: 8287721624 dataset_size: 8255501088 - config_name: subset_483 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8274451687 num_examples: 1667 download_size: 8306808681 dataset_size: 8274451687 - config_name: subset_484 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8573537899 num_examples: 1690 download_size: 8607168860 dataset_size: 8573537899 - config_name: subset_485 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8384503494 num_examples: 1686 download_size: 8417100259 dataset_size: 8384503494 - config_name: subset_486 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8588897502 num_examples: 1681 download_size: 8622495228 dataset_size: 8588897502 - config_name: subset_487 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8437517535 num_examples: 1712 download_size: 8470186354 dataset_size: 8437517535 - config_name: subset_488 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8418827545 num_examples: 1681 download_size: 8451202784 dataset_size: 8418827545 - config_name: subset_489 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8584589048 num_examples: 1709 download_size: 8618337451 dataset_size: 8584589048 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14774694546 num_examples: 2154 download_size: 14824929896 dataset_size: 14774694546 - config_name: subset_490 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8663901120 num_examples: 1682 download_size: 8697624762 dataset_size: 8663901120 - config_name: subset_491 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8488371055 num_examples: 1722 download_size: 8521153862 dataset_size: 8488371055 - config_name: subset_492 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8203980754 num_examples: 1655 download_size: 8236225054 dataset_size: 8203980754 - config_name: subset_493 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8391363760 num_examples: 1667 download_size: 8423105052 dataset_size: 8391363760 - config_name: subset_494 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8568767921 num_examples: 1712 download_size: 8602723551 dataset_size: 8568767921 - config_name: subset_495 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8174939825 num_examples: 1617 download_size: 8206800473 dataset_size: 8174939825 - config_name: subset_496 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8570411815 num_examples: 1706 download_size: 8604255375 dataset_size: 8570411815 - config_name: subset_497 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8379436558 num_examples: 1647 download_size: 8411700765 dataset_size: 8379436558 - config_name: subset_498 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8262554246 num_examples: 1635 download_size: 8294680975 dataset_size: 8262554246 - config_name: subset_499 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8342799972 num_examples: 1656 download_size: 8375085115 dataset_size: 8342799972 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17613015503 num_examples: 2216 download_size: 17669708546 dataset_size: 17613015503 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14650896380 num_examples: 2139 download_size: 14700785975 dataset_size: 14650896380 - config_name: subset_500 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8430401608 num_examples: 1705 download_size: 8462967390 dataset_size: 8430401608 - config_name: subset_501 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8386054846 num_examples: 1676 download_size: 8418093888 dataset_size: 8386054846 - config_name: subset_502 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8291804091 num_examples: 1691 download_size: 8324392895 dataset_size: 8291804091 - config_name: subset_503 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8522249041 num_examples: 1712 download_size: 8555125608 dataset_size: 8522249041 - config_name: subset_504 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8504759173 num_examples: 1699 download_size: 8538443019 dataset_size: 8504759173 - config_name: subset_505 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8838284884 num_examples: 1720 download_size: 8871610293 dataset_size: 8838284884 - config_name: subset_506 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8510139570 num_examples: 1719 download_size: 8543995249 dataset_size: 8510139570 - config_name: subset_507 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8409163618 num_examples: 1713 download_size: 8441906356 dataset_size: 8409163618 - config_name: subset_508 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8588008063 num_examples: 1705 download_size: 8621825321 dataset_size: 8588008063 - config_name: subset_509 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8301639362 num_examples: 1688 download_size: 8334312765 dataset_size: 8301639362 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14432555019 num_examples: 2132 download_size: 14481692751 dataset_size: 14432555019 - config_name: subset_510 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8509654655 num_examples: 1709 download_size: 8543505342 dataset_size: 8509654655 - config_name: subset_511 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8152253737 num_examples: 1675 download_size: 8184762472 dataset_size: 8152253737 - config_name: subset_512 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8124134538 num_examples: 1633 download_size: 8156224283 dataset_size: 8124134538 - config_name: subset_513 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8457785980 num_examples: 1688 download_size: 8490228205 dataset_size: 8457785980 - config_name: subset_514 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8176494586 num_examples: 1649 download_size: 8208157175 dataset_size: 8176494586 - config_name: subset_515 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8449600460 num_examples: 1663 download_size: 8481929815 dataset_size: 8449600460 - config_name: subset_516 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8490244498 num_examples: 1704 download_size: 8522811553 dataset_size: 8490244498 - config_name: subset_517 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8511404348 num_examples: 1681 download_size: 8545098624 dataset_size: 8511404348 - config_name: subset_518 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8591455689 num_examples: 1674 download_size: 8624241495 dataset_size: 8591455689 - config_name: subset_519 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8593419410 num_examples: 1727 download_size: 8627485550 dataset_size: 8593419410 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11020293083 num_examples: 1601 download_size: 11058125578 dataset_size: 11020293083 - config_name: subset_520 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8182579727 num_examples: 1642 download_size: 8214372099 dataset_size: 8182579727 - config_name: subset_521 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8553497907 num_examples: 1689 download_size: 8587345591 dataset_size: 8553497907 - config_name: subset_522 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8447619989 num_examples: 1687 download_size: 8480217100 dataset_size: 8447619989 - config_name: subset_523 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8605695102 num_examples: 1686 download_size: 8639343629 dataset_size: 8605695102 - config_name: subset_524 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8230959805 num_examples: 1662 download_size: 8263208309 dataset_size: 8230959805 - config_name: subset_525 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8510842070 num_examples: 1665 download_size: 8544182808 dataset_size: 8510842070 - config_name: subset_526 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8408423738 num_examples: 1685 download_size: 8441048945 dataset_size: 8408423738 - config_name: subset_527 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8219454542 num_examples: 1633 download_size: 8251593706 dataset_size: 8219454542 - config_name: subset_528 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8475244982 num_examples: 1700 download_size: 8507313060 dataset_size: 8475244982 - config_name: subset_529 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8333066335 num_examples: 1680 download_size: 8365502946 dataset_size: 8333066335 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12267977115 num_examples: 1816 download_size: 12310050810 dataset_size: 12267977115 - config_name: subset_530 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8575189198 num_examples: 1681 download_size: 8608931147 dataset_size: 8575189198 - config_name: subset_531 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8418213352 num_examples: 1688 download_size: 8450742964 dataset_size: 8418213352 - config_name: subset_532 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 4996766459 num_examples: 1030 download_size: 5016215095 dataset_size: 4996766459 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14247382247 num_examples: 2086 download_size: 14296226830 dataset_size: 14247382247 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14238518466 num_examples: 2130 download_size: 14287390000 dataset_size: 14238518466 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14607130726 num_examples: 2168 download_size: 14657506181 dataset_size: 14607130726 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14210056261 num_examples: 2122 download_size: 14259218666 dataset_size: 14210056261 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14211054746 num_examples: 2116 download_size: 14259893924 dataset_size: 14211054746 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14605275078 num_examples: 2122 download_size: 14655148647 dataset_size: 14605275078 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16966145283 num_examples: 2212 download_size: 17020515363 dataset_size: 16966145283 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14182365223 num_examples: 2148 download_size: 14231621670 dataset_size: 14182365223 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14125830113 num_examples: 2099 download_size: 14174466038 dataset_size: 14125830113 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14486968006 num_examples: 2164 download_size: 14536306900 dataset_size: 14486968006 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14272019850 num_examples: 2119 download_size: 14320951437 dataset_size: 14272019850 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13951158579 num_examples: 2114 download_size: 13998495055 dataset_size: 13951158579 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14091720924 num_examples: 2101 download_size: 14140547460 dataset_size: 14091720924 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14109820088 num_examples: 2142 download_size: 14158896675 dataset_size: 14109820088 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14005906998 num_examples: 2113 download_size: 14054155208 dataset_size: 14005906998 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14301837003 num_examples: 2160 download_size: 14351134493 dataset_size: 14301837003 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13966734315 num_examples: 2117 download_size: 14014525192 dataset_size: 13966734315 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17450587514 num_examples: 2266 download_size: 17506459251 dataset_size: 17450587514 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14219970789 num_examples: 2148 download_size: 14269024541 dataset_size: 14219970789 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14501306569 num_examples: 2167 download_size: 14551012326 dataset_size: 14501306569 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13769708196 num_examples: 2109 download_size: 13817441686 dataset_size: 13769708196 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13883416692 num_examples: 2117 download_size: 13931221847 dataset_size: 13883416692 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14219211013 num_examples: 2160 download_size: 14268320291 dataset_size: 14219211013 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13926577539 num_examples: 2115 download_size: 13974286633 dataset_size: 13926577539 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14312562492 num_examples: 2142 download_size: 14361474867 dataset_size: 14312562492 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14192446366 num_examples: 2145 download_size: 14241283219 dataset_size: 14192446366 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13896932954 num_examples: 2118 download_size: 13944745673 dataset_size: 13896932954 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13740365813 num_examples: 2143 download_size: 13788404251 dataset_size: 13740365813 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17326265954 num_examples: 2240 download_size: 17382031150 dataset_size: 17326265954 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13956747719 num_examples: 2148 download_size: 14004630176 dataset_size: 13956747719 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13911203686 num_examples: 2137 download_size: 13959165662 dataset_size: 13911203686 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13638266766 num_examples: 2122 download_size: 13686243724 dataset_size: 13638266766 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13903350636 num_examples: 2137 download_size: 13951036539 dataset_size: 13903350636 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14069026843 num_examples: 2155 download_size: 14117216022 dataset_size: 14069026843 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13906708923 num_examples: 2142 download_size: 13954600557 dataset_size: 13906708923 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13356555486 num_examples: 2116 download_size: 13403132164 dataset_size: 13356555486 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13674103379 num_examples: 2103 download_size: 13721834580 dataset_size: 13674103379 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13773798807 num_examples: 2142 download_size: 13821765327 dataset_size: 13773798807 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13775818415 num_examples: 2126 download_size: 13823549616 dataset_size: 13775818415 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 17101700745 num_examples: 2236 download_size: 17157344999 dataset_size: 17101700745 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13384785417 num_examples: 2103 download_size: 13431244462 dataset_size: 13384785417 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13360679867 num_examples: 2093 download_size: 13406930008 dataset_size: 13360679867 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13535363269 num_examples: 2130 download_size: 13583293758 dataset_size: 13535363269 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13441592585 num_examples: 2095 download_size: 13487809010 dataset_size: 13441592585 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13422431033 num_examples: 2124 download_size: 13469001040 dataset_size: 13422431033 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13733605259 num_examples: 2160 download_size: 13781705313 dataset_size: 13733605259 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13503605486 num_examples: 2132 download_size: 13551490247 dataset_size: 13503605486 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13765914180 num_examples: 2132 download_size: 13813630773 dataset_size: 13765914180 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13111453176 num_examples: 2046 download_size: 13157636795 dataset_size: 13111453176 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: esA.id dtype: string - name: esA.laser_score dtype: float64 - name: esA.audio.speaker_embedding sequence: float32 - name: esA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13252223433 num_examples: 2038 download_size: 13298410606 dataset_size: 13252223433 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_145 data_files: - split: train path: subset_145/train-* - config_name: subset_146 data_files: - split: train path: subset_146/train-* - config_name: subset_147 data_files: - split: train path: subset_147/train-* - config_name: subset_148 data_files: - split: train path: subset_148/train-* - config_name: subset_149 data_files: - split: train path: subset_149/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_150 data_files: - split: train path: subset_150/train-* - config_name: subset_151 data_files: - split: train path: subset_151/train-* - config_name: subset_152 data_files: - split: train path: subset_152/train-* - config_name: subset_153 data_files: - split: train path: subset_153/train-* - config_name: subset_154 data_files: - split: train path: subset_154/train-* - config_name: subset_155 data_files: - split: train path: subset_155/train-* - config_name: subset_156 data_files: - split: train path: subset_156/train-* - config_name: subset_157 data_files: - split: train path: subset_157/train-* - config_name: subset_158 data_files: - split: train path: subset_158/train-* - config_name: subset_159 data_files: - split: train path: subset_159/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_160 data_files: - split: train path: subset_160/train-* - config_name: subset_161 data_files: - split: train path: subset_161/train-* - config_name: subset_162 data_files: - split: train path: subset_162/train-* - config_name: subset_163 data_files: - split: train path: subset_163/train-* - config_name: subset_164 data_files: - split: train path: subset_164/train-* - config_name: subset_165 data_files: - split: train path: subset_165/train-* - config_name: subset_166 data_files: - split: train path: subset_166/train-* - config_name: subset_167 data_files: - split: train path: subset_167/train-* - config_name: subset_168 data_files: - split: train path: subset_168/train-* - config_name: subset_169 data_files: - split: train path: subset_169/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_170 data_files: - split: train path: subset_170/train-* - config_name: subset_171 data_files: - split: train path: subset_171/train-* - config_name: subset_172 data_files: - split: train path: subset_172/train-* - config_name: subset_173 data_files: - split: train path: subset_173/train-* - config_name: subset_174 data_files: - split: train path: subset_174/train-* - config_name: subset_175 data_files: - split: train path: subset_175/train-* - config_name: subset_176 data_files: - split: train path: subset_176/train-* - config_name: subset_177 data_files: - split: train path: subset_177/train-* - config_name: subset_178 data_files: - split: train path: subset_178/train-* - config_name: subset_179 data_files: - split: train path: subset_179/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_180 data_files: - split: train path: subset_180/train-* - config_name: subset_181 data_files: - split: train path: subset_181/train-* - config_name: subset_182 data_files: - split: train path: subset_182/train-* - config_name: subset_183 data_files: - split: train path: subset_183/train-* - config_name: subset_184 data_files: - split: train path: subset_184/train-* - config_name: subset_185 data_files: - split: train path: subset_185/train-* - config_name: subset_186 data_files: - split: train path: subset_186/train-* - config_name: subset_187 data_files: - split: train path: subset_187/train-* - config_name: subset_188 data_files: - split: train path: subset_188/train-* - config_name: subset_189 data_files: - split: train path: subset_189/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_190 data_files: - split: train path: subset_190/train-* - config_name: subset_191 data_files: - split: train path: subset_191/train-* - config_name: subset_192 data_files: - split: train path: subset_192/train-* - config_name: subset_193 data_files: - split: train path: subset_193/train-* - config_name: subset_194 data_files: - split: train path: subset_194/train-* - config_name: subset_195 data_files: - split: train path: subset_195/train-* - config_name: subset_196 data_files: - split: train path: subset_196/train-* - config_name: subset_197 data_files: - split: train path: subset_197/train-* - config_name: subset_198 data_files: - split: train path: subset_198/train-* - config_name: subset_199 data_files: - split: train path: subset_199/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_200 data_files: - split: train path: subset_200/train-* - config_name: subset_201 data_files: - split: train path: subset_201/train-* - config_name: subset_202 data_files: - split: train path: subset_202/train-* - config_name: subset_203 data_files: - split: train path: subset_203/train-* - config_name: subset_204 data_files: - split: train path: subset_204/train-* - config_name: subset_205 data_files: - split: train path: subset_205/train-* - config_name: subset_206 data_files: - split: train path: subset_206/train-* - config_name: subset_207 data_files: - split: train path: subset_207/train-* - config_name: subset_208 data_files: - split: train path: subset_208/train-* - config_name: subset_209 data_files: - split: train path: subset_209/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_210 data_files: - split: train path: subset_210/train-* - config_name: subset_211 data_files: - split: train path: subset_211/train-* - config_name: subset_212 data_files: - split: train path: subset_212/train-* - config_name: subset_213 data_files: - split: train path: subset_213/train-* - config_name: subset_214 data_files: - split: train path: subset_214/train-* - config_name: subset_215 data_files: - split: train path: subset_215/train-* - config_name: subset_216 data_files: - split: train path: subset_216/train-* - config_name: subset_217 data_files: - split: train path: subset_217/train-* - config_name: subset_218 data_files: - split: train path: subset_218/train-* - config_name: subset_219 data_files: - split: train path: subset_219/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_220 data_files: - split: train path: subset_220/train-* - config_name: subset_221 data_files: - split: train path: subset_221/train-* - config_name: subset_222 data_files: - split: train path: subset_222/train-* - config_name: subset_223 data_files: - split: train path: subset_223/train-* - config_name: subset_224 data_files: - split: train path: subset_224/train-* - config_name: subset_225 data_files: - split: train path: subset_225/train-* - config_name: subset_226 data_files: - split: train path: subset_226/train-* - config_name: subset_227 data_files: - split: train path: subset_227/train-* - config_name: subset_228 data_files: - split: train path: subset_228/train-* - config_name: subset_229 data_files: - split: train path: subset_229/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_230 data_files: - split: train path: subset_230/train-* - config_name: subset_231 data_files: - split: train path: subset_231/train-* - config_name: subset_232 data_files: - split: train path: subset_232/train-* - config_name: subset_233 data_files: - split: train path: subset_233/train-* - config_name: subset_234 data_files: - split: train path: subset_234/train-* - config_name: subset_235 data_files: - split: train path: subset_235/train-* - config_name: subset_236 data_files: - split: train path: subset_236/train-* - config_name: subset_237 data_files: - split: train path: subset_237/train-* - config_name: subset_238 data_files: - split: train path: subset_238/train-* - config_name: subset_239 data_files: - split: train path: subset_239/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_240 data_files: - split: train path: subset_240/train-* - config_name: subset_241 data_files: - split: train path: subset_241/train-* - config_name: subset_242 data_files: - split: train path: subset_242/train-* - config_name: subset_243 data_files: - split: train path: subset_243/train-* - config_name: subset_244 data_files: - split: train path: subset_244/train-* - config_name: subset_245 data_files: - split: train path: subset_245/train-* - config_name: subset_246 data_files: - split: train path: subset_246/train-* - config_name: subset_247 data_files: - split: train path: subset_247/train-* - config_name: subset_248 data_files: - split: train path: subset_248/train-* - config_name: subset_249 data_files: - split: train path: subset_249/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_250 data_files: - split: train path: subset_250/train-* - config_name: subset_251 data_files: - split: train path: subset_251/train-* - config_name: subset_252 data_files: - split: train path: subset_252/train-* - config_name: subset_253 data_files: - split: train path: subset_253/train-* - config_name: subset_254 data_files: - split: train path: subset_254/train-* - config_name: subset_255 data_files: - split: train path: subset_255/train-* - config_name: subset_256 data_files: - split: train path: subset_256/train-* - config_name: subset_257 data_files: - split: train path: subset_257/train-* - config_name: subset_258 data_files: - split: train path: subset_258/train-* - config_name: subset_259 data_files: - split: train path: subset_259/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_260 data_files: - split: train path: subset_260/train-* - config_name: subset_261 data_files: - split: train path: subset_261/train-* - config_name: subset_262 data_files: - split: train path: subset_262/train-* - config_name: subset_263 data_files: - split: train path: subset_263/train-* - config_name: subset_264 data_files: - split: train path: subset_264/train-* - config_name: subset_265 data_files: - split: train path: subset_265/train-* - config_name: subset_266 data_files: - split: train path: subset_266/train-* - config_name: subset_267 data_files: - split: train path: subset_267/train-* - config_name: subset_268 data_files: - split: train path: subset_268/train-* - config_name: subset_269 data_files: - split: train path: subset_269/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_270 data_files: - split: train path: subset_270/train-* - config_name: subset_271 data_files: - split: train path: subset_271/train-* - config_name: subset_272 data_files: - split: train path: subset_272/train-* - config_name: subset_273 data_files: - split: train path: subset_273/train-* - config_name: subset_274 data_files: - split: train path: subset_274/train-* - config_name: subset_275 data_files: - split: train path: subset_275/train-* - config_name: subset_276 data_files: - split: train path: subset_276/train-* - config_name: subset_277 data_files: - split: train path: subset_277/train-* - config_name: subset_278 data_files: - split: train path: subset_278/train-* - config_name: subset_279 data_files: - split: train path: subset_279/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_280 data_files: - split: train path: subset_280/train-* - config_name: subset_281 data_files: - split: train path: subset_281/train-* - config_name: subset_282 data_files: - split: train path: subset_282/train-* - config_name: subset_283 data_files: - split: train path: subset_283/train-* - config_name: subset_284 data_files: - split: train path: subset_284/train-* - config_name: subset_285 data_files: - split: train path: subset_285/train-* - config_name: subset_286 data_files: - split: train path: subset_286/train-* - config_name: subset_287 data_files: - split: train path: subset_287/train-* - config_name: subset_288 data_files: - split: train path: subset_288/train-* - config_name: subset_289 data_files: - split: train path: subset_289/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_290 data_files: - split: train path: subset_290/train-* - config_name: subset_291 data_files: - split: train path: subset_291/train-* - config_name: subset_292 data_files: - split: train path: subset_292/train-* - config_name: subset_293 data_files: - split: train path: subset_293/train-* - config_name: subset_294 data_files: - split: train path: subset_294/train-* - config_name: subset_295 data_files: - split: train path: subset_295/train-* - config_name: subset_296 data_files: - split: train path: subset_296/train-* - config_name: subset_297 data_files: - split: train path: subset_297/train-* - config_name: subset_298 data_files: - split: train path: subset_298/train-* - config_name: subset_299 data_files: - split: train path: subset_299/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_300 data_files: - split: train path: subset_300/train-* - config_name: subset_301 data_files: - split: train path: subset_301/train-* - config_name: subset_302 data_files: - split: train path: subset_302/train-* - config_name: subset_303 data_files: - split: train path: subset_303/train-* - config_name: subset_304 data_files: - split: train path: subset_304/train-* - config_name: subset_305 data_files: - split: train path: subset_305/train-* - config_name: subset_306 data_files: - split: train path: subset_306/train-* - config_name: subset_307 data_files: - split: train path: subset_307/train-* - config_name: subset_308 data_files: - split: train path: subset_308/train-* - config_name: subset_309 data_files: - split: train path: subset_309/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_310 data_files: - split: train path: subset_310/train-* - config_name: subset_311 data_files: - split: train path: subset_311/train-* - config_name: subset_312 data_files: - split: train path: subset_312/train-* - config_name: subset_313 data_files: - split: train path: subset_313/train-* - config_name: subset_314 data_files: - split: train path: subset_314/train-* - config_name: subset_315 data_files: - split: train path: subset_315/train-* - config_name: subset_316 data_files: - split: train path: subset_316/train-* - config_name: subset_317 data_files: - split: train path: subset_317/train-* - config_name: subset_318 data_files: - split: train path: subset_318/train-* - config_name: subset_319 data_files: - split: train path: subset_319/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_320 data_files: - split: train path: subset_320/train-* - config_name: subset_321 data_files: - split: train path: subset_321/train-* - config_name: subset_322 data_files: - split: train path: subset_322/train-* - config_name: subset_323 data_files: - split: train path: subset_323/train-* - config_name: subset_324 data_files: - split: train path: subset_324/train-* - config_name: subset_325 data_files: - split: train path: subset_325/train-* - config_name: subset_326 data_files: - split: train path: subset_326/train-* - config_name: subset_327 data_files: - split: train path: subset_327/train-* - config_name: subset_328 data_files: - split: train path: subset_328/train-* - config_name: subset_329 data_files: - split: train path: subset_329/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_330 data_files: - split: train path: subset_330/train-* - config_name: subset_331 data_files: - split: train path: subset_331/train-* - config_name: subset_332 data_files: - split: train path: subset_332/train-* - config_name: subset_333 data_files: - split: train path: subset_333/train-* - config_name: subset_334 data_files: - split: train path: subset_334/train-* - config_name: subset_335 data_files: - split: train path: subset_335/train-* - config_name: subset_336 data_files: - split: train path: subset_336/train-* - config_name: subset_337 data_files: - split: train path: subset_337/train-* - config_name: subset_338 data_files: - split: train path: subset_338/train-* - config_name: subset_339 data_files: - split: train path: subset_339/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_340 data_files: - split: train path: subset_340/train-* - config_name: subset_341 data_files: - split: train path: subset_341/train-* - config_name: subset_342 data_files: - split: train path: subset_342/train-* - config_name: subset_343 data_files: - split: train path: subset_343/train-* - config_name: subset_344 data_files: - split: train path: subset_344/train-* - config_name: subset_345 data_files: - split: train path: subset_345/train-* - config_name: subset_346 data_files: - split: train path: subset_346/train-* - config_name: subset_347 data_files: - split: train path: subset_347/train-* - config_name: subset_348 data_files: - split: train path: subset_348/train-* - config_name: subset_349 data_files: - split: train path: subset_349/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_350 data_files: - split: train path: subset_350/train-* - config_name: subset_351 data_files: - split: train path: subset_351/train-* - config_name: subset_352 data_files: - split: train path: subset_352/train-* - config_name: subset_353 data_files: - split: train path: subset_353/train-* - config_name: subset_354 data_files: - split: train path: subset_354/train-* - config_name: subset_355 data_files: - split: train path: subset_355/train-* - config_name: subset_356 data_files: - split: train path: subset_356/train-* - config_name: subset_357 data_files: - split: train path: subset_357/train-* - config_name: subset_358 data_files: - split: train path: subset_358/train-* - config_name: subset_359 data_files: - split: train path: subset_359/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_360 data_files: - split: train path: subset_360/train-* - config_name: subset_361 data_files: - split: train path: subset_361/train-* - config_name: subset_362 data_files: - split: train path: subset_362/train-* - config_name: subset_363 data_files: - split: train path: subset_363/train-* - config_name: subset_364 data_files: - split: train path: subset_364/train-* - config_name: subset_365 data_files: - split: train path: subset_365/train-* - config_name: subset_366 data_files: - split: train path: subset_366/train-* - config_name: subset_367 data_files: - split: train path: subset_367/train-* - config_name: subset_368 data_files: - split: train path: subset_368/train-* - config_name: subset_369 data_files: - split: train path: subset_369/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_370 data_files: - split: train path: subset_370/train-* - config_name: subset_371 data_files: - split: train path: subset_371/train-* - config_name: subset_372 data_files: - split: train path: subset_372/train-* - config_name: subset_373 data_files: - split: train path: subset_373/train-* - config_name: subset_374 data_files: - split: train path: subset_374/train-* - config_name: subset_375 data_files: - split: train path: subset_375/train-* - config_name: subset_376 data_files: - split: train path: subset_376/train-* - config_name: subset_377 data_files: - split: train path: subset_377/train-* - config_name: subset_378 data_files: - split: train path: subset_378/train-* - config_name: subset_379 data_files: - split: train path: subset_379/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_380 data_files: - split: train path: subset_380/train-* - config_name: subset_381 data_files: - split: train path: subset_381/train-* - config_name: subset_382 data_files: - split: train path: subset_382/train-* - config_name: subset_383 data_files: - split: train path: subset_383/train-* - config_name: subset_384 data_files: - split: train path: subset_384/train-* - config_name: subset_385 data_files: - split: train path: subset_385/train-* - config_name: subset_386 data_files: - split: train path: subset_386/train-* - config_name: subset_387 data_files: - split: train path: subset_387/train-* - config_name: subset_388 data_files: - split: train path: subset_388/train-* - config_name: subset_389 data_files: - split: train path: subset_389/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_390 data_files: - split: train path: subset_390/train-* - config_name: subset_391 data_files: - split: train path: subset_391/train-* - config_name: subset_392 data_files: - split: train path: subset_392/train-* - config_name: subset_393 data_files: - split: train path: subset_393/train-* - config_name: subset_394 data_files: - split: train path: subset_394/train-* - config_name: subset_395 data_files: - split: train path: subset_395/train-* - config_name: subset_396 data_files: - split: train path: subset_396/train-* - config_name: subset_397 data_files: - split: train path: subset_397/train-* - config_name: subset_398 data_files: - split: train path: subset_398/train-* - config_name: subset_399 data_files: - split: train path: subset_399/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_400 data_files: - split: train path: subset_400/train-* - config_name: subset_401 data_files: - split: train path: subset_401/train-* - config_name: subset_402 data_files: - split: train path: subset_402/train-* - config_name: subset_403 data_files: - split: train path: subset_403/train-* - config_name: subset_404 data_files: - split: train path: subset_404/train-* - config_name: subset_405 data_files: - split: train path: subset_405/train-* - config_name: subset_406 data_files: - split: train path: subset_406/train-* - config_name: subset_407 data_files: - split: train path: subset_407/train-* - config_name: subset_408 data_files: - split: train path: subset_408/train-* - config_name: subset_409 data_files: - split: train path: subset_409/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_410 data_files: - split: train path: subset_410/train-* - config_name: subset_411 data_files: - split: train path: subset_411/train-* - config_name: subset_412 data_files: - split: train path: subset_412/train-* - config_name: subset_413 data_files: - split: train path: subset_413/train-* - config_name: subset_414 data_files: - split: train path: subset_414/train-* - config_name: subset_415 data_files: - split: train path: subset_415/train-* - config_name: subset_416 data_files: - split: train path: subset_416/train-* - config_name: subset_417 data_files: - split: train path: subset_417/train-* - config_name: subset_418 data_files: - split: train path: subset_418/train-* - config_name: subset_419 data_files: - split: train path: subset_419/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_420 data_files: - split: train path: subset_420/train-* - config_name: subset_421 data_files: - split: train path: subset_421/train-* - config_name: subset_422 data_files: - split: train path: subset_422/train-* - config_name: subset_423 data_files: - split: train path: subset_423/train-* - config_name: subset_424 data_files: - split: train path: subset_424/train-* - config_name: subset_425 data_files: - split: train path: subset_425/train-* - config_name: subset_426 data_files: - split: train path: subset_426/train-* - config_name: subset_427 data_files: - split: train path: subset_427/train-* - config_name: subset_428 data_files: - split: train path: subset_428/train-* - config_name: subset_429 data_files: - split: train path: subset_429/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_430 data_files: - split: train path: subset_430/train-* - config_name: subset_431 data_files: - split: train path: subset_431/train-* - config_name: subset_432 data_files: - split: train path: subset_432/train-* - config_name: subset_433 data_files: - split: train path: subset_433/train-* - config_name: subset_434 data_files: - split: train path: subset_434/train-* - config_name: subset_435 data_files: - split: train path: subset_435/train-* - config_name: subset_436 data_files: - split: train path: subset_436/train-* - config_name: subset_437 data_files: - split: train path: subset_437/train-* - config_name: subset_438 data_files: - split: train path: subset_438/train-* - config_name: subset_439 data_files: - split: train path: subset_439/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_440 data_files: - split: train path: subset_440/train-* - config_name: subset_441 data_files: - split: train path: subset_441/train-* - config_name: subset_442 data_files: - split: train path: subset_442/train-* - config_name: subset_443 data_files: - split: train path: subset_443/train-* - config_name: subset_444 data_files: - split: train path: subset_444/train-* - config_name: subset_445 data_files: - split: train path: subset_445/train-* - config_name: subset_446 data_files: - split: train path: subset_446/train-* - config_name: subset_447 data_files: - split: train path: subset_447/train-* - config_name: subset_448 data_files: - split: train path: subset_448/train-* - config_name: subset_449 data_files: - split: train path: subset_449/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_450 data_files: - split: train path: subset_450/train-* - config_name: subset_451 data_files: - split: train path: subset_451/train-* - config_name: subset_452 data_files: - split: train path: subset_452/train-* - config_name: subset_453 data_files: - split: train path: subset_453/train-* - config_name: subset_454 data_files: - split: train path: subset_454/train-* - config_name: subset_455 data_files: - split: train path: subset_455/train-* - config_name: subset_456 data_files: - split: train path: subset_456/train-* - config_name: subset_457 data_files: - split: train path: subset_457/train-* - config_name: subset_458 data_files: - split: train path: subset_458/train-* - config_name: subset_459 data_files: - split: train path: subset_459/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_460 data_files: - split: train path: subset_460/train-* - config_name: subset_461 data_files: - split: train path: subset_461/train-* - config_name: subset_462 data_files: - split: train path: subset_462/train-* - config_name: subset_463 data_files: - split: train path: subset_463/train-* - config_name: subset_464 data_files: - split: train path: subset_464/train-* - config_name: subset_465 data_files: - split: train path: subset_465/train-* - config_name: subset_466 data_files: - split: train path: subset_466/train-* - config_name: subset_467 data_files: - split: train path: subset_467/train-* - config_name: subset_468 data_files: - split: train path: subset_468/train-* - config_name: subset_469 data_files: - split: train path: subset_469/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_470 data_files: - split: train path: subset_470/train-* - config_name: subset_471 data_files: - split: train path: subset_471/train-* - config_name: subset_472 data_files: - split: train path: subset_472/train-* - config_name: subset_473 data_files: - split: train path: subset_473/train-* - config_name: subset_474 data_files: - split: train path: subset_474/train-* - config_name: subset_475 data_files: - split: train path: subset_475/train-* - config_name: subset_476 data_files: - split: train path: subset_476/train-* - config_name: subset_477 data_files: - split: train path: subset_477/train-* - config_name: subset_478 data_files: - split: train path: subset_478/train-* - config_name: subset_479 data_files: - split: train path: subset_479/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_480 data_files: - split: train path: subset_480/train-* - config_name: subset_481 data_files: - split: train path: subset_481/train-* - config_name: subset_482 data_files: - split: train path: subset_482/train-* - config_name: subset_483 data_files: - split: train path: subset_483/train-* - config_name: subset_484 data_files: - split: train path: subset_484/train-* - config_name: subset_485 data_files: - split: train path: subset_485/train-* - config_name: subset_486 data_files: - split: train path: subset_486/train-* - config_name: subset_487 data_files: - split: train path: subset_487/train-* - config_name: subset_488 data_files: - split: train path: subset_488/train-* - config_name: subset_489 data_files: - split: train path: subset_489/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_490 data_files: - split: train path: subset_490/train-* - config_name: subset_491 data_files: - split: train path: subset_491/train-* - config_name: subset_492 data_files: - split: train path: subset_492/train-* - config_name: subset_493 data_files: - split: train path: subset_493/train-* - config_name: subset_494 data_files: - split: train path: subset_494/train-* - config_name: subset_495 data_files: - split: train path: subset_495/train-* - config_name: subset_496 data_files: - split: train path: subset_496/train-* - config_name: subset_497 data_files: - split: train path: subset_497/train-* - config_name: subset_498 data_files: - split: train path: subset_498/train-* - config_name: subset_499 data_files: - split: train path: subset_499/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_500 data_files: - split: train path: subset_500/train-* - config_name: subset_501 data_files: - split: train path: subset_501/train-* - config_name: subset_502 data_files: - split: train path: subset_502/train-* - config_name: subset_503 data_files: - split: train path: subset_503/train-* - config_name: subset_504 data_files: - split: train path: subset_504/train-* - config_name: subset_505 data_files: - split: train path: subset_505/train-* - config_name: subset_506 data_files: - split: train path: subset_506/train-* - config_name: subset_507 data_files: - split: train path: subset_507/train-* - config_name: subset_508 data_files: - split: train path: subset_508/train-* - config_name: subset_509 data_files: - split: train path: subset_509/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_510 data_files: - split: train path: subset_510/train-* - config_name: subset_511 data_files: - split: train path: subset_511/train-* - config_name: subset_512 data_files: - split: train path: subset_512/train-* - config_name: subset_513 data_files: - split: train path: subset_513/train-* - config_name: subset_514 data_files: - split: train path: subset_514/train-* - config_name: subset_515 data_files: - split: train path: subset_515/train-* - config_name: subset_516 data_files: - split: train path: subset_516/train-* - config_name: subset_517 data_files: - split: train path: subset_517/train-* - config_name: subset_518 data_files: - split: train path: subset_518/train-* - config_name: subset_519 data_files: - split: train path: subset_519/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_520 data_files: - split: train path: subset_520/train-* - config_name: subset_521 data_files: - split: train path: subset_521/train-* - config_name: subset_522 data_files: - split: train path: subset_522/train-* - config_name: subset_523 data_files: - split: train path: subset_523/train-* - config_name: subset_524 data_files: - split: train path: subset_524/train-* - config_name: subset_525 data_files: - split: train path: subset_525/train-* - config_name: subset_526 data_files: - split: train path: subset_526/train-* - config_name: subset_527 data_files: - split: train path: subset_527/train-* - config_name: subset_528 data_files: - split: train path: subset_528/train-* - config_name: subset_529 data_files: - split: train path: subset_529/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_530 data_files: - split: train path: subset_530/train-* - config_name: subset_531 data_files: - split: train path: subset_531/train-* - config_name: subset_532 data_files: - split: train path: subset_532/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

japanese-asr/whisper_transcriptions.mls.wer_10.0

japanese-asr

--- dataset_info: - config_name: subset_0 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29741913577.241814 num_examples: 62101 download_size: 28406057868 dataset_size: 29741913577.241814 - config_name: subset_1 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29815585138.73427 num_examples: 62323 download_size: 28488972470 dataset_size: 29815585138.73427 - config_name: subset_10 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29831443458.675167 num_examples: 62172 download_size: 28490041949 dataset_size: 29831443458.675167 - config_name: subset_100 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29740102232.58974 num_examples: 62114 download_size: 28402573685 dataset_size: 29740102232.58974 - config_name: subset_101 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29804666990.485275 num_examples: 62225 download_size: 28477636147 dataset_size: 29804666990.485275 - config_name: subset_102 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29847859656.366245 num_examples: 62219 download_size: 28508104461 dataset_size: 29847859656.366245 - config_name: subset_103 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29776271336.13424 num_examples: 62248 download_size: 28453790146 dataset_size: 29776271336.13424 - config_name: subset_104 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29864954995.718533 num_examples: 62348 download_size: 28540369174 dataset_size: 29864954995.718533 - config_name: subset_105 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29845768222.852547 num_examples: 62287 download_size: 28508203679 dataset_size: 29845768222.852547 - config_name: subset_106 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29868915195.73696 num_examples: 62355 download_size: 28531446961 dataset_size: 29868915195.73696 - config_name: subset_107 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29833296511.762436 num_examples: 62252 download_size: 28502966117 dataset_size: 29833296511.762436 - config_name: subset_108 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29846554379.21017 num_examples: 62398 download_size: 28521313998 dataset_size: 29846554379.21017 - config_name: subset_109 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29808600165.9863 num_examples: 62240 download_size: 28473663596 dataset_size: 29808600165.9863 - config_name: subset_11 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29807895865.53131 num_examples: 62230 download_size: 28470625940 dataset_size: 29807895865.53131 - config_name: subset_110 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29829181073.93217 num_examples: 62281 download_size: 28508841100 dataset_size: 29829181073.93217 - config_name: subset_111 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29845682710.49548 num_examples: 62335 download_size: 28524753965 dataset_size: 29845682710.49548 - config_name: subset_112 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29826059756.774582 num_examples: 62252 download_size: 28493408051 dataset_size: 29826059756.774582 - config_name: subset_113 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29736425530.042995 num_examples: 62066 download_size: 28408328564 dataset_size: 29736425530.042995 - config_name: subset_114 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 4936296.0 num_examples: 11 download_size: 4709772 dataset_size: 4936296.0 - config_name: subset_115 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29775544304.801655 num_examples: 62159 download_size: 28447112935 dataset_size: 29775544304.801655 - config_name: subset_116 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29764092406.31982 num_examples: 62150 download_size: 28424856922 dataset_size: 29764092406.31982 - config_name: subset_117 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29734215090.831867 num_examples: 62098 download_size: 28401429108 dataset_size: 29734215090.831867 - config_name: subset_118 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29785403327.377136 num_examples: 62307 download_size: 28454761582 dataset_size: 29785403327.377136 - config_name: subset_119 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29887080358.46854 num_examples: 62437 download_size: 28560903814 dataset_size: 29887080358.46854 - config_name: subset_12 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29778963955.27637 num_examples: 62217 download_size: 28456064768 dataset_size: 29778963955.27637 - config_name: subset_120 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29795324063.32621 num_examples: 62213 download_size: 28459179628 dataset_size: 29795324063.32621 - config_name: subset_121 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29823497463.618946 num_examples: 62219 download_size: 28486036307 dataset_size: 29823497463.618946 - config_name: subset_122 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29825885978.784977 num_examples: 62198 download_size: 28495894587 dataset_size: 29825885978.784977 - config_name: subset_123 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29824518738.544853 num_examples: 62207 download_size: 28482461945 dataset_size: 29824518738.544853 - config_name: subset_124 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29734472830.244003 num_examples: 62044 download_size: 28397807256 dataset_size: 29734472830.244003 - config_name: subset_125 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29751692495.66535 num_examples: 62132 download_size: 28418245723 dataset_size: 29751692495.66535 - config_name: subset_126 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29860413580.83239 num_examples: 62262 download_size: 28531745153 dataset_size: 29860413580.83239 - config_name: subset_127 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29844407241.442238 num_examples: 62182 download_size: 28520446380 dataset_size: 29844407241.442238 - config_name: subset_128 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29802989154.327606 num_examples: 62225 download_size: 28463177779 dataset_size: 29802989154.327606 - config_name: subset_129 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29850861116.343075 num_examples: 62330 download_size: 28520805908 dataset_size: 29850861116.343075 - config_name: subset_13 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29796741055.90437 num_examples: 62202 download_size: 28466354764 dataset_size: 29796741055.90437 - config_name: subset_130 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 4263112.0 num_examples: 9 download_size: 4073797 dataset_size: 4263112.0 - config_name: subset_131 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29720943599.72362 num_examples: 61994 download_size: 28379216482 dataset_size: 29720943599.72362 - config_name: subset_132 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29797620915.980434 num_examples: 62210 download_size: 28461599359 dataset_size: 29797620915.980434 - config_name: subset_133 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29782749863.416126 num_examples: 62161 download_size: 28447689082 dataset_size: 29782749863.416126 - config_name: subset_134 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29775975351.80884 num_examples: 62252 download_size: 28445935648 dataset_size: 29775975351.80884 - config_name: subset_135 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29804785291.47995 num_examples: 62332 download_size: 28474094120 dataset_size: 29804785291.47995 - config_name: subset_136 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29764251087.81636 num_examples: 62135 download_size: 28435055519 dataset_size: 29764251087.81636 - config_name: subset_137 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29796171709.935783 num_examples: 62226 download_size: 28468528453 dataset_size: 29796171709.935783 - config_name: subset_138 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29818809747.066654 num_examples: 62253 download_size: 28486190334 dataset_size: 29818809747.066654 - config_name: subset_14 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29713149830.08086 num_examples: 62058 download_size: 28370992605 dataset_size: 29713149830.08086 - config_name: subset_15 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29857118469.690784 num_examples: 62295 download_size: 28520133081 dataset_size: 29857118469.690784 - config_name: subset_16 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44717472597.38111 num_examples: 93380 download_size: 42705151644 dataset_size: 44717472597.38111 - config_name: subset_17 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44567963372.985085 num_examples: 93081 download_size: 42557871062 dataset_size: 44567963372.985085 - config_name: subset_18 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 487488.0 num_examples: 1 download_size: 482536 dataset_size: 487488.0 - config_name: subset_19 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44578540518.278465 num_examples: 93092 download_size: 42574195823 dataset_size: 44578540518.278465 - config_name: subset_2 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29779834173.05709 num_examples: 62194 download_size: 28457283265 dataset_size: 29779834173.05709 - config_name: subset_20 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44612078576.6915 num_examples: 93192 download_size: 42608986260 dataset_size: 44612078576.6915 - config_name: subset_21 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44716611297.93694 num_examples: 93435 download_size: 42724070775 dataset_size: 44716611297.93694 - config_name: subset_22 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44642599292.25394 num_examples: 93272 download_size: 42638436011 dataset_size: 44642599292.25394 - config_name: subset_23 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44773238981.78718 num_examples: 93425 download_size: 42769260156 dataset_size: 44773238981.78718 - config_name: subset_24 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44643199115.213066 num_examples: 93280 download_size: 42643630676 dataset_size: 44643199115.213066 - config_name: subset_25 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44775786873.71317 num_examples: 93521 download_size: 42787596471 dataset_size: 44775786873.71317 - config_name: subset_26 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44724169162.378235 num_examples: 93381 download_size: 42734030121 dataset_size: 44724169162.378235 - config_name: subset_27 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44673408393.32555 num_examples: 93316 download_size: 42671093570 dataset_size: 44673408393.32555 - config_name: subset_28 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44647540966.199005 num_examples: 93158 download_size: 42647063249 dataset_size: 44647540966.199005 - config_name: subset_29 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 2062592.0 num_examples: 5 download_size: 1973372 dataset_size: 2062592.0 - config_name: subset_3 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29781556446.893677 num_examples: 62185 download_size: 28457664262 dataset_size: 29781556446.893677 - config_name: subset_30 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44619423613.42147 num_examples: 93230 download_size: 42616420647 dataset_size: 44619423613.42147 - config_name: subset_31 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44686832436.53614 num_examples: 93302 download_size: 42675035403 dataset_size: 44686832436.53614 - config_name: subset_32 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44667832285.4235 num_examples: 93252 download_size: 42664546252 dataset_size: 44667832285.4235 - config_name: subset_33 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44767218387.43479 num_examples: 93463 download_size: 42772690686 dataset_size: 44767218387.43479 - config_name: subset_34 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44759250508.174644 num_examples: 93435 download_size: 42765984681 dataset_size: 44759250508.174644 - config_name: subset_35 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44661416756.55649 num_examples: 93247 download_size: 42662115327 dataset_size: 44661416756.55649 - config_name: subset_36 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44697682741.818405 num_examples: 93316 download_size: 42706948136 dataset_size: 44697682741.818405 - config_name: subset_37 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44642072687.35433 num_examples: 93214 download_size: 42642766174 dataset_size: 44642072687.35433 - config_name: subset_38 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44703619421.43295 num_examples: 93385 download_size: 42705784293 dataset_size: 44703619421.43295 - config_name: subset_39 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44691234018.50057 num_examples: 93382 download_size: 42688816370 dataset_size: 44691234018.50057 - config_name: subset_4 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29804659756.840668 num_examples: 62191 download_size: 28469961087 dataset_size: 29804659756.840668 - config_name: subset_40 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 3749600.0 num_examples: 8 download_size: 3544062 dataset_size: 3749600.0 - config_name: subset_41 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44710781677.17146 num_examples: 93390 download_size: 42686048101 dataset_size: 44710781677.17146 - config_name: subset_42 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44595765733.45953 num_examples: 93072 download_size: 42586674927 dataset_size: 44595765733.45953 - config_name: subset_43 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44642287217.473366 num_examples: 93216 download_size: 42643283814 dataset_size: 44642287217.473366 - config_name: subset_44 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44680782381.93174 num_examples: 93330 download_size: 42679060966 dataset_size: 44680782381.93174 - config_name: subset_45 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44632730866.69406 num_examples: 93280 download_size: 42632582031 dataset_size: 44632730866.69406 - config_name: subset_46 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44777176265.9063 num_examples: 93367 download_size: 42774172043 dataset_size: 44777176265.9063 - config_name: subset_47 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44723520638.39092 num_examples: 93353 download_size: 42739592034 dataset_size: 44723520638.39092 - config_name: subset_48 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44699581610.83543 num_examples: 93264 download_size: 42691617545 dataset_size: 44699581610.83543 - config_name: subset_49 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29776883327.862305 num_examples: 62152 download_size: 28437717863 dataset_size: 29776883327.862305 - config_name: subset_5 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29770798634.794384 num_examples: 62238 download_size: 28425692361 dataset_size: 29770798634.794384 - config_name: subset_50 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29799476758.913025 num_examples: 62205 download_size: 28471561046 dataset_size: 29799476758.913025 - config_name: subset_51 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29840586701.87915 num_examples: 62210 download_size: 28512098634 dataset_size: 29840586701.87915 - config_name: subset_52 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29863217529.513218 num_examples: 62358 download_size: 28535498406 dataset_size: 29863217529.513218 - config_name: subset_53 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29800253005.76768 num_examples: 62172 download_size: 28473498615 dataset_size: 29800253005.76768 - config_name: subset_54 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29790807067.45104 num_examples: 62220 download_size: 28462782039 dataset_size: 29790807067.45104 - config_name: subset_55 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29756188946.40286 num_examples: 62087 download_size: 28428539117 dataset_size: 29756188946.40286 - config_name: subset_56 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 4052942.222222222 num_examples: 8 download_size: 3756055 dataset_size: 4052942.222222222 - config_name: subset_57 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29815135874.530243 num_examples: 62215 download_size: 28480808968 dataset_size: 29815135874.530243 - config_name: subset_58 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29768678268.566994 num_examples: 62182 download_size: 28432025537 dataset_size: 29768678268.566994 - config_name: subset_59 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29792832738.55261 num_examples: 62236 download_size: 28467550664 dataset_size: 29792832738.55261 - config_name: subset_6 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29760036816.438248 num_examples: 62119 download_size: 28431028357 dataset_size: 29760036816.438248 - config_name: subset_60 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29795475110.996426 num_examples: 62199 download_size: 28458203598 dataset_size: 29795475110.996426 - config_name: subset_61 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29810850600.259956 num_examples: 62218 download_size: 28472533876 dataset_size: 29810850600.259956 - config_name: subset_62 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29793053976.98263 num_examples: 62354 download_size: 28468189848 dataset_size: 29793053976.98263 - config_name: subset_63 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29830633313.527344 num_examples: 62245 download_size: 28488179308 dataset_size: 29830633313.527344 - config_name: subset_64 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29815723311.686073 num_examples: 62295 download_size: 28481396085 dataset_size: 29815723311.686073 - config_name: subset_65 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29816082510.257248 num_examples: 62317 download_size: 28483004258 dataset_size: 29816082510.257248 - config_name: subset_66 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29823849926.137985 num_examples: 62310 download_size: 28501727354 dataset_size: 29823849926.137985 - config_name: subset_67 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29779693486.822372 num_examples: 62204 download_size: 28440702784 dataset_size: 29779693486.822372 - config_name: subset_68 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29791077271.97951 num_examples: 62238 download_size: 28470796275 dataset_size: 29791077271.97951 - config_name: subset_69 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29804033246.804424 num_examples: 62214 download_size: 28469224555 dataset_size: 29804033246.804424 - config_name: subset_7 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 435616.0 num_examples: 1 download_size: 429318 dataset_size: 435616.0 - config_name: subset_70 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29769624892.128063 num_examples: 62139 download_size: 28427172030 dataset_size: 29769624892.128063 - config_name: subset_71 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29682503840.61426 num_examples: 61996 download_size: 28356389982 dataset_size: 29682503840.61426 - config_name: subset_72 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 1459624.0 num_examples: 3 download_size: 1398432 dataset_size: 1459624.0 - config_name: subset_73 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29818453655.1624 num_examples: 62294 download_size: 28492225008 dataset_size: 29818453655.1624 - config_name: subset_74 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29809226392.643494 num_examples: 62275 download_size: 28471896097 dataset_size: 29809226392.643494 - config_name: subset_75 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29813615006.46017 num_examples: 62247 download_size: 28481389086 dataset_size: 29813615006.46017 - config_name: subset_76 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29787940909.366352 num_examples: 62176 download_size: 28457880270 dataset_size: 29787940909.366352 - config_name: subset_77 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29786889343.17914 num_examples: 62093 download_size: 28459598814 dataset_size: 29786889343.17914 - config_name: subset_78 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29766008072.24979 num_examples: 62168 download_size: 28429784870 dataset_size: 29766008072.24979 - config_name: subset_79 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29771618615.300034 num_examples: 62183 download_size: 28430361717 dataset_size: 29771618615.300034 - config_name: subset_8 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29784846446.236767 num_examples: 62208 download_size: 28456467319 dataset_size: 29784846446.236767 - config_name: subset_80 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29825455286.15237 num_examples: 62242 download_size: 28494746372 dataset_size: 29825455286.15237 - config_name: subset_81 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44611282857.507706 num_examples: 93149 download_size: 42605499635 dataset_size: 44611282857.507706 - config_name: subset_82 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44633857773.640816 num_examples: 93209 download_size: 42617883549 dataset_size: 44633857773.640816 - config_name: subset_83 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44731114501.95697 num_examples: 93285 download_size: 42734681724 dataset_size: 44731114501.95697 - config_name: subset_84 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44652331899.52017 num_examples: 93224 download_size: 42640405452 dataset_size: 44652331899.52017 - config_name: subset_85 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44738443066.61914 num_examples: 93391 download_size: 42752260132 dataset_size: 44738443066.61914 - config_name: subset_86 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44658486276.88759 num_examples: 93256 download_size: 42653904477 dataset_size: 44658486276.88759 - config_name: subset_87 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44624811790.03121 num_examples: 93178 download_size: 42605954586 dataset_size: 44624811790.03121 - config_name: subset_88 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44661490498.22551 num_examples: 93239 download_size: 42652915154 dataset_size: 44661490498.22551 - config_name: subset_89 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44716406347.45679 num_examples: 93404 download_size: 42727072094 dataset_size: 44716406347.45679 - config_name: subset_9 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29792706171.83141 num_examples: 62109 download_size: 28450168341 dataset_size: 29792706171.83141 - config_name: subset_90 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 44676470960.951996 num_examples: 93187 download_size: 42678524371 dataset_size: 44676470960.951996 - config_name: subset_91 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29764280076.125225 num_examples: 62196 download_size: 28429282112 dataset_size: 29764280076.125225 - config_name: subset_92 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29850619337.3585 num_examples: 62351 download_size: 28512846915 dataset_size: 29850619337.3585 - config_name: subset_93 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29837744714.346436 num_examples: 62233 download_size: 28501403452 dataset_size: 29837744714.346436 - config_name: subset_94 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29839780119.8114 num_examples: 62323 download_size: 28513940315 dataset_size: 29839780119.8114 - config_name: subset_95 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29748188964.62823 num_examples: 62172 download_size: 28413924658 dataset_size: 29748188964.62823 - config_name: subset_96 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29800727262.69699 num_examples: 62260 download_size: 28475125160 dataset_size: 29800727262.69699 - config_name: subset_97 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29767717411.338116 num_examples: 62148 download_size: 28440311229 dataset_size: 29767717411.338116 - config_name: subset_98 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 4303888.0 num_examples: 9 download_size: 4144170 dataset_size: 4303888.0 - config_name: subset_99 features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_length dtype: int64 splits: - name: train num_bytes: 29787160440.723938 num_examples: 62157 download_size: 28445447346 dataset_size: 29787160440.723938 configs: - config_name: subset_0 data_files: - split: train path: subset_0/train-* - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

laion/strategic_game_maze

laion

--- license: cc-by-4.0 --- NOTICE: some of the game is mistakenly label as both length and width columns are 40, they are 30 actually. # maze This dataset contains 350,000 mazes, represents over 39.29 billion moves. Each maze is a 30x30 ASCII representation, with solutions derived using the BFS. It has two columns: - 'Maze': representation of maze in a list of string.shape is 30*30 - visual example <image src="https://cdn-uploads.huggingface.co/production/uploads/644b983f0fbe4830f192c4f5/BGplH40fK5wQzpofPocMK.png" alt="drawing" width="200"/> - 'Path': solution from start point to end point in a list of string, each item represent a position in the maze.

LLM360/K2Datasets

LLM360

--- license: odc-by --- # K2 Dataset Card <!-- Provide a quick summary of the dataset. --> The following data mix was used to train [K2](https://huggingface.co/LLM360/K2) and achieve results in line with Llama 2 70B. ## Dataset Details K2 was trained on 1.4T tokens across two stages. The data sources and data mix for each stage are listed below. ### Dataset Description: Stage 1 <!-- Provide a longer summary of what this dataset is. --> | Dataset | Starting Tokens | Multiplier | Total Tokens |% of Total | | ----------- | ----------- | ----------- | ----------- | ----------- | | [dm-math](https://github.com/google-deepmind/mathematics_dataset) | 4.33B | 3x | 13B | 1% | | pubmed-abstracts (from the Pile) | 4.77B | 3x | 14.3B | 1.1% | | uspto (from the Pile) | 4.77B | 3x | 14.3B | 1.1% | | pubmed-central (from the Pile) | 26B | 1x | 26B | 2% | | [redpajama.arxiv](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 27.3B | 1x | 27.3B | 2.1% | | [starcoder.spm](https://huggingface.co/datasets/bigcode/starcoderdata) | 67.6B | 0.5x | 33.8B | 2.6% | | [starcoder.fim](https://huggingface.co/datasets/bigcode/starcoderdata) | 67.6B | 0.5x | 33.8B | 2.6% | | [redpajama.stackexchange](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 61.1B | 1x | 61.1B | 4.7% | | [starcoder](https://huggingface.co/datasets/bigcode/starcoderdata) | 132.6B | 0.5x | 66.3B | 5.1% | | [pile-of-law](https://huggingface.co/datasets/pile-of-law/pile-of-law) | 76.7B | 1x | 76.7B | 5.9% | | [redpajama.book](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 80.6B | 1x | 80.6B | 6.2% | | [s2orc](https://allenai.org/data/s2orc) | 107.9B | 1x | 107.9B | 8.3% | | [redpajama.wikipedia](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 22.1B | 6x | 132.6B | 10.2% | | [refinedweb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 612.3B | 1x | 612.3B | 47.1% | | Totals | - | - | 1.3T | 100% | ### Dataset Description: Stage 2 | Dataset | Starting Tokens | Multiplier | Total Tokens |% of Total | | ----------- | ----------- | ----------- | ----------- | ----------- | | [open-web-math](https://huggingface.co/datasets/EleutherAI/proof-pile-2) | 14.6B | 1x | 14.6B | 21% | | [redpajama.arxiv](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 2B | 1x | 2B | 2.9% | | [simple-wiki](https://huggingface.co/datasets/allenai/dolma) | 4.3B | 1x | 4.3B | 6.2% | | [redpajama.book](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 2B | 1x | 2B | 2.9% | | [algebraic-stack](https://huggingface.co/datasets/EleutherAI/proof-pile-2) | 10.9B | 1x | 10.9B | 15.7% | | [pile-of-law](https://huggingface.co/datasets/pile-of-law/pile-of-law) | 2B | 0.5x | 33.8B | 2.9% | | books | 5.8B | 1x | 5.8B | 8.3% | | [pes20](https://huggingface.co/datasets/allenai/peS2o) | 1.2B | 1x | 1.2B | 1.8% | | [pubmed-central (from the Pile)](https://github.com/EleutherAI/pile-pubmedcentral) | 2B | 1x | 2B | 2.9% | | [redpajama.wikipedia](https://huggingface.co/datasets/cerebras/SlimPajama-627B) | 2B | 1x | 2B | 2.9% | | python | 20.5B | 1x | 20.5B | 29.6% | | [s2orc](https://allenai.org/data/s2orc) | 2B | 1x | 2B | 2.9% | | Totals | - | - | 69.4B* | 100% | *rounding #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> A step-by-step tutorial for reproducing the K2's data preperation can be found in the [LLM360 Pretraining Suite here](https://www.llm360.ai/pretraining.html) ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation **BibTeX:** ```bibtex @misc{ title={LLM360 K2-65B: Scaling Up Open and Transparent Language Models}, author={The LLM360 Team}, year={2024}, } ```

gsarti/flores_101

gsarti

--- annotations_creators: - found language_creators: - expert-generated language: - af - am - ar - hy - as - ast - az - be - bn - bs - bg - my - ca - ceb - zho - hr - cs - da - nl - en - et - tl - fi - fr - ff - gl - lg - ka - de - el - gu - ha - he - hi - hu - is - ig - id - ga - it - ja - jv - kea - kam - kn - kk - km - ko - ky - lo - lv - ln - lt - luo - lb - mk - ms - ml - mt - mi - mr - mn - ne - ns - 'no' - ny - oc - or - om - ps - fa - pl - pt - pa - ro - ru - sr - sn - sd - sk - sl - so - ku - es - sw - sv - tg - ta - te - th - tr - uk - umb - ur - uz - vi - cy - wo - xh - yo - zu license: - cc-by-sa-4.0 multilinguality: - multilingual - translation size_categories: - unknown source_datasets: - extended|flores task_categories: - text-generation - translation task_ids: [] paperswithcode_id: flores pretty_name: flores101 tags: - conditional-text-generation --- # Dataset Card for Flores 101 ## Table of Contents - [Dataset Card for Flores 101](#dataset-card-for-flores-101) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Home:** [WMT](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html) - **Repository:** [Github](https://github.com/facebookresearch/flores) - **Blogpost:** [FAIR](https://ai.facebook.com/blog/the-flores-101-data-set-helping-build-better-translation-systems-around-the-world) - **Paper:** [Arxiv](https://arxiv.org/abs/2106.03193) - **Point of Contact:** [[email protected]](mailto:[email protected]) - **Leaderboard** [Dynabench](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) ### Dataset Summary FLORES is a benchmark dataset for machine translation between English and low-resource languages. Abstract from the original paper: > One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current evaluation benchmarks either lack good coverage of low-resource languages, consider only restricted domains, or are low quality because they are constructed using semi-automatic procedures. In this work, we introduce the FLORES evaluation benchmark, consisting of 3001 sentences extracted from English Wikipedia and covering a variety of different topics and domains. These sentences have been translated in 101 languages by professional translators through a carefully controlled process. The resulting dataset enables better assessment of model quality on the long tail of low-resource languages, including the evaluation of many-to-many multilingual translation systems, as all translations are multilingually aligned. By publicly releasing such a high-quality and high-coverage dataset, we hope to foster progress in the machine translation community and beyond. **Disclaimer**: *The Flores-101 dataset is hosted by the Facebook and licensed under the [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/). ### Supported Tasks and Leaderboards #### Multilingual Machine Translation Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). ### Languages The dataset contains parallel sentences for 101 languages, as mentioned in the original [Github](https://github.com/facebookresearch/flores/blob/master/README.md) page for the project. Languages are identified with the ISO 639-3 code (e.g. `eng`, `fra`, `rus`) as in the original dataset. **New:** Use the configuration `all` to access the full set of parallel sentences for all the available languages in a single command. ## Dataset Structure ### Data Instances A sample from the `dev` split for the Russian language (`rus` config) is provided below. All configurations have the same structure, and all sentences are aligned across configurations and splits. ```python { 'id': 1, 'sentence': 'В понедельник ученые из Медицинской школы Стэнфордского университета объявили об изобретении нового диагностического инструмента, который может сортировать клетки по их типу; это маленький чип, который можно напечатать, используя стандартный струйный принтер примерно за 1 цент США.', 'URL': 'https://en.wikinews.org/wiki/Scientists_say_new_medical_diagnostic_chip_can_sort_cells_anywhere_with_an_inkjet', 'domain': 'wikinews', 'topic': 'health', 'has_image': 0, 'has_hyperlink': 0 } ``` The text is provided as-in the original dataset, without further preprocessing or tokenization. ### Data Fields - `id`: Row number for the data entry, starting at 1. - `sentence`: The full sentence in the specific language. - `URL`: The URL for the English article from which the sentence was extracted. - `domain`: The domain of the sentence. - `topic`: The topic of the sentence. - `has_image`: Whether the original article contains an image. - `has_hyperlink`: Whether the sentence contains a hyperlink. ### Data Splits | config| `dev`| `devtest`| |-----------------:|-----:|---------:| |all configurations| 997| 1012:| ### Dataset Creation Please refer to the original article [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://arxiv.org/abs/2106.03193) for additional information on dataset creation. ## Additional Information ### Dataset Curators The original authors of FLORES-101 are the curators of the original dataset. For problems or updates on this 🤗 Datasets version, please contact [[email protected]](mailto:[email protected]). ### Licensing Information Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/). ### Citation Information Please cite the authors if you use these corpora in your work: ```bibtex @inproceedings{flores101, title={The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation}, author={Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm\'{a}n, Francisco and Fan, Angela}, journal={arXiv preprint arXiv:2106.03193}, year={2021} } ```

Voxel51/PIDray

Voxel51

--- annotations_creators: [] language: en license: apache-2.0 size_categories: - 1K<n<10K task_categories: - object-detection task_ids: [] pretty_name: pidray tags: - fiftyone - image - object-detection dataset_summary: '  This is a [FiftyOne](https://github.com/voxel51/fiftyone) dataset with 9482 samples. ## Installation If you haven''t already, install FiftyOne: ```bash pip install -U fiftyone ``` ## Usage ```python import fiftyone as fo import fiftyone.utils.huggingface as fouh # Load the dataset # Note: other available arguments include ''max_samples'', etc dataset = fouh.load_from_hub("voxel51/PIDray") # Launch the App session = fo.launch_app(dataset) ``` ' --- # Dataset Card for pidray PIDray is a large-scale dataset which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. The dataset contains 12 categories of prohibited items in 47, 677 X-ray images with high-quality annotated segmentation masks and bounding boxes.  This is a [FiftyOne](https://github.com/voxel51/fiftyone) dataset with 9482 samples. ## Installation If you haven't already, install FiftyOne: ```bash pip install -U fiftyone ``` ## Usage ```python import fiftyone as fo import fiftyone.utils.huggingface as fouh # Load the dataset # Note: other available arguments include 'max_samples', etc dataset = fouh.load_from_hub("dgural/PIDray") # Launch the App session = fo.launch_app(dataset) ``` ## Dataset Details ### Dataset Description From _Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark_: Automatic security inspection using computer vision technology is a challenging task in real-world scenarios due to various factors, including intra-class variance, class imbalance, and occlusion. Most of the previous methods rarely solve the cases that the prohibited items are deliberately hidden in messy objects due to the lack of large-scale datasets, restricted their applications in real-world scenarios. Towards real-world prohibited item detection, we collect a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. With an intensive amount of effort, our dataset contains categories of prohibited items in X-ray images with high-quality annotated segmentation masks and bounding boxes. To the best of our knowledge, it is the largest prohibited items detection dataset to date. Meanwhile, we design the selective dense attention network (SDANet) to construct a strong baseline, which consists of the dense attention module and the dependency refinement module. The dense attention module formed by the spatial and channel-wise dense attentions, is designed to learn the discriminative features to boost the performance. The dependency refinement module is used to exploit the dependencies of multi-scale features. Extensive experiments conducted on the collected PIDray dataset demonstrate that the proposed method performs favorably against the state-of-the-art methods, especially for detecting the deliberately hidden items. - **Language(s) (NLP):** en - **License:** apache-2.0 The images and the corresponding annotations in PIDray Dataset can be used ONLY for academic purposes, NOT for commercial purposes. Copyright © 2021 Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences All rights reserved. ### Dataset Sources - **Repository:** https://github.com/bywang2018/security-dataset - **Paper [optional]:** https://arxiv.org/abs/2108.07020 ## Uses This used for academic research on airport security screening machines and the detection of objects being scanned. ### Out-of-Scope Use Any non-academic work is out of scope and prohibited. ## Citation @inproceedings{wang2021towards, title={Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark}, author={Wang, Boying and Zhang, Libo and Wen, Longyin and Liu, Xianglong and Wu, Yanjun}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={5412--5421}, year={2021} }

wecover/OPUS_GlobalVoices

wecover

--- configs: - config_name: default data_files: - split: train path: '*/*/train.parquet' - split: valid path: '*/*/valid.parquet' - split: test path: '*/*/test.parquet' - config_name: am data_files: - split: train path: '*/*am*/train.parquet' - split: test path: '*/*am*/test.parquet' - split: valid path: '*/*am*/valid.parquet' - config_name: ar data_files: - split: train path: '*/*ar*/train.parquet' - split: test path: '*/*ar*/test.parquet' - split: valid path: '*/*ar*/valid.parquet' - config_name: bn data_files: - split: train path: '*/*bn*/train.parquet' - split: test path: '*/*bn*/test.parquet' - split: valid path: '*/*bn*/valid.parquet' - config_name: ca data_files: - split: train path: '*/*ca*/train.parquet' - split: test path: '*/*ca*/test.parquet' - split: valid path: '*/*ca*/valid.parquet' - config_name: de data_files: - split: train path: '*/*de*/train.parquet' - split: test path: '*/*de*/test.parquet' - split: valid path: '*/*de*/valid.parquet' - config_name: el data_files: - split: train path: '*/*el*/train.parquet' - split: test path: '*/*el*/test.parquet' - split: valid path: '*/*el*/valid.parquet' - config_name: en data_files: - split: train path: '*/*en*/train.parquet' - split: test path: '*/*en*/test.parquet' - split: valid path: '*/*en*/valid.parquet' - config_name: es data_files: - split: train path: '*/*es*/train.parquet' - split: test path: '*/*es*/test.parquet' - split: valid path: '*/*es*/valid.parquet' - config_name: fa data_files: - split: train path: '*/*fa*/train.parquet' - split: test path: '*/*fa*/test.parquet' - split: valid path: '*/*fa*/valid.parquet' - config_name: fr data_files: - split: train path: '*/*fr*/train.parquet' - split: test path: '*/*fr*/test.parquet' - split: valid path: '*/*fr*/valid.parquet' - config_name: hi data_files: - split: train path: '*/*hi*/train.parquet' - split: test path: '*/*hi*/test.parquet' - split: valid path: '*/*hi*/valid.parquet' - config_name: hu data_files: - split: train path: '*/*hu*/train.parquet' - split: test path: '*/*hu*/test.parquet' - split: valid path: '*/*hu*/valid.parquet' - config_name: id data_files: - split: train path: '*/*id*/train.parquet' - split: test path: '*/*id*/test.parquet' - split: valid path: '*/*id*/valid.parquet' - config_name: it data_files: - split: train path: '*/*it*/train.parquet' - split: test path: '*/*it*/test.parquet' - split: valid path: '*/*it*/valid.parquet' - config_name: mg data_files: - split: train path: '*/*mg*/train.parquet' - split: test path: '*/*mg*/test.parquet' - split: valid path: '*/*mg*/valid.parquet' - config_name: mk data_files: - split: train path: '*/*mk*/train.parquet' - split: test path: '*/*mk*/test.parquet' - split: valid path: '*/*mk*/valid.parquet' - config_name: my data_files: - split: train path: '*/*my*/train.parquet' - split: test path: '*/*my*/test.parquet' - split: valid path: '*/*my*/valid.parquet' - config_name: nl data_files: - split: train path: '*/*nl*/train.parquet' - split: test path: '*/*nl*/test.parquet' - split: valid path: '*/*nl*/valid.parquet' - config_name: pl data_files: - split: train path: '*/*pl*/train.parquet' - split: test path: '*/*pl*/test.parquet' - split: valid path: '*/*pl*/valid.parquet' - config_name: pt data_files: - split: train path: '*/*pt*/train.parquet' - split: test path: '*/*pt*/test.parquet' - split: valid path: '*/*pt*/valid.parquet' - config_name: ru data_files: - split: train path: '*/*ru*/train.parquet' - split: test path: '*/*ru*/test.parquet' - split: valid path: '*/*ru*/valid.parquet' - config_name: sr data_files: - split: train path: '*/*sr*/train.parquet' - split: test path: '*/*sr*/test.parquet' - split: valid path: '*/*sr*/valid.parquet' - config_name: sw data_files: - split: train path: '*/*sw*/train.parquet' - split: test path: '*/*sw*/test.parquet' - split: valid path: '*/*sw*/valid.parquet' - config_name: tr data_files: - split: train path: '*/*tr*/train.parquet' - split: test path: '*/*tr*/test.parquet' - split: valid path: '*/*tr*/valid.parquet' - config_name: ur data_files: - split: train path: '*/*ur*/train.parquet' - split: test path: '*/*ur*/test.parquet' - split: valid path: '*/*ur*/valid.parquet' - config_name: zhs data_files: - split: train path: '*/*zhs*/train.parquet' - split: test path: '*/*zhs*/test.parquet' - split: valid path: '*/*zhs*/valid.parquet' - config_name: zht data_files: - split: train path: '*/*zht*/train.parquet' - split: test path: '*/*zht*/test.parquet' - split: valid path: '*/*zht*/valid.parquet' - config_name: bg data_files: - split: train path: '*/*bg*/train.parquet' - split: test path: '*/*bg*/test.parquet' - split: valid path: '*/*bg*/valid.parquet' - config_name: cs data_files: - split: train path: '*/*cs*/train.parquet' - split: test path: '*/*cs*/test.parquet' - split: valid path: '*/*cs*/valid.parquet' - config_name: da data_files: - split: train path: '*/*da*/train.parquet' - split: test path: '*/*da*/test.parquet' - split: valid path: '*/*da*/valid.parquet' - config_name: eo data_files: - split: train path: '*/*eo*/train.parquet' - split: test path: '*/*eo*/test.parquet' - split: valid path: '*/*eo*/valid.parquet' - config_name: he data_files: - split: train path: '*/*he*/train.parquet' - split: test path: '*/*he*/test.parquet' - split: valid path: '*/*he*/valid.parquet' - config_name: km data_files: - split: train path: '*/*km*/train.parquet' - split: test path: '*/*km*/test.parquet' - split: valid path: '*/*km*/valid.parquet' - config_name: ko data_files: - split: train path: '*/*ko*/train.parquet' - split: test path: '*/*ko*/test.parquet' - split: valid path: '*/*ko*/valid.parquet' - config_name: ku data_files: - split: train path: '*/*ku*/train.parquet' - split: test path: '*/*ku*/test.parquet' - split: valid path: '*/*ku*/valid.parquet' - config_name: ne data_files: - split: train path: '*/*ne*/train.parquet' - split: test path: '*/*ne*/test.parquet' - split: valid path: '*/*ne*/valid.parquet' - config_name: or data_files: - split: train path: '*/*or*/train.parquet' - split: test path: '*/*or*/test.parquet' - split: valid path: '*/*or*/valid.parquet' - config_name: pa data_files: - split: train path: '*/*pa*/train.parquet' - split: test path: '*/*pa*/test.parquet' - split: valid path: '*/*pa*/valid.parquet' - config_name: ro data_files: - split: train path: '*/*ro*/train.parquet' - split: test path: '*/*ro*/test.parquet' - split: valid path: '*/*ro*/valid.parquet' - config_name: sq data_files: - split: train path: '*/*sq*/train.parquet' - split: test path: '*/*sq*/test.parquet' - split: valid path: '*/*sq*/valid.parquet' - config_name: sv data_files: - split: train path: '*/*sv*/train.parquet' - split: test path: '*/*sv*/test.parquet' - split: valid path: '*/*sv*/valid.parquet' language: - am - ar - bg - bn - ca - cs - da - de - el - en - eo - es - fa - fr - he - hi - hu - id - it - km - ko - ku - mg - mk - my - ne - nl - or - pa - pt - pl - ro - ru - sq - sr - sv - sw - tr - ur - zh ---

Hemabhushan/capstone_sakuga_preproc_optical_flow

Hemabhushan

--- dataset_info: - config_name: sample_subset features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 30244617541 num_examples: 2396 download_size: 5461228507 dataset_size: 30244617541 - config_name: seg1_part1 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482846975 num_examples: 2498 download_size: 5683747736 dataset_size: 31482846975 - config_name: seg1_part10 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533368384 num_examples: 2498 download_size: 5651523132 dataset_size: 31533368384 - config_name: seg1_part11 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31495470684 num_examples: 2498 download_size: 5646719194 dataset_size: 31495470684 - config_name: seg1_part12 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533346986 num_examples: 2498 download_size: 5705163694 dataset_size: 31533346986 - config_name: seg1_part14 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31432281831 num_examples: 2498 download_size: 5627562296 dataset_size: 31432281831 - config_name: seg1_part15 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508092434 num_examples: 2498 download_size: 5647225033 dataset_size: 31508092434 - config_name: seg1_part18 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482843486 num_examples: 2498 download_size: 5703102313 dataset_size: 31482843486 - config_name: seg1_part2 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31457575891 num_examples: 2498 download_size: 5650519682 dataset_size: 31457575891 - config_name: seg1_part20 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31470181418 num_examples: 2498 download_size: 5625192608 dataset_size: 31470181418 - config_name: seg1_part21 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508103461 num_examples: 2498 download_size: 5680819286 dataset_size: 31508103461 - config_name: seg1_part24 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31520754590 num_examples: 2498 download_size: 5697959164 dataset_size: 31520754590 - config_name: seg1_part25 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482806663 num_examples: 2498 download_size: 5628329196 dataset_size: 31482806663 - config_name: seg1_part26 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533316255 num_examples: 2498 download_size: 5662161621 dataset_size: 31533316255 - config_name: seg1_part27 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533349249 num_examples: 2498 download_size: 5654417461 dataset_size: 31533349249 - config_name: seg1_part28 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533349763 num_examples: 2498 download_size: 5644209592 dataset_size: 31533349763 - config_name: seg1_part29 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508101677 num_examples: 2498 download_size: 5725512822 dataset_size: 31508101677 - config_name: seg1_part30 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31520696316 num_examples: 2498 download_size: 5649748978 dataset_size: 31520696316 - config_name: seg1_part31 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31470211581 num_examples: 2498 download_size: 5691521624 dataset_size: 31470211581 - config_name: seg1_part32 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31520703122 num_examples: 2498 download_size: 5611392470 dataset_size: 31520703122 - config_name: seg1_part33 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533395644 num_examples: 2498 download_size: 5765660331 dataset_size: 31533395644 - config_name: seg1_part34 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482802747 num_examples: 2498 download_size: 5654024836 dataset_size: 31482802747 - config_name: seg1_part35 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508072238 num_examples: 2498 download_size: 5632935439 dataset_size: 31508072238 - config_name: seg1_part36 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508118773 num_examples: 2498 download_size: 5708713170 dataset_size: 31508118773 - config_name: seg1_part39 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508101149 num_examples: 2498 download_size: 5697274819 dataset_size: 31508101149 - config_name: seg1_part4 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482829874 num_examples: 2498 download_size: 5700440041 dataset_size: 31482829874 - config_name: seg1_part40 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31508069004 num_examples: 2498 download_size: 5640935450 dataset_size: 31508069004 - config_name: seg1_part41 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31558603213 num_examples: 2498 download_size: 5713447755 dataset_size: 31558603213 - config_name: seg1_part42 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31482828955 num_examples: 2498 download_size: 5640954061 dataset_size: 31482828955 - config_name: seg1_part43 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31520704278 num_examples: 2498 download_size: 5736520090 dataset_size: 31520704278 - config_name: seg1_part44 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31166950691 num_examples: 2471 download_size: 5640666013 dataset_size: 31166950691 - config_name: seg1_part45 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' splits: - name: train num_bytes: 0 num_examples: 0 download_size: 6857 dataset_size: 0 - config_name: seg1_part6 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31545984682 num_examples: 2498 download_size: 5674259234 dataset_size: 31545984682 - config_name: seg1_part8 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31545987289 num_examples: 2498 download_size: 5733443343 dataset_size: 31545987289 - config_name: seg1_part9 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: word_count dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: frames dtype: 'null' - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31533382844 num_examples: 2498 download_size: 5634081955 dataset_size: 31533382844 - config_name: seg2_part1 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: prev_conv list: - name: content list: - name: text dtype: string - name: type dtype: string - name: role dtype: string - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31284870750 num_examples: 2498 download_size: 6023339313 dataset_size: 31284870750 - config_name: seg2_part3 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: prev_conv list: - name: content list: - name: text dtype: string - name: type dtype: string - name: role dtype: string - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31297486132 num_examples: 2498 download_size: 6033401989 dataset_size: 31297486132 - config_name: seg2_part4 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: prev_conv list: - name: content list: - name: text dtype: string - name: type dtype: string - name: role dtype: string - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31209057858 num_examples: 2498 download_size: 6033150218 dataset_size: 31209057858 - config_name: seg2_part7 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: prev_conv list: - name: content list: - name: text dtype: string - name: type dtype: string - name: role dtype: string - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31310131354 num_examples: 2498 download_size: 6026279130 dataset_size: 31310131354 - config_name: seg3_part1 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31091165546 num_examples: 2498 download_size: 6013722850 dataset_size: 31091165546 - config_name: seg3_part3 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 30964835031 num_examples: 2498 download_size: 5981318118 dataset_size: 30964835031 - config_name: seg3_part4 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31141675653 num_examples: 2498 download_size: 6035418048 dataset_size: 31141675653 - config_name: seg3_part7 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31230125953 num_examples: 2498 download_size: 6080001698 dataset_size: 31230125953 - config_name: seg4_part1 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31230126642 num_examples: 2498 download_size: 6074698944 dataset_size: 31230126642 - config_name: seg4_part3 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31040618574 num_examples: 2498 download_size: 5968129650 dataset_size: 31040618574 - config_name: seg4_part5 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31015355157 num_examples: 2498 download_size: 6027043124 dataset_size: 31015355157 - config_name: seg4_part6 features: - name: identifier dtype: string - name: hash_identifier dtype: string - name: url_link dtype: string - name: scene_start_time dtype: string - name: scene_end_time dtype: string - name: frame_number dtype: float64 - name: key_frame_number dtype: float64 - name: anime_tags dtype: string - name: user_tags dtype: string - name: text_description dtype: string - name: aesthetic_score dtype: float64 - name: dynamic_score dtype: float64 - name: rating dtype: string - name: text_prob dtype: float64 - name: width dtype: int64 - name: height dtype: int64 - name: file_ext dtype: string - name: fps dtype: float64 - name: Taxonomy_Time dtype: string - name: Taxonomy_Venue dtype: string - name: Taxonomy_Media dtype: string - name: Taxonomy_Filming dtype: string - name: Taxonomy_Composition dtype: string - name: Taxonomy_Character dtype: string - name: __index_level_0__ dtype: int64 - name: video_id dtype: string - name: video_segment_no dtype: int64 - name: word_count dtype: int64 - name: video_frames sequence: sequence: sequence: sequence: float32 splits: - name: train num_bytes: 31116405163 num_examples: 2498 download_size: 6079250810 dataset_size: 31116405163 configs: - config_name: sample_subset data_files: - split: train path: sample_subset/train-* - config_name: seg1_part1 data_files: - split: train path: seg1_part1/train-* - config_name: seg1_part10 data_files: - split: train path: seg1_part10/train-* - config_name: seg1_part11 data_files: - split: train path: seg1_part11/train-* - config_name: seg1_part12 data_files: - split: train path: seg1_part12/train-* - config_name: seg1_part14 data_files: - split: train path: seg1_part14/train-* - config_name: seg1_part15 data_files: - split: train path: seg1_part15/train-* - config_name: seg1_part18 data_files: - split: train path: seg1_part18/train-* - config_name: seg1_part2 data_files: - split: train path: seg1_part2/train-* - config_name: seg1_part20 data_files: - split: train path: seg1_part20/train-* - config_name: seg1_part21 data_files: - split: train path: seg1_part21/train-* - config_name: seg1_part24 data_files: - split: train path: seg1_part24/train-* - config_name: seg1_part25 data_files: - split: train path: seg1_part25/train-* - config_name: seg1_part26 data_files: - split: train path: seg1_part26/train-* - config_name: seg1_part27 data_files: - split: train path: seg1_part27/train-* - config_name: seg1_part28 data_files: - split: train path: seg1_part28/train-* - config_name: seg1_part29 data_files: - split: train path: seg1_part29/train-* - config_name: seg1_part30 data_files: - split: train path: seg1_part30/train-* - config_name: seg1_part31 data_files: - split: train path: seg1_part31/train-* - config_name: seg1_part32 data_files: - split: train path: seg1_part32/train-* - config_name: seg1_part33 data_files: - split: train path: seg1_part33/train-* - config_name: seg1_part34 data_files: - split: train path: seg1_part34/train-* - config_name: seg1_part35 data_files: - split: train path: seg1_part35/train-* - config_name: seg1_part36 data_files: - split: train path: seg1_part36/train-* - config_name: seg1_part39 data_files: - split: train path: seg1_part39/train-* - config_name: seg1_part4 data_files: - split: train path: seg1_part4/train-* - config_name: seg1_part40 data_files: - split: train path: seg1_part40/train-* - config_name: seg1_part41 data_files: - split: train path: seg1_part41/train-* - config_name: seg1_part42 data_files: - split: train path: seg1_part42/train-* - config_name: seg1_part43 data_files: - split: train path: seg1_part43/train-* - config_name: seg1_part44 data_files: - split: train path: seg1_part44/train-* - config_name: seg1_part45 data_files: - split: train path: seg1_part45/train-* - config_name: seg1_part6 data_files: - split: train path: seg1_part6/train-* - config_name: seg1_part8 data_files: - split: train path: seg1_part8/train-* - config_name: seg1_part9 data_files: - split: train path: seg1_part9/train-* - config_name: seg2_part1 data_files: - split: train path: seg2_part1/train-* - config_name: seg2_part3 data_files: - split: train path: seg2_part3/train-* - config_name: seg2_part4 data_files: - split: train path: seg2_part4/train-* - config_name: seg2_part7 data_files: - split: train path: seg2_part7/train-* - config_name: seg3_part1 data_files: - split: train path: seg3_part1/train-* - config_name: seg3_part3 data_files: - split: train path: seg3_part3/train-* - config_name: seg3_part4 data_files: - split: train path: seg3_part4/train-* - config_name: seg3_part7 data_files: - split: train path: seg3_part7/train-* - config_name: seg4_part1 data_files: - split: train path: seg4_part1/train-* - config_name: seg4_part3 data_files: - split: train path: seg4_part3/train-* - config_name: seg4_part5 data_files: - split: train path: seg4_part5/train-* - config_name: seg4_part6 data_files: - split: train path: seg4_part6/train-* ---

sailor2/sea-synthetic

sailor2

--- license: apache-2.0 ---

MLCommons/peoples_speech

MLCommons

--- annotations_creators: - crowdsourced - machine-generated language_creators: - crowdsourced - machine-generated language: - en license: - cc-by-2.0 - cc-by-2.5 - cc-by-3.0 - cc-by-4.0 - cc-by-sa-3.0 - cc-by-sa-4.0 multilinguality: - monolingual size_categories: - 1T<n source_datasets: - original task_categories: - automatic-speech-recognition task_ids: [] pretty_name: People's Speech tags: - robust-speech-recognition - noisy-speech-recognition - speech-recognition dataset_info: - config_name: clean features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 401733771186.124 num_examples: 1501271 - name: validation num_bytes: 2459781412.24 num_examples: 18622 - name: test num_bytes: 4324307722.96 num_examples: 34898 download_size: 398550700437 dataset_size: 408517860321.32404 - config_name: clean_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 75267509124.558 num_examples: 257093 - name: validation num_bytes: 2075929254.254 num_examples: 18622 - name: test num_bytes: 3894954757.41 num_examples: 34898 download_size: 72518549222 dataset_size: 81238393136.222 - config_name: dirty features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 1569500875399.994 num_examples: 5476898 - name: validation num_bytes: 2641406179.2539997 num_examples: 18622 - name: test num_bytes: 5097236056.41 num_examples: 34898 download_size: 1496747948260 dataset_size: 1577239517635.6577 - config_name: dirty_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 163776914241.91 num_examples: 548014 - name: validation num_bytes: 2075929254.254 num_examples: 18622 - name: test num_bytes: 3894954757.41 num_examples: 34898 download_size: 149326092074 dataset_size: 169747798253.574 - config_name: microset features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 92397066.0 num_examples: 336 download_size: 90204303 dataset_size: 92397066.0 - config_name: test features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3894954757.41 num_examples: 34898 download_size: 4087772459 dataset_size: 3894954757.41 - config_name: validation features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 2075929254.254 num_examples: 18622 download_size: 2335244149 dataset_size: 2075929254.254 configs: - config_name: clean data_files: - split: train path: clean/train-* - split: validation path: clean/validation-* - split: test path: clean/test-* - config_name: clean_sa data_files: - split: train path: clean_sa/train-* - split: validation path: clean_sa/validation-* - split: test path: clean_sa/test-* - config_name: dirty data_files: - split: train path: dirty/train-* - split: validation path: dirty/validation-* - split: test path: dirty/test-* - config_name: dirty_sa data_files: - split: train path: dirty_sa/train-* - split: validation path: dirty_sa/validation-* - split: test path: dirty_sa/test-* - config_name: microset data_files: - split: train path: microset/train-* - config_name: test data_files: - split: test path: test/test-* - config_name: validation data_files: - split: validation path: validation/validation-* --- # Dataset Card for People's Speech ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-instances) - [Data Splits](#data-instances) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) ## Dataset Description - **Homepage:** https://mlcommons.org/en/peoples-speech/ - **Repository:** https://github.com/mlcommons/peoples-speech - **Paper:** https://arxiv.org/abs/2111.09344 - **Leaderboard:** [Needs More Information] - **Point of Contact:** [[email protected]](mailto:[email protected]) ### Dataset Summary The People's Speech Dataset is among the world's largest English speech recognition corpus today that is licensed for academic and commercial usage under CC-BY-SA and CC-BY 4.0. It includes 30,000+ hours of transcribed speech in English languages with a diverse set of speakers. This open dataset is large enough to train speech-to-text systems and crucially is available with a permissive license. ### Supported Tasks and Leaderboards [Needs More Information] ### Languages English ## Dataset Structure ### Data Instances { "id": "gov_DOT_uscourts_DOT_scotus_DOT_19-161/gov_DOT_uscourts_DOT_scotus_DOT_19-161_DOT_2020-03-02_DOT_mp3_00002.flac", "audio": { "path": "gov_DOT_uscourts_DOT_scotus_DOT_19-161/gov_DOT_uscourts_DOT_scotus_DOT_19-161_DOT_2020-03-02_DOT_mp3_00002.flac" "array": array([-6.10351562e-05, ...]), "sampling_rate": 16000 } "duration_ms": 14490, "text": "contends that the suspension clause requires a [...]" } ### Data Fields { "id": datasets.Value("string"), "audio": datasets.Audio(sampling_rate=16_000), "duration_ms": datasets.Value("int32"), "text": datasets.Value("string"), } ### Data Splits We provide the following configurations for the dataset: `cc-by-clean` (`"clean"`), `cc-by-dirty` (`"dirty"`), `cc-by-sa-clean` (`"clean_sa"`), `cc-by-sa-dirty` (`"dirty_sa"`), and `microset` (`"microset"`). We also provide validation and test configurations, which are not only available as standalone configurations but are also included as validation and test splits within each of the above configurations for ease of use. Specifically: - Setting `data_dir="validation"` and `split="validation"` corresponds to the validation split of any of the configurations: `"clean"`, `"clean_sa"`, `"dirty"`, or `"dirty_sa"`. - Similarly, setting `data_dir="test"` and `split="test"` corresponds to the test split of these configurations. ``` ├── clean │ ├── train │ ├── validation │ └── test ├── clean_sa │ ├── train │ ├── validation │ └── test ├── dirty │ ├── train │ ├── validation │ └── test ├── dirty_sa │ ├── train │ ├── validation │ └── test ├── microset │ └── train ├── validation │ └── validation └── test └── test ``` ## Dataset Creation ### Curation Rationale See our [paper](https://arxiv.org/abs/2111.09344). ### Source Data #### Initial Data Collection and Normalization Data was downloaded via the archive.org API. No data inference was done. #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process No manual annotation is done. We download only source audio with already existing transcripts. #### Who are the annotators? For the test and dev sets, we paid native American English speakers to do transcriptions. We do not know the identities of the transcriptionists for data in the training set. For the training set, we have noticed that some transcriptions are likely to be the output of automatic speech recognition systems. ### Personal and Sensitive Information Several of our sources are legal and government proceedings, spoken histories, speeches, and so on. Given that these were intended as public documents and licensed as such, it is natural that the involved individuals are aware of this. ## Considerations for Using the Data ### Social Impact of Dataset The dataset could be used for speech synthesis. However, this requires careful cleaning of the dataset, as background noise is not tolerable for speech synthesis. The dataset could be used for keyword spotting tasks as well. In particular, this is good use case for the non-English audio in the dataset. Our sincere hope is that the large breadth of sources our dataset incorporates reduces existing quality of service issues today, like speech recognition system’s poor understanding of non-native English accents. We cannot think of any unfair treatment that come from using this dataset at this time. ### Discussion of Biases Our data is downloaded from archive.org. As such, the data is biased towards whatever users decide to upload there. Almost all of our data is American accented English. ### Other Known Limitations As of version 1.0, a portion of data in the training, test, and dev sets is poorly aligned. Specifically, some words appear in the transcript, but not the audio, or some words appear in the audio, but not the transcript. We are working on it. ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information We provide CC-BY and CC-BY-SA subsets of the dataset. ### Citation Information Please cite: ``` @article{DBLP:journals/corr/abs-2111-09344, author = {Daniel Galvez and Greg Diamos and Juan Ciro and Juan Felipe Cer{\'{o}}n and Keith Achorn and Anjali Gopi and David Kanter and Maximilian Lam and Mark Mazumder and Vijay Janapa Reddi}, title = {The People's Speech: {A} Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage}, journal = {CoRR}, volume = {abs/2111.09344}, year = {2021}, url = {https://arxiv.org/abs/2111.09344}, eprinttype = {arXiv}, eprint = {2111.09344}, timestamp = {Mon, 22 Nov 2021 16:44:07 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-09344.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

HuggingFaceGECLM/REDDIT_comments

HuggingFaceGECLM

--- dataset_info: features: - name: archived dtype: string - name: author dtype: string - name: author_fullname dtype: string - name: body dtype: string - name: comment_type dtype: string - name: controversiality dtype: string - name: created_utc dtype: string - name: edited dtype: string - name: gilded dtype: string - name: id dtype: string - name: link_id dtype: string - name: locked dtype: string - name: name dtype: string - name: parent_id dtype: string - name: permalink dtype: string - name: retrieved_on dtype: string - name: score dtype: string - name: subreddit_id dtype: string - name: subreddit_name_prefixed dtype: string - name: subreddit_type dtype: string - name: total_awards_received dtype: string splits: - name: programming num_bytes: 3466623746 num_examples: 7503347 - name: tifu num_bytes: 4761338653 num_examples: 12738669 - name: explainlikeimfive num_bytes: 8451732573 num_examples: 16392814 - name: WritingPrompts num_bytes: 4651591771 num_examples: 4436210 - name: changemyview num_bytes: 8603031915 num_examples: 11600073 - name: LifeProTips num_bytes: 5272994396 num_examples: 12829459 - name: todayilearned num_bytes: 22655655241 num_examples: 60199778 - name: science num_bytes: 7069809765 num_examples: 18112884 - name: askscience num_bytes: 3144754665 num_examples: 6286702 - name: ifyoulikeblank num_bytes: 547200329 num_examples: 1332211 - name: Foodforthought num_bytes: 308377128 num_examples: 567900 - name: IWantToLearn num_bytes: 408331672 num_examples: 745543 - name: bestof num_bytes: 2003718831 num_examples: 4347522 - name: IAmA num_bytes: 9380094090 num_examples: 25778822 - name: socialskills num_bytes: 1000014402 num_examples: 1842733 - name: relationship_advice num_bytes: 22298879735 num_examples: 38937398 - name: philosophy num_bytes: 1494947876 num_examples: 2391695 - name: YouShouldKnow num_bytes: 1165617658 num_examples: 2639265 - name: history num_bytes: 1457852402 num_examples: 2962043 - name: books num_bytes: 4562689426 num_examples: 10187495 - name: Showerthoughts num_bytes: 13259109532 num_examples: 34123213 - name: personalfinance num_bytes: 9484869588 num_examples: 18361314 - name: buildapc num_bytes: 9801044390 num_examples: 21761801 - name: EatCheapAndHealthy num_bytes: 853462012 num_examples: 1821897 - name: boardgames num_bytes: 3131627378 num_examples: 6328926 - name: malefashionadvice num_bytes: 2928017882 num_examples: 7712258 - name: femalefashionadvice num_bytes: 1619784736 num_examples: 3262969 - name: scifi num_bytes: 888152056 num_examples: 2193741 - name: Fantasy num_bytes: 2285934538 num_examples: 4566639 - name: Games num_bytes: 10396813188 num_examples: 23373965 - name: bodyweightfitness num_bytes: 794549854 num_examples: 1613634 - name: SkincareAddiction num_bytes: 3421122597 num_examples: 5660550 - name: podcasts num_bytes: 464773126 num_examples: 943266 - name: suggestmeabook num_bytes: 1842944304 num_examples: 3492937 - name: AskHistorians num_bytes: 2244587909 num_examples: 2714353 - name: gaming num_bytes: 28374513722 num_examples: 85729253 - name: DIY num_bytes: 2113533684 num_examples: 4489265 - name: sports num_bytes: 2230129132 num_examples: 6470079 - name: space num_bytes: 3081499208 num_examples: 7896182 - name: gadgets num_bytes: 1683252868 num_examples: 4104833 - name: Documentaries num_bytes: 1852644771 num_examples: 4051474 - name: GetMotivated num_bytes: 1211761267 num_examples: 3221980 - name: UpliftingNews num_bytes: 2003149025 num_examples: 4741948 - name: technology num_bytes: 10826871436 num_examples: 25404699 - name: Fitness num_bytes: 6191132755 num_examples: 14319856 - name: travel num_bytes: 1740556350 num_examples: 3806755 - name: lifehacks num_bytes: 626791812 num_examples: 1799437 - name: Damnthatsinteresting num_bytes: 6376694618 num_examples: 15643554 - name: gardening num_bytes: 1825313940 num_examples: 4568468 - name: mildlyinteresting num_bytes: 9079894206 num_examples: 26436769 download_size: 109177016105 dataset_size: 255339788158 annotations_creators: - no-annotation language: - en language_creators: - found license: [] multilinguality: - monolingual pretty_name: Reddit comments size_categories: - 10B<n<100B source_datasets: [] tags: - reddit - social-media task_categories: - text-generation task_ids: - dialogue-modeling - language-modeling --- # Dataset Card for "REDDIT_comments" ## Dataset Description - **Homepage:** - **Paper: https://arxiv.org/abs/2001.08435** ### Dataset Summary Comments of 50 high-quality subreddits, extracted from the REDDIT PushShift data dumps (from 2006 to Jan 2023). ### Supported Tasks These comments can be used for text generation and language modeling, as well as dialogue modeling. ## Dataset Structure ### Data Splits Each split corresponds to a specific subreddit in the following list: "tifu", "explainlikeimfive", "WritingPrompts", "changemyview", "LifeProTips", "todayilearned", "science", "askscience", "ifyoulikeblank", "Foodforthought", "IWantToLearn", "bestof", "IAmA", "socialskills", "relationship_advice", "philosophy", "YouShouldKnow", "history", "books", "Showerthoughts", "personalfinance", "buildapc", "EatCheapAndHealthy", "boardgames", "malefashionadvice", "femalefashionadvice", "scifi", "Fantasy", "Games", "bodyweightfitness", "SkincareAddiction", "podcasts", "suggestmeabook", "AskHistorians", "gaming", "DIY", "mildlyinteresting", "sports", "space", "gadgets", "Documentaries", "GetMotivated", "UpliftingNews", "technology", "Fitness", "travel", "lifehacks", "Damnthatsinteresting", "gardening", "programming" ## Dataset Creation ### Curation Rationale All the information fields have been cast to string, as their format change through time from one dump to the following. A reduced number of keys have been kept: "archived", "author", "author_fullname", "body", "comment_type", "controversiality", "created_utc", "edited", "gilded", "id", "link_id", "locked", "name", "parent_id", "permalink", "retrieved_on", "score", "subreddit", "subreddit_id", "subreddit_name_prefixed", "subreddit_type", "total_awards_received". ### Source Data The [Reddit PushShift data dumps](https://files.pushshift.io/reddit/) are part of a data collection effort which crawls Reddit at regular intervals, to extract and keep all its data. #### Initial Data Collection and Normalization See the paper. #### Who are the source language producers? Redditors are mostly young (65% below 30), male (70%), and American (50% of the site). ### Personal and Sensitive Information The data contains Redditor's usernames associated to their content. ## Considerations for Using the Data This dataset should be anonymized before any processing. Though the subreddits selected are considered as being of higher quality, they can still reflect what you can find on the internet in terms of expressions of biases and toxicity. ### Contributions Thanks to [@clefourrier](https://github.com/clefourrier) for adding this dataset.

tttarun/captcha_store

tttarun

--- license: mit ---

hoskinson-center/proof-pile

hoskinson-center

--- annotations_creators: - no-annotation language: - en language_creators: - found license: [apache-2.0] multilinguality: - monolingual pretty_name: proof-pile size_categories: [] source_datasets: [] tags: - math - mathematics - formal-mathematics task_categories: - text-generation task_ids: - language-modeling --- # Dataset Description The `proof-pile` is a 13GB pre-training dataset of mathematical text that comprises 8.3 billion tokens (using the `gpt-neox` tokenizer). Models trained on this dataset are coming soon :) The dataset is composed of diverse sources of both informal and formal mathematics, namely - ArXiv.math (10GB) - Open-source math textbooks (50MB) - Formal mathematics libraries (500MB) - Lean mathlib and other Lean repositories - Isabelle AFP - Coq mathematical components and other Coq repositories - HOL Light - set.mm - Mizar Mathematical Library - Math Overflow and Math Stack Exchange (2.5GB) - Wiki-style sources (50MB) - ProofWiki - Wikipedia math articles - MATH dataset (6MB) The construction of the dataset is reproducible using the code and instructions in the [proof-pile Github repo](https://github.com/zhangir-azerbayev/proof-pile). # Supported Tasks This dataset is intended to be used for pre-training and fine-tuning language models. We envision models trained on the `proof-pile` will have many downstream applications, including informal quantitative reasoning, formal theorem proving, semantic search for formal mathematics, and autoformalization. # Languages All informal mathematics in the `proof-pile` is written in English and LaTeX (arXiv articles in other languages are filtered out using [languagedetect](https://github.com/shuyo/language-detection/blob/wiki/ProjectHome.md)). Formal theorem proving languages represented in this dataset are Lean 3, Isabelle, Coq, HOL Light, Metamath, and Mizar. # Evaluation The version of `set.mm` in this dataset has 10% of proofs replaced with the `?` character in order to preserve a validation and test set for Metamath provers pre-trained on the `proof-pile`. The precise split can be found here: [validation](https://github.com/zhangir-azerbayev/mm-extract/blob/main/valid_decls.json) and [test](https://github.com/zhangir-azerbayev/mm-extract/blob/main/test_decls.json). The Lean mathlib commit used in this dataset is `6313863`. Theorems created in subsequent commits can be used for evaluating Lean theorem provers. This dataset contains only the training set of the [MATH dataset](https://github.com/hendrycks/math). However, because this dataset contains ProofWiki, the Stacks Project, Trench's Analysis, and Stein's Number Theory, models trained on it cannot be evaluated on the [NaturalProofs dataset](https://github.com/wellecks/naturalproofs). # Data Preprocessing This section describes any significant filtering and transformations made to various subsets of the data. **arXiv.math.** The arXiv.math dataset is large, heterogeneous, and contains a great deal of noise. We used the following heuristics when choosing which files from arXiv.math source folders to include in the dataset: - Keep only files with a `.tex` extension. - Only include files that use either a `utf-8/16/32` or `latin-1` text encoding. - Discard files that do not contain a part, chapter, section, sub...section, paragraph, or subparagraph heading. - Delete files that contain the keyword `gnuplot`. Gnuplot-latex is an old command line utility that generates blocks of entirely unintelligible source. - Include only articles in English, as determined by the [langdetect library](https://pypi.org/project/langdetect/). \n", "\n", - Exclude files shorter than 280 characters (characters counted after substring removal described below). In addition, we apply the following transformations to arXiv.math texts: - Delete everything outside of `\begin{document}` and `\end{document}`. - Delete everything including or after `\Refs`, `\begin{thebibliography}`, or `\begin{bibdiv}` - Delete comments. - Any more than three consecutive newlines are replaced by three consecutive newlines. In [this notebook](https://github.com/zhangir-azerbayev/proof-pile/blob/main/analysis/arxiv_noisedetection.ipynb), we provide an analysis of the prevalence of noisy documents in the arXiv.math subset of the proof-pile. **Stack Exchange.** We only include questions that have at least 5 upvotes and an answer. We format Stack Exchange posts as follows ``` QUESTION [{num_upvotes} upvotes]: {text of question} REPLY [{num_upvotes} votes]: {text of reply} REPLY [{num_upvotes} votes]: {text of reply} . . . ``` **set.mm.** We converted `set.mm` into human-readable form by following the instructions in the [mm-extract repo](https://github.com/zhangir-azerbayev/mm-extract) ## Contributions Authors: Zhangir Azerbayev, Edward Ayers, Bartosz Piotrowski. We would like to thank Jeremy Avigad, Albert Jiang, and Wenda Li for their invaluable guidance, and the Hoskinson Center for Formal Mathematics for its support.

lmms-lab/LLaVA-OneVision-Data

lmms-lab

--- language: - en - zh license: apache-2.0 pretty_name: llava-onevision-data dataset_info: - config_name: CLEVR-Math(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 791346970 num_examples: 5280 download_size: 441208499 dataset_size: 791346970 - config_name: FigureQA(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 463326576.625 num_examples: 17587 download_size: 258197193 dataset_size: 463326576.625 - config_name: GEOS(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1503641 num_examples: 498 download_size: 684471 dataset_size: 1503641 - config_name: GeoQA+(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 53579705.75 num_examples: 17162 download_size: 33480538 dataset_size: 53579705.75 - config_name: Geometry3K(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 218085473.5 num_examples: 9724 download_size: 125914780 dataset_size: 218085473.5 - config_name: IconQA(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 208430568.375 num_examples: 22589 download_size: 117222488 dataset_size: 208430568.375 - config_name: MapQA(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 384120915.875 num_examples: 5225 download_size: 215768443 dataset_size: 384120915.875 - config_name: PMC-VQA(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 571444866.5 num_examples: 35948 download_size: 326541003 dataset_size: 571444866.5 - config_name: Super-CLEVR(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2795082410.75 num_examples: 8642 download_size: 1580301917 dataset_size: 2795082410.75 - config_name: TabMWP(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 307726997.5 num_examples: 22452 download_size: 173938487 dataset_size: 307726997.5 - config_name: UniGeo(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 38296693.375 num_examples: 11949 download_size: 24170743 dataset_size: 38296693.375 - config_name: VisualWebInstruct(filtered) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 36317112275.0 num_examples: 263584 download_size: 36239916454 dataset_size: 36317112275.0 - config_name: VizWiz(MathV360K) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1170333936.5 num_examples: 6604 download_size: 660752297 dataset_size: 1170333936.5 - config_name: ai2d(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 438572782.375 num_examples: 2429 download_size: 437348514 dataset_size: 438572782.375 - config_name: ai2d(gpt4v) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 866076731 num_examples: 4864 download_size: 860306578 dataset_size: 866076731 - config_name: ai2d(internvl) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1832787249.625 num_examples: 12403 download_size: 527493895 dataset_size: 1832787249.625 - config_name: allava_instruct_laion4v features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 5981767621.25 num_examples: 49990 download_size: 5873046236 dataset_size: 5981767621.25 - config_name: allava_instruct_vflan4v features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2680974558.25 num_examples: 19990 download_size: 2670088751 dataset_size: 2680974558.25 - config_name: aokvqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 6896420844.25 num_examples: 16534 download_size: 6894236970 dataset_size: 6896420844.25 - config_name: chart2text(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1145458729.5 num_examples: 26956 download_size: 1123681047 dataset_size: 1145458729.5 - config_name: chartqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 815335215.5 num_examples: 18260 download_size: 803084541 dataset_size: 815335215.5 - config_name: chrome_writting features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 44422597.875 num_examples: 8825 download_size: 39611257 dataset_size: 44422597.875 - config_name: clevr(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 10528974543.625 num_examples: 69995 download_size: 10460536445 dataset_size: 10528974543.625 - config_name: diagram_image_to_text(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 18858266 num_examples: 295 download_size: 18659115 dataset_size: 18858266 - config_name: dvqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 4487270615.625 num_examples: 199995 download_size: 4277056467 dataset_size: 4487270615.625 - config_name: figureqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2351194509.625 num_examples: 99995 download_size: 2222640639 dataset_size: 2351194509.625 - config_name: geo170k(align) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 204236256.75 num_examples: 60242 download_size: 58185410 dataset_size: 204236256.75 - config_name: geo170k(qa) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 266040519.125 num_examples: 67823 download_size: 160022430 dataset_size: 266040519.125 - config_name: geo3k features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 42634333.625 num_examples: 2091 download_size: 41097851 dataset_size: 42634333.625 - config_name: geomverse(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2263893609.75 num_examples: 9298 download_size: 2211726352 dataset_size: 2263893609.75 - config_name: hateful_memes(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 3057252325.125 num_examples: 8495 download_size: 3055839880 dataset_size: 3057252325.125 - config_name: hitab(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 161706881.125 num_examples: 2495 download_size: 157871287 dataset_size: 161706881.125 - config_name: hme100k features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 273229915.5 num_examples: 74492 download_size: 241005430 dataset_size: 273229915.5 - config_name: iam(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1131633206.75 num_examples: 5658 download_size: 1128371221 dataset_size: 1131633206.75 - config_name: iconqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 331284932.25 num_examples: 27302 download_size: 327005220 dataset_size: 331284932.25 - config_name: iiit5k features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 21821437.25 num_examples: 1990 download_size: 21623116 dataset_size: 21821437.25 - config_name: image_textualization(filtered) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 5218283253.375 num_examples: 99573 download_size: 5164176816 dataset_size: 5218283253.375 - config_name: infographic(gpt4v) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 713657496.25 num_examples: 1982 download_size: 656276080 dataset_size: 713657496.25 - config_name: infographic_vqa features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1528953078.75 num_examples: 4394 download_size: 1419340319 dataset_size: 1528953078.75 - config_name: infographic_vqa_llava_format features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1765315696.875 num_examples: 2113 download_size: 1764548536 dataset_size: 1765315696.875 - config_name: intergps(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 24973395.625 num_examples: 1275 download_size: 24736545 dataset_size: 24973395.625 - config_name: k12_printing features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1205153118.5 num_examples: 256636 download_size: 1108572712 dataset_size: 1205153118.5 - config_name: llavar_gpt4_20k features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 633833350.25 num_examples: 19790 download_size: 625365542 dataset_size: 633833350.25 - config_name: lrv_chart features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 99338686 num_examples: 1776 download_size: 97979446 dataset_size: 99338686 - config_name: lrv_normal(filtered) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 422589381.75 num_examples: 10490 download_size: 406958773 dataset_size: 422589381.75 - config_name: magpie_pro(l3_80b_mt) features: - name: id dtype: string - name: image dtype: 'null' - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1657129141 num_examples: 299988 download_size: 885893066 dataset_size: 1657129141 - config_name: magpie_pro(l3_80b_st) features: - name: id dtype: string - name: image dtype: 'null' - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1033666690 num_examples: 299990 download_size: 562771564 dataset_size: 1033666690 - config_name: magpie_pro(qwen2_72b_st) features: - name: id dtype: string - name: image dtype: 'null' - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 703489344 num_examples: 299982 download_size: 361433408 dataset_size: 703489344 - config_name: mapqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 3355751195.5 num_examples: 37412 download_size: 3305639218 dataset_size: 3355751195.5 - config_name: mathqa features: - name: id dtype: string - name: image dtype: 'null' - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 18318538 num_examples: 29827 download_size: 7857130 dataset_size: 18318538 - config_name: mavis_math_metagen features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2304025372.5 num_examples: 87348 download_size: 322776224 dataset_size: 2304025372.5 - config_name: mavis_math_rule_geo features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 14313211512.25 num_examples: 99990 download_size: 5841283073 dataset_size: 14313211512.25 - config_name: multihiertt(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 300319803.25 num_examples: 7614 download_size: 295638314 dataset_size: 300319803.25 - config_name: orand_car_a features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 23602442.125 num_examples: 1999 download_size: 23333412 dataset_size: 23602442.125 - config_name: raven(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 1706160514.625 num_examples: 41995 download_size: 1693150088 dataset_size: 1706160514.625 - config_name: rendered_text(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 11082594894.625 num_examples: 9995 download_size: 11081962044 dataset_size: 11082594894.625 - config_name: robut_sqa(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 685580779.375 num_examples: 8509 download_size: 678666263 dataset_size: 685580779.375 - config_name: robut_wikisql(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 6200499653 num_examples: 74984 download_size: 6168399217 dataset_size: 6200499653 - config_name: robut_wtq(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 4091776188.875 num_examples: 38241 download_size: 4062777449 dataset_size: 4091776188.875 - config_name: scienceqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 286843125.625 num_examples: 4971 download_size: 282896809 dataset_size: 286843125.625 - config_name: scienceqa(nona_context) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2111029055 num_examples: 19208 download_size: 2053942726 dataset_size: 2111029055 - config_name: screen2words(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 7977502095.375 num_examples: 15725 download_size: 7962327904 dataset_size: 7977502095.375 - config_name: sharegpt4o features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 6968025789.5 num_examples: 57284 download_size: 6772195470 dataset_size: 6968025789.5 - config_name: sharegpt4v(coco) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2620153362.875 num_examples: 50017 download_size: 2595583499 dataset_size: 2620153362.875 - config_name: sharegpt4v(knowledge) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 372100773.5 num_examples: 1988 download_size: 369799318 dataset_size: 372100773.5 - config_name: sharegpt4v(llava) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 781795487.25 num_examples: 29990 download_size: 400344187 dataset_size: 781795487.25 - config_name: sharegpt4v(sam) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 4437405218.25 num_examples: 8990 download_size: 4428597081 dataset_size: 4437405218.25 - config_name: sroie features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 117810195 num_examples: 33616 download_size: 103647636 dataset_size: 117810195 - config_name: st_vqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 5771194098.75 num_examples: 17242 download_size: 5768888141 dataset_size: 5771194098.75 - config_name: tabmwp(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 311192518.375 num_examples: 22717 download_size: 306092255 dataset_size: 311192518.375 - config_name: tallyqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 35998988065.625 num_examples: 98675 download_size: 35982430394 dataset_size: 35998988065.625 - config_name: textcaps features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2222268476.25 num_examples: 21942 download_size: 2217838132 dataset_size: 2222268476.25 - config_name: textocr(gpt4v) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2581655353 num_examples: 25104 download_size: 2574418106 dataset_size: 2581655353 - config_name: tqa(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 331203026.25 num_examples: 27302 download_size: 326999466 dataset_size: 331203026.25 - config_name: ureader_cap features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 9269857109.75 num_examples: 91434 download_size: 2292099971 dataset_size: 9269857109.75 - config_name: ureader_ie features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 11871457209.75 num_examples: 17322 download_size: 1999083115 dataset_size: 11871457209.75 - config_name: vision_flan(filtered) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 24847242604.5 num_examples: 186060 download_size: 24750561877 dataset_size: 24847242604.5 - config_name: vistext(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 550187184.5 num_examples: 9964 download_size: 452795103 dataset_size: 550187184.5 - config_name: visual7w(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 4451436523.875 num_examples: 14361 download_size: 4441971985 dataset_size: 4451436523.875 - config_name: visualmrc(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 2938154124.25 num_examples: 3022 download_size: 2909296079 dataset_size: 2938154124.25 - config_name: vqarad(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 95533417 num_examples: 308 download_size: 95410398 dataset_size: 95533417 - config_name: vsr(cauldron,llava_format) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 891981646 num_examples: 2152 download_size: 891572866 dataset_size: 891981646 - config_name: websight(cauldron) features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string - name: data_source dtype: string splits: - name: train num_bytes: 11209715828.625 num_examples: 9995 download_size: 11144460985 dataset_size: 11209715828.625 configs: - config_name: CLEVR-Math(MathV360K) data_files: - split: train path: CLEVR-Math(MathV360K)/train-* - config_name: FigureQA(MathV360K) data_files: - split: train path: FigureQA(MathV360K)/train-* - config_name: GEOS(MathV360K) data_files: - split: train path: GEOS(MathV360K)/train-* - config_name: GeoQA+(MathV360K) data_files: - split: train path: GeoQA+(MathV360K)/train-* - config_name: Geometry3K(MathV360K) data_files: - split: train path: Geometry3K(MathV360K)/train-* - config_name: IconQA(MathV360K) data_files: - split: train path: IconQA(MathV360K)/train-* - config_name: MapQA(MathV360K) data_files: - split: train path: MapQA(MathV360K)/train-* - config_name: PMC-VQA(MathV360K) data_files: - split: train path: PMC-VQA(MathV360K)/train-* - config_name: Super-CLEVR(MathV360K) data_files: - split: train path: Super-CLEVR(MathV360K)/train-* - config_name: TabMWP(MathV360K) data_files: - split: train path: TabMWP(MathV360K)/train-* - config_name: UniGeo(MathV360K) data_files: - split: train path: UniGeo(MathV360K)/train-* - config_name: VisualWebInstruct(filtered) data_files: - split: train path: VisualWebInstruct(filtered)/train-* - config_name: VizWiz(MathV360K) data_files: - split: train path: VizWiz(MathV360K)/train-* - config_name: ai2d(cauldron,llava_format) data_files: - split: train path: ai2d(cauldron,llava_format)/train-* - config_name: ai2d(gpt4v) data_files: - split: train path: ai2d(gpt4v)/train-* - config_name: ai2d(internvl) data_files: - split: train path: ai2d(internvl)/train-* - config_name: allava_instruct_laion4v data_files: - split: train path: allava_instruct_laion4v/train-* - config_name: allava_instruct_vflan4v data_files: - split: train path: allava_instruct_vflan4v/train-* - config_name: aokvqa(cauldron,llava_format) data_files: - split: train path: aokvqa(cauldron,llava_format)/train-* - config_name: chart2text(cauldron) data_files: - split: train path: chart2text(cauldron)/train-* - config_name: chartqa(cauldron,llava_format) data_files: - split: train path: chartqa(cauldron,llava_format)/train-* - config_name: chrome_writting data_files: - split: train path: chrome_writting/train-* - config_name: clevr(cauldron,llava_format) data_files: - split: train path: clevr(cauldron,llava_format)/train-* - config_name: diagram_image_to_text(cauldron) data_files: - split: train path: diagram_image_to_text(cauldron)/train-* - config_name: dvqa(cauldron,llava_format) data_files: - split: train path: dvqa(cauldron,llava_format)/train-* - config_name: figureqa(cauldron,llava_format) data_files: - split: train path: figureqa(cauldron,llava_format)/train-* - config_name: geo170k(align) data_files: - split: train path: geo170k(align)/train-* - config_name: geo170k(qa) data_files: - split: train path: geo170k(qa)/train-* - config_name: geo3k data_files: - split: train path: geo3k/train-* - config_name: geomverse(cauldron) data_files: - split: train path: geomverse(cauldron)/train-* - config_name: hateful_memes(cauldron,llava_format) data_files: - split: train path: hateful_memes(cauldron,llava_format)/train-* - config_name: hitab(cauldron,llava_format) data_files: - split: train path: hitab(cauldron,llava_format)/train-* - config_name: hme100k data_files: - split: train path: hme100k/train-* - config_name: iam(cauldron) data_files: - split: train path: iam(cauldron)/train-* - config_name: iconqa(cauldron,llava_format) data_files: - split: train path: iconqa(cauldron,llava_format)/train-* - config_name: iiit5k data_files: - split: train path: iiit5k/train-* - config_name: image_textualization(filtered) data_files: - split: train path: image_textualization(filtered)/train-* - config_name: infographic(gpt4v) data_files: - split: train path: infographic(gpt4v)/train-* - config_name: infographic_vqa data_files: - split: train path: infographic_vqa/train-* - config_name: infographic_vqa_llava_format data_files: - split: train path: infographic_vqa_llava_format/train-* - config_name: intergps(cauldron,llava_format) data_files: - split: train path: intergps(cauldron,llava_format)/train-* - config_name: k12_printing data_files: - split: train path: k12_printing/train-* - config_name: llavar_gpt4_20k data_files: - split: train path: llavar_gpt4_20k/train-* - config_name: lrv_chart data_files: - split: train path: lrv_chart/train-* - config_name: lrv_normal(filtered) data_files: - split: train path: lrv_normal(filtered)/train-* - config_name: magpie_pro(l3_80b_mt) data_files: - split: train path: magpie_pro(l3_80b_mt)/train-* - config_name: magpie_pro(l3_80b_st) data_files: - split: train path: magpie_pro(l3_80b_st)/train-* - config_name: magpie_pro(qwen2_72b_st) data_files: - split: train path: magpie_pro(qwen2_72b_st)/train-* - config_name: mapqa(cauldron,llava_format) data_files: - split: train path: mapqa(cauldron,llava_format)/train-* - config_name: mathqa data_files: - split: train path: mathqa/train-* - config_name: mavis_math_metagen data_files: - split: train path: mavis_math_metagen/train-* - config_name: mavis_math_rule_geo data_files: - split: train path: mavis_math_rule_geo/train-* - config_name: multihiertt(cauldron) data_files: - split: train path: multihiertt(cauldron)/train-* - config_name: orand_car_a data_files: - split: train path: orand_car_a/train-* - config_name: raven(cauldron) data_files: - split: train path: raven(cauldron)/train-* - config_name: rendered_text(cauldron) data_files: - split: train path: rendered_text(cauldron)/train-* - config_name: robut_sqa(cauldron) data_files: - split: train path: robut_sqa(cauldron)/train-* - config_name: robut_wikisql(cauldron) data_files: - split: train path: robut_wikisql(cauldron)/train-* - config_name: robut_wtq(cauldron,llava_format) data_files: - split: train path: robut_wtq(cauldron,llava_format)/train-* - config_name: scienceqa(cauldron,llava_format) data_files: - split: train path: scienceqa(cauldron,llava_format)/train-* - config_name: scienceqa(nona_context) data_files: - split: train path: scienceqa(nona_context)/train-* - config_name: screen2words(cauldron) data_files: - split: train path: screen2words(cauldron)/train-* - config_name: sharegpt4o data_files: - split: train path: sharegpt4o/train-* - config_name: sharegpt4v(coco) data_files: - split: train path: sharegpt4v(coco)/train-* - config_name: sharegpt4v(knowledge) data_files: - split: train path: sharegpt4v(knowledge)/train-* - config_name: sharegpt4v(llava) data_files: - split: train path: sharegpt4v(llava)/train-* - config_name: sharegpt4v(sam) data_files: - split: train path: sharegpt4v(sam)/train-* - config_name: sroie data_files: - split: train path: sroie/train-* - config_name: st_vqa(cauldron,llava_format) data_files: - split: train path: st_vqa(cauldron,llava_format)/train-* - config_name: tabmwp(cauldron) data_files: - split: train path: tabmwp(cauldron)/train-* - config_name: tallyqa(cauldron,llava_format) data_files: - split: train path: tallyqa(cauldron,llava_format)/train-* - config_name: textcaps data_files: - split: train path: textcaps/train-* - config_name: textocr(gpt4v) data_files: - split: train path: textocr(gpt4v)/train-* - config_name: tqa(cauldron,llava_format) data_files: - split: train path: tqa(cauldron,llava_format)/train-* - config_name: ureader_cap data_files: - split: train path: ureader_cap/train-* - config_name: ureader_ie data_files: - split: train path: ureader_ie/train-* - config_name: vision_flan(filtered) data_files: - split: train path: vision_flan(filtered)/train-* - config_name: vistext(cauldron) data_files: - split: train path: vistext(cauldron)/train-* - config_name: visual7w(cauldron,llava_format) data_files: - split: train path: visual7w(cauldron,llava_format)/train-* - config_name: visualmrc(cauldron) data_files: - split: train path: visualmrc(cauldron)/train-* - config_name: vqarad(cauldron,llava_format) data_files: - split: train path: vqarad(cauldron,llava_format)/train-* - config_name: vsr(cauldron,llava_format) data_files: - split: train path: vsr(cauldron,llava_format)/train-* - config_name: websight(cauldron) data_files: - split: train path: websight(cauldron)/train-* --- # Dataset Card for LLaVA-OneVision **[2024-09-01]: Uploaded VisualWebInstruct(filtered), it's used in OneVision Stage** > almost all subsets are uploaded with HF's required format and you can use the recommended interface to download them and follow our code below to convert them. > the subset of `ureader_kg` and `ureader_qa` are uploaded with the processed jsons and tar.gz of image folders. > You may directly download them from the following url. > https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data/tree/main/ureader_kg In this dataset, we include the data splits used in the both final image stage and one-vision stage. For more details, please check our [paper](arxiv.org/abs/2408.03326) and our [training doc](https://github.com/LLaVA-VL/LLaVA-NeXT/tree/main/scripts/train#about-the-llava-onevision-data). ## Dataset Description - **Curated by:** Bo Li, Kaichen Zhang, Hao Zhang, Yuanhan Zhang, Renrui Zhang, Feng Li, Dong Guo - **Language(s) (NLP):** English, Chinese - **License:** Apache License 2.0 ## Dataset Sources <!-- Provide the basic links for the dataset. --> - **Dataset Collection:** We include a few subsets from existing dataset collection [Cambrian](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M), [Cauldron](https://huggingface.co/datasets/HuggingFaceM4/the_cauldron), [UReader](https://arxiv.org/abs/2310.05126). Since we only used a few subsets from these datasets, and applied the cleaning and re-annotation process, we uploaded our processed version of these datasets into our own repository and thank the authors for providing the original datasets. - **Other Datasets:** For rest single source dataset, such as AI2D, OKVQA, we cite and link the original sources in our paper. ## Uses This dataset is used for the training of the LLaVA-OneVision model. We only allow the use of this dataset for academic research and education purpose. For OpenAI GPT-4 generated data, we recommend the users to check the [OpenAI Usage Policy](https://openai.com/policies/usage-policies/). ## Dataset Structure We expalin the data composition for mid-stage and final-stage at our repo in [**training doc**](https://github.com/LLaVA-VL/LLaVA-NeXT/tree/main/scripts/train#about-the-llava-onevision-data). ### Statistics We provide the statistics of the dataset in the following figures, and refer the audience to check our paper.   ### Code Guidance To help audience to better understand our dataest, we upload them into Hugging Face Dataset compatible format. During LLaVA-OneVision training, we use the `json` and `image/video` folder to store the data. > the subset of `ureader_kg` and `ureader_qa` are uploaded with the processed jsons and tar.gz of image folders. You may directly download them from the following url. > https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data/tree/main/ureader_kg Here we provide the code guidance to convert the dataset into the format of LLaVA-OneVision, and conduct the training of the LLaVA-OneVision model with converted dataset. ```python import os from datasets import load_dataset from tqdm import tqdm import json data = load_dataset("lmms-lab/LLaVA-OneVision-Data", split="train") image_folder = "<your_image_folder>" converted_data = [] for da in tqdm(data): json_data = {} json_data["id"] = da["id"] if da["image"] is not None: json_data["image"] = f"{da['id']}.jpg" da["image"].save(os.path.join(image_folder, json_data["image"])) json_data["conversations"] = da["conversations"] converted_data.append(json_data) with open("<your_json_file>.json", "w") as f: json.dump(converted_data, f, indent=4, ensure_ascii=False) ``` ## Citation **BibTeX:** [More Information Needed] ## Glossary The dataset collection process is conducted by all of the authors, we thank the Feng Li and Renrui Zhang for providing [LLaVA-M4-Instruct Data](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data) and Yuanhan for providing the [Video datasets](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K). After the dataset collection, the cleaning and re-annotation process, including final mixture of the dataset, is conducted by Bo Li and with the great help of Kaichen Zhang. ## Dataset Card Authors The dataset is curated by the following authors: Bo Li, Kaichen Zhang, Hao Zhang, Yuanhan Zhang, Renrui Zhang, Feng Li ## Dataset Card Contact [Bo Li](https://brianboli.com/): [email protected] [Kaichen Zhang](https://www.linkedin.com/in/kaichen-zhang-014b17219/?originalSubdomain=sg)

MU-NLPC/Calc-svamp

MU-NLPC

--- language: - en license: mit size_categories: - n<1K task_categories: - text-generation tags: - math world problems - math - arithmetics dataset_info: - config_name: default features: - name: id dtype: string - name: question dtype: string - name: chain dtype: string - name: result dtype: string - name: result_float dtype: float64 - name: equation dtype: string - name: problem_type dtype: string splits: - name: test num_bytes: 335744 num_examples: 1000 download_size: 116449 dataset_size: 335744 - config_name: original-splits features: - name: id dtype: string - name: question dtype: string - name: chain dtype: string - name: result dtype: string - name: result_float dtype: float64 - name: equation dtype: string - name: problem_type dtype: string splits: - name: test num_bytes: 335744 num_examples: 1000 download_size: 116449 dataset_size: 335744 configs: - config_name: default data_files: - split: test path: data/test-* - config_name: original-splits data_files: - split: test path: original-splits/test-* --- # Dataset Card for Calc-SVAMP ## Summary The dataset is a collection of simple math word problems focused on arithmetics. It is derived from <https://github.com/arkilpatel/SVAMP/>. The main addition in this dataset variant is the `chain` column. It was created by converting the solution to a simple html-like language that can be easily parsed (e.g. by BeautifulSoup). The data contains 3 types of tags: - gadget: A tag whose content is intended to be evaluated by calling an external tool (sympy-based calculator in this case) - output: An output of the external tool - result: The final answer to the mathematical problem (a number) ## Supported Tasks This variant of the dataset is intended for training Chain-of-Thought reasoning models able to use external tools to enhance the factuality of their responses. This dataset presents in-context scenarios where models can outsource the computations in the reasoning chain to a calculator. ## Construction process We created the dataset by converting the **equation** attribute in the original dataset to a sequence (chain) of calculations, with final one being the result to the math problem. We also perform in-dataset and cross-dataset data-leak detection within the [Calc-X collection](https://huggingface.co/collections/MU-NLPC/calc-x-652fee9a6b838fd820055483). However, for SVAMP specifically, we detected no data leaks and filtered no data. ## Content and data splits The dataset contains the same data instances as the original dataset except for a correction of inconsistency between `equation` and `answer` in one data instance. To the best of our knowledge, the original dataset does not contain an official train-test split. We treat the whole dataset as a testing benchmark. ## Attributes: - **id**: problem id from the original dataset - **question**: the question intended to answer - **chain**: series of simple operations (derived from `equation`) that leads to the solution - **result**: the result (number) as a string - **result_float**: result converted to a floating point - **equation**: a nested expression that evaluates to the correct result - **problem_type**: a category of the problem Attributes **id**, **question**, **chain**, and **result** are present in all datasets in [Calc-X collection](https://huggingface.co/collections/MU-NLPC/calc-x-652fee9a6b838fd820055483). ## Related work This dataset was created as a part of a larger effort in training models capable of using a calculator during inference, which we call Calcformers. - [**Calc-X collection**](https://huggingface.co/collections/MU-NLPC/calc-x-652fee9a6b838fd820055483) - datasets for training Calcformers - [**Calcformers collection**](https://huggingface.co/collections/MU-NLPC/calcformers-65367392badc497807b3caf5) - calculator-using models we trained and published on HF - [**Calc-X and Calcformers paper**](https://arxiv.org/abs/2305.15017) - [**Calc-X and Calcformers repo**](https://github.com/prompteus/calc-x) Here are links to the original dataset: - [**original SVAMP dataset and repo**](https://github.com/arkilpatel/SVAMP/) - [**original SVAMP paper**](https://www.semanticscholar.org/paper/Are-NLP-Models-really-able-to-Solve-Simple-Math-Patel-Bhattamishra/13c4e5a6122f3fa2663f63e49537091da6532f35) ## Licence MIT, consistent with the original source dataset linked above. ## Cite If you use this version of dataset in research, please cite the original [SVAMP paper](https://www.semanticscholar.org/paper/Are-NLP-Models-really-able-to-Solve-Simple-Math-Patel-Bhattamishra/13c4e5a6122f3fa2663f63e49537091da6532f35), and [Calc-X collection](https://arxiv.org/abs/2305.15017) as follows: ```bibtex @inproceedings{kadlcik-etal-2023-soft, title = "Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems", author = "Marek Kadlčík and Michal Štefánik and Ondřej Sotolář and Vlastimil Martinek", booktitle = "Proceedings of the The 2023 Conference on Empirical Methods in Natural Language Processing: Main track", month = dec, year = "2023", address = "Singapore, Singapore", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/2305.15017", } ```

cardiffnlp/tweet_eval

cardiffnlp

--- annotations_creators: - found language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 100K<n<1M - 10K<n<100K - 1K<n<10K - n<1K source_datasets: - extended|other-tweet-datasets task_categories: - text-classification task_ids: - intent-classification - multi-class-classification - sentiment-classification paperswithcode_id: tweeteval pretty_name: TweetEval config_names: - emoji - emotion - hate - irony - offensive - sentiment - stance_abortion - stance_atheism - stance_climate - stance_feminist - stance_hillary dataset_info: - config_name: emoji features: - name: text dtype: string - name: label dtype: class_label: names: '0': ❤ '1': 😍 '2': 😂 '3': 💕 '4': 🔥 '5': 😊 '6': 😎 '7': ✨ '8': 💙 '9': 😘 '10': 📷 '11': 🇺🇸 '12': ☀ '13': 💜 '14': 😉 '15': 💯 '16': 😁 '17': 🎄 '18': 📸 '19': 😜 splits: - name: train num_bytes: 3803167 num_examples: 45000 - name: test num_bytes: 4255901 num_examples: 50000 - name: validation num_bytes: 396079 num_examples: 5000 download_size: 5939308 dataset_size: 8455147 - config_name: emotion features: - name: text dtype: string - name: label dtype: class_label: names: '0': anger '1': joy '2': optimism '3': sadness splits: - name: train num_bytes: 338871 num_examples: 3257 - name: test num_bytes: 146645 num_examples: 1421 - name: validation num_bytes: 38273 num_examples: 374 download_size: 367016 dataset_size: 523789 - config_name: hate features: - name: text dtype: string - name: label dtype: class_label: names: '0': non-hate '1': hate splits: - name: train num_bytes: 1223650 num_examples: 9000 - name: test num_bytes: 428934 num_examples: 2970 - name: validation num_bytes: 154144 num_examples: 1000 download_size: 1196346 dataset_size: 1806728 - config_name: irony features: - name: text dtype: string - name: label dtype: class_label: names: '0': non_irony '1': irony splits: - name: train num_bytes: 259187 num_examples: 2862 - name: test num_bytes: 75897 num_examples: 784 - name: validation num_bytes: 86017 num_examples: 955 download_size: 297647 dataset_size: 421101 - config_name: offensive features: - name: text dtype: string - name: label dtype: class_label: names: '0': non-offensive '1': offensive splits: - name: train num_bytes: 1648061 num_examples: 11916 - name: test num_bytes: 135473 num_examples: 860 - name: validation num_bytes: 192417 num_examples: 1324 download_size: 1234528 dataset_size: 1975951 - config_name: sentiment features: - name: text dtype: string - name: label dtype: class_label: names: '0': negative '1': neutral '2': positive splits: - name: train num_bytes: 5425122 num_examples: 45615 - name: test num_bytes: 1279540 num_examples: 12284 - name: validation num_bytes: 239084 num_examples: 2000 download_size: 4849675 dataset_size: 6943746 - config_name: stance_abortion features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 68694 num_examples: 587 - name: test num_bytes: 33171 num_examples: 280 - name: validation num_bytes: 7657 num_examples: 66 download_size: 73517 dataset_size: 109522 - config_name: stance_atheism features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 54775 num_examples: 461 - name: test num_bytes: 25716 num_examples: 220 - name: validation num_bytes: 6320 num_examples: 52 download_size: 62265 dataset_size: 86811 - config_name: stance_climate features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 40249 num_examples: 355 - name: test num_bytes: 19925 num_examples: 169 - name: validation num_bytes: 4801 num_examples: 40 download_size: 48493 dataset_size: 64975 - config_name: stance_feminist features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 70509 num_examples: 597 - name: test num_bytes: 33305 num_examples: 285 - name: validation num_bytes: 8035 num_examples: 67 download_size: 76345 dataset_size: 111849 - config_name: stance_hillary features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 69596 num_examples: 620 - name: test num_bytes: 34487 num_examples: 295 - name: validation num_bytes: 7532 num_examples: 69 download_size: 74057 dataset_size: 111615 configs: - config_name: emoji data_files: - split: train path: emoji/train-* - split: test path: emoji/test-* - split: validation path: emoji/validation-* - config_name: emotion data_files: - split: train path: emotion/train-* - split: test path: emotion/test-* - split: validation path: emotion/validation-* - config_name: hate data_files: - split: train path: hate/train-* - split: test path: hate/test-* - split: validation path: hate/validation-* - config_name: irony data_files: - split: train path: irony/train-* - split: test path: irony/test-* - split: validation path: irony/validation-* - config_name: offensive data_files: - split: train path: offensive/train-* - split: test path: offensive/test-* - split: validation path: offensive/validation-* - config_name: sentiment data_files: - split: train path: sentiment/train-* - split: test path: sentiment/test-* - split: validation path: sentiment/validation-* - config_name: stance_abortion data_files: - split: train path: stance_abortion/train-* - split: test path: stance_abortion/test-* - split: validation path: stance_abortion/validation-* - config_name: stance_atheism data_files: - split: train path: stance_atheism/train-* - split: test path: stance_atheism/test-* - split: validation path: stance_atheism/validation-* - config_name: stance_climate data_files: - split: train path: stance_climate/train-* - split: test path: stance_climate/test-* - split: validation path: stance_climate/validation-* - config_name: stance_feminist data_files: - split: train path: stance_feminist/train-* - split: test path: stance_feminist/test-* - split: validation path: stance_feminist/validation-* - config_name: stance_hillary data_files: - split: train path: stance_hillary/train-* - split: test path: stance_hillary/test-* - split: validation path: stance_hillary/validation-* train-eval-index: - config: emotion task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: hate task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: irony task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: offensive task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: sentiment task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for tweet_eval ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [Needs More Information] - **Repository:** [GitHub](https://github.com/cardiffnlp/tweeteval) - **Paper:** [EMNLP Paper](https://arxiv.org/pdf/2010.12421.pdf) - **Leaderboard:** [GitHub Leaderboard](https://github.com/cardiffnlp/tweeteval) - **Point of Contact:** [Needs More Information] ### Dataset Summary TweetEval consists of seven heterogenous tasks in Twitter, all framed as multi-class tweet classification. The tasks include - irony, hate, offensive, stance, emoji, emotion, and sentiment. All tasks have been unified into the same benchmark, with each dataset presented in the same format and with fixed training, validation and test splits. ### Supported Tasks and Leaderboards - `text_classification`: The dataset can be trained using a SentenceClassification model from HuggingFace transformers. ### Languages The text in the dataset is in English, as spoken by Twitter users. ## Dataset Structure ### Data Instances An instance from `emoji` config: ``` {'label': 12, 'text': 'Sunday afternoon walking through Venice in the sun with @user ️ ️ ️ @ Abbot Kinney, Venice'} ``` An instance from `emotion` config: ``` {'label': 2, 'text': "“Worry is a down payment on a problem you may never have'. \xa0Joyce Meyer. #motivation #leadership #worry"} ``` An instance from `hate` config: ``` {'label': 0, 'text': '@user nice new signage. Are you not concerned by Beatlemania -style hysterical crowds crongregating on you…'} ``` An instance from `irony` config: ``` {'label': 1, 'text': 'seeing ppl walking w/ crutches makes me really excited for the next 3 weeks of my life'} ``` An instance from `offensive` config: ``` {'label': 0, 'text': '@user Bono... who cares. Soon people will understand that they gain nothing from following a phony celebrity. Become a Leader of your people instead or help and support your fellow countrymen.'} ``` An instance from `sentiment` config: ``` {'label': 2, 'text': '"QT @user In the original draft of the 7th book, Remus Lupin survived the Battle of Hogwarts. #HappyBirthdayRemusLupin"'} ``` An instance from `stance_abortion` config: ``` {'label': 1, 'text': 'we remind ourselves that love means to be willing to give until it hurts - Mother Teresa'} ``` An instance from `stance_atheism` config: ``` {'label': 1, 'text': '@user Bless Almighty God, Almighty Holy Spirit and the Messiah. #SemST'} ``` An instance from `stance_climate` config: ``` {'label': 0, 'text': 'Why Is The Pope Upset? via @user #UnzippedTruth #PopeFrancis #SemST'} ``` An instance from `stance_feminist` config: ``` {'label': 1, 'text': "@user @user is the UK's answer to @user and @user #GamerGate #SemST"} ``` An instance from `stance_hillary` config: ``` {'label': 1, 'text': "If a man demanded staff to get him an ice tea he'd be called a sexists elitist pig.. Oink oink #Hillary #SemST"} ``` ### Data Fields For `emoji` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: ❤ `1`: 😍 `2`: 😂 `3`: 💕 `4`: 🔥 `5`: 😊 `6`: 😎 `7`: ✨ `8`: 💙 `9`: 😘 `10`: 📷 `11`: 🇺🇸 `12`: ☀ `13`: 💜 `14`: 😉 `15`: 💯 `16`: 😁 `17`: 🎄 `18`: 📸 `19`: 😜 For `emotion` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: anger `1`: joy `2`: optimism `3`: sadness For `hate` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non-hate `1`: hate For `irony` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non_irony `1`: irony For `offensive` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non-offensive `1`: offensive For `sentiment` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: negative `1`: neutral `2`: positive For `stance_abortion` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_atheism` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_climate` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_feminist` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_hillary` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor ### Data Splits | name | train | validation | test | | --------------- | ----- | ---------- | ----- | | emoji | 45000 | 5000 | 50000 | | emotion | 3257 | 374 | 1421 | | hate | 9000 | 1000 | 2970 | | irony | 2862 | 955 | 784 | | offensive | 11916 | 1324 | 860 | | sentiment | 45615 | 2000 | 12284 | | stance_abortion | 587 | 66 | 280 | | stance_atheism | 461 | 52 | 220 | | stance_climate | 355 | 40 | 169 | | stance_feminist | 597 | 67 | 285 | | stance_hillary | 620 | 69 | 295 | ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators Francesco Barbieri, Jose Camacho-Collados, Luis Espiinosa-Anke and Leonardo Neves through Cardiff NLP. ### Licensing Information This is not a single dataset, therefore each subset has its own license (the collection itself does not have additional restrictions). All of the datasets require complying with Twitter [Terms Of Service](https://twitter.com/tos) and Twitter API [Terms Of Service](https://developer.twitter.com/en/developer-terms/agreement-and-policy) Additionally the license are: - emoji: Undefined - emotion(EmoInt): Undefined - hate (HateEval): Need permission [here](http://hatespeech.di.unito.it/hateval.html) - irony: Undefined - Offensive: Undefined - Sentiment: [Creative Commons Attribution 3.0 Unported License](https://groups.google.com/g/semevaltweet/c/k5DDcvVb_Vo/m/zEOdECFyBQAJ) - Stance: Undefined ### Citation Information ``` @inproceedings{barbieri2020tweeteval, title={{TweetEval:Unified Benchmark and Comparative Evaluation for Tweet Classification}}, author={Barbieri, Francesco and Camacho-Collados, Jose and Espinosa-Anke, Luis and Neves, Leonardo}, booktitle={Proceedings of Findings of EMNLP}, year={2020} } ``` If you use any of the TweetEval datasets, please cite their original publications: #### Emotion Recognition: ``` @inproceedings{mohammad2018semeval, title={Semeval-2018 task 1: Affect in tweets}, author={Mohammad, Saif and Bravo-Marquez, Felipe and Salameh, Mohammad and Kiritchenko, Svetlana}, booktitle={Proceedings of the 12th international workshop on semantic evaluation}, pages={1--17}, year={2018} } ``` #### Emoji Prediction: ``` @inproceedings{barbieri2018semeval, title={Semeval 2018 task 2: Multilingual emoji prediction}, author={Barbieri, Francesco and Camacho-Collados, Jose and Ronzano, Francesco and Espinosa-Anke, Luis and Ballesteros, Miguel and Basile, Valerio and Patti, Viviana and Saggion, Horacio}, booktitle={Proceedings of The 12th International Workshop on Semantic Evaluation}, pages={24--33}, year={2018} } ``` #### Irony Detection: ``` @inproceedings{van2018semeval, title={Semeval-2018 task 3: Irony detection in english tweets}, author={Van Hee, Cynthia and Lefever, Els and Hoste, V{\'e}ronique}, booktitle={Proceedings of The 12th International Workshop on Semantic Evaluation}, pages={39--50}, year={2018} } ``` #### Hate Speech Detection: ``` @inproceedings{basile-etal-2019-semeval, title = "{S}em{E}val-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in {T}witter", author = "Basile, Valerio and Bosco, Cristina and Fersini, Elisabetta and Nozza, Debora and Patti, Viviana and Rangel Pardo, Francisco Manuel and Rosso, Paolo and Sanguinetti, Manuela", booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation", year = "2019", address = "Minneapolis, Minnesota, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/S19-2007", doi = "10.18653/v1/S19-2007", pages = "54--63" } ``` #### Offensive Language Identification: ``` @inproceedings{zampieri2019semeval, title={SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)}, author={Zampieri, Marcos and Malmasi, Shervin and Nakov, Preslav and Rosenthal, Sara and Farra, Noura and Kumar, Ritesh}, booktitle={Proceedings of the 13th International Workshop on Semantic Evaluation}, pages={75--86}, year={2019} } ``` #### Sentiment Analysis: ``` @inproceedings{rosenthal2017semeval, title={SemEval-2017 task 4: Sentiment analysis in Twitter}, author={Rosenthal, Sara and Farra, Noura and Nakov, Preslav}, booktitle={Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017)}, pages={502--518}, year={2017} } ``` #### Stance Detection: ``` @inproceedings{mohammad2016semeval, title={Semeval-2016 task 6: Detecting stance in tweets}, author={Mohammad, Saif and Kiritchenko, Svetlana and Sobhani, Parinaz and Zhu, Xiaodan and Cherry, Colin}, booktitle={Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)}, pages={31--41}, year={2016} } ``` ### Contributions Thanks to [@gchhablani](https://github.com/gchhablani) and [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset.

parrotzone/sdxl-1.0

parrotzone

--- license: openrail++ --- # check [sdxl.parrotzone.art](https://sdxl.parrotzone.art) for easy viewing ⋆｡°✩ --- ## all images were made with SDXL 1.0 + the 0.9 VAE - steps: 20 - cfg scale: 7 - no refiner - random seeds

Matthijs/cmu-arctic-xvectors

Matthijs

--- pretty_name: CMU ARCTIC X-Vectors task_categories: - text-to-speech - audio-to-audio license: mit --- # Speaker embeddings extracted from CMU ARCTIC There is one `.npy` file for each utterance in the dataset, 7931 files in total. The speaker embeddings are 512-element X-vectors. The [CMU ARCTIC](http://www.festvox.org/cmu_arctic/) dataset divides the utterances among the following speakers: - bdl (US male) - slt (US female) - jmk (Canadian male) - awb (Scottish male) - rms (US male) - clb (US female) - ksp (Indian male) The X-vectors were extracted using [this script](https://huggingface.co/mechanicalsea/speecht5-vc/blob/main/manifest/utils/prep_cmu_arctic_spkemb.py), which uses the `speechbrain/spkrec-xvect-voxceleb` model. Usage: ```python from datasets import load_dataset embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation") speaker_embeddings = embeddings_dataset[7306]["xvector"] speaker_embeddings = torch.tensor(speaker_embeddings).unsqueeze(0) ```

lukaemon/bbh

lukaemon

--- dataset_info: - config_name: boolean_expressions features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 11790 num_examples: 250 download_size: 17172 dataset_size: 11790 - config_name: causal_judgement features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 198021 num_examples: 187 download_size: 202943 dataset_size: 198021 - config_name: date_understanding features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 54666 num_examples: 250 download_size: 61760 dataset_size: 54666 - config_name: disambiguation_qa features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 78620 num_examples: 250 download_size: 85255 dataset_size: 78620 - config_name: dyck_languages features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38432 num_examples: 250 download_size: 43814 dataset_size: 38432 - config_name: formal_fallacies features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 138224 num_examples: 250 download_size: 145562 dataset_size: 138224 - config_name: geometric_shapes features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 68560 num_examples: 250 download_size: 77242 dataset_size: 68560 - config_name: hyperbaton features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38574 num_examples: 250 download_size: 44706 dataset_size: 38574 - config_name: logical_deduction_five_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 148595 num_examples: 250 download_size: 155477 dataset_size: 148595 - config_name: logical_deduction_seven_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 191022 num_examples: 250 download_size: 198404 dataset_size: 191022 - config_name: logical_deduction_three_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 105831 num_examples: 250 download_size: 112213 dataset_size: 105831 - config_name: movie_recommendation features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 50985 num_examples: 250 download_size: 57684 dataset_size: 50985 - config_name: multistep_arithmetic_two features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 12943 num_examples: 250 download_size: 18325 dataset_size: 12943 - config_name: navigate features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 49031 num_examples: 250 download_size: 55163 dataset_size: 49031 - config_name: object_counting features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 30508 num_examples: 250 download_size: 35890 dataset_size: 30508 - config_name: penguins_in_a_table features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 70062 num_examples: 146 download_size: 74516 dataset_size: 70062 - config_name: reasoning_about_colored_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 89579 num_examples: 250 download_size: 98694 dataset_size: 89579 - config_name: ruin_names features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 46537 num_examples: 250 download_size: 53178 dataset_size: 46537 - config_name: salient_translation_error_detection features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 277110 num_examples: 250 download_size: 286443 dataset_size: 277110 - config_name: snarks features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38223 num_examples: 178 download_size: 42646 dataset_size: 38223 - config_name: sports_understanding features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 22723 num_examples: 250 download_size: 28617 dataset_size: 22723 - config_name: temporal_sequences features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 139546 num_examples: 250 download_size: 148176 dataset_size: 139546 - config_name: tracking_shuffled_objects_five_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 162590 num_examples: 250 download_size: 169722 dataset_size: 162590 - config_name: tracking_shuffled_objects_seven_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 207274 num_examples: 250 download_size: 214906 dataset_size: 207274 - config_name: tracking_shuffled_objects_three_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 122104 num_examples: 250 download_size: 128736 dataset_size: 122104 - config_name: web_of_lies features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 47582 num_examples: 250 download_size: 52964 dataset_size: 47582 - config_name: word_sorting features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 60918 num_examples: 250 download_size: 66300 dataset_size: 60918 --- # BIG-bench Hard dataset homepage: https://github.com/suzgunmirac/BIG-Bench-Hard ``` @article{suzgun2022challenging, title={Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them}, author={Suzgun, Mirac and Scales, Nathan and Sch{\"a}rli, Nathanael and Gehrmann, Sebastian and Tay, Yi and Chung, Hyung Won and Chowdhery, Aakanksha and Le, Quoc V and Chi, Ed H and Zhou, Denny and and Wei, Jason}, journal={arXiv preprint arXiv:2210.09261}, year={2022} } ```

imageomics/TreeOfLife-10M

imageomics

--- License: cc0-1.0 language: - en - la pretty_name: TreeOfLife-10M task_categories: - image-classification - zero-shot-classification tags: - biology - images - animals - evolutionary biology - CV - multimodal - clip - biology - species - taxonomy - knowledge-guided - imbalanced size_categories: 10M<n<100M --- # Dataset Card for TreeOfLife-10M ## Dataset Description <!-- - **Homepage:** --> - **Repository:** [Imageomics/bioclip](https://github.com/Imageomics/bioclip) - **Paper:** BioCLIP: A Vision Foundation Model for the Tree of Life ([arXiv](https://doi.org/10.48550/arXiv.2311.18803)) <!-- - **Leaderboard:** --> ### Dataset Summary With over 10 million images covering 454 thousand taxa in the tree of life, TreeOfLife-10M is the largest-to-date ML-ready dataset of images of biological organisms paired with their associated taxonomic labels. It expands on the foundation established by existing high-quality datasets, such as iNat21 and BIOSCAN-1M, by further incorporating newly curated images from the Encyclopedia of Life (eol.org), which supplies most of TreeOfLife-10M’s data diversity. Every image in TreeOfLife-10M is labeled to the most specific taxonomic level possible, as well as higher taxonomic ranks in the tree of life (see [Text Types](#text-types) for examples of taxonomic ranks and labels). TreeOfLife-10M was generated for the purpose of training [BioCLIP](https://huggingface.co/imageomics/bioclip) and future biology foundation models. 
 <!--This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1). And further altered to suit Imageomics Institute needs. --> || |:--| |**Figure 1.** Treemap from phyla down to family for TreeOfLife-10M. Interactive version available in [`visuals`](https://huggingface.co/datasets/imageomics/TreeOfLife-10M/tree/main/visuals) folder.| ### Supported Tasks and Leaderboards Image Classification, Zero-shot and few-shot Classification. ### Languages English, Latin ## Dataset Contents ``` /dataset/ EOL/ image_set_01.tar.gz image_set_02.tar.gz ... image_set_63.tar.gz metadata/ catalog.csv species_level_taxonomy_chains.csv taxon.tab licenses.csv naming/ bioscan_name_lookup.json eol_name_lookup.json inat21_name_lookup.json visuals/ kingodm_ToL_tree.html kingdom_ToL_tree.pdf phyla_ToL_tree.html phyla_ToL_tree.pdf phyla_ToL_tree.png ``` Each `image_set` is approximately 30GB and contains 100 thousand images, each named `<treeoflife_id>.jpg`. We cannot reproduce the `iNat21` data, but step-by-step [***reproduction instructions***](https://github.com/Imageomics/bioclip/blob/main/docs/imageomics/treeoflife10m.md#reproduce-treeoflife-10m) are provided on the BioCLIP GitHub repository to recreate the proper webdataset structure. This process will produce a collection of files named `shard-######.tar` in a `train`, `val`, and `train_small` folder with which to work. Inside each shard is a collection of images (named `<treeoflife_id>.jpg`), for which each has the following files: ``` <treeoflife_id>.com.txt <treeoflife_id>.common_name.txt <treeoflife_id>.jpg <treeoflife_id>.sci.txt <treeoflife_id>.sci_com.txt <treeoflife_id>.scientific_name.txt <treeoflife_id>.taxon.txt <treeoflife_id>.taxonTag.txt <treeoflife_id>.taxonTag_com.txt <treeoflife_id>.taxon_com.txt <treeoflife_id>.taxonomic_name.txt ``` ### Data Instances This dataset is a collection of images with associated text. The text matched to images contains both [Linnaean taxonomy](https://www.britannica.com/science/taxonomy/The-objectives-of-biological-classification) (kingdom through species) for the particular subject of the image and its common (or vernacular) name where available. There are 8,455,243 images with full taxonomic labels. ### Data Fields #### Metadata Files `catalog.csv`: contains the following metadata associated with each image in the dataset - `split`: indicates which data split the image belongs to (`train`, `val`, or `train_small`), `train_small` is a duplicated subset of `train` and thus should not be included when analyzing overall stats of the dataset. - `treeoflife_id`: unique identifier for the image in the dataset. - `eol_content_id`: unique identifier within EOL database for images sourced from [EOL](https://eol.org). Note that EOL content IDs are not stable. - `eol_page_id`: identifier of page from which images from EOL are sourced. Note that an image's association to a particular page ID may change with updates to the EOL (or image provider's) hierarchy. However, EOL taxon page IDs are stable. - `bioscan_part`: indicates to which of the 113 data chunks of [BIOSCAN-1M](https://github.com/zahrag/BIOSCAN-1M#-iv-rgb-images) each image belongs. Note that there are 10K images per chunk and 8,313 in chunk #113. - `bioscan_filename`: unique identifier within BIOSCAN-1M dataset for images sourced from [BIOSCAN-1M](https://github.com/zahrag/BIOSCAN-1M). - `inat21_filename`: unique identifier within iNat21 dataset for images sourced from [iNat21](https://github.com/visipedia/inat_comp/blob/master/2021/README.md). <!-- (`file_name` given in `images` of the [`train.json`](https://github.com/visipedia/inat_comp/tree/master/2021#annotation-format) `file_name` = "train/#####_Kingdom_Phylum_..._Genus_species/STRING(uuid?).jpg"). `inat21_filename` is the end of the `file_name` string. The taxa are the `cls_name`, and the number is the `cls_num` (leading 0 may be lost here).--> - `inat21_cls_name`: `<Kingdom>_<Phylum>_<Class>_<Order>_<Family>_<Genus>_<species>` as labeled by iNaturalist. - `inat21_cls_num`: Number assigned by iNat21 to the given species (unique identifier for that species within iNat21 dataset). The remaining terms describe the _Linnaean taxonomy_ of the subject of the image; they are sourced as described in [Annotation Process, below](#annotation-process). - `kingdom`: kingdom to which the subject of the image belongs (`Animalia`, `Plantae`, `Fungi`, `Chromista`, `Protozoa`, `Bacteria`, `Viridiplantae`, `Protista`, `Orthornavirae`, `Bamfordvirae`, `Archaea`, or `Shotokuvirae`). Note: this large number of kingdoms are considered in recognition of the fact that there is not agreement on merging them. - `phylum`: phylum to which the subject of the image belongs. - `class`: class to which the subject of the image belongs. - `order`: order to which the subject of the image belongs. - `family`: family to which the subject of the image belongs. - `genus`: genus to which the subject of the image belongs. - `species`: species to which the subject of the image belongs. - `common`: common name associated with the subject of the image where available. Otherwise, this is the scientific name (`genus-species`), else whatever subset of the taxonomic hierarchy is available (eg., `kingdom-phylum-class-order` or `kingdom-phylum-class-order-family`). All images have a non-null entry for this column. Note that the `species` column occasionally has entries such as "sp. ___(get ex)" with some string following. This seems to be used to indicate the species is unknown, but various specimens/images are known to be the same species. Additionally, for `species` values containing an `x` between names, this is indicative of a hybrid that is a cross of the two species listed on either side of the `x`. ##### Text Types | Text Type | Example | | ---- | -------- | | Common | black-billed magpie | | Scientific | _Pica hudsonia_ | | Taxonomic | _Animalia Chordata Aves Passeriformes Corvidae Pica hudsonia_ | `naming/`: these files provide the taxonomic name lookup for each data source in the reconstruction of the dataset. `species_level_taxonomy_chains.csv`: CSV with the ITIS taxonomic hierarchy, indicated as follows: - `hierarchy_string_tsn`: string of Taxonomic Serial Numbers (TSN)* for the names of the ranks provided from highest to lowest, connected by dashes (eg., `202422-846491-660046-846497-846508-846553-954935-5549-5550`). - `hierarchy_string_names`: string of the names of the ranks provided from highest to lowest, connected by arrows (eg., `Plantae->Biliphyta->Rhodophyta->Cyanidiophytina->Cyanidiophyceae->Cyanidiales->Cyanidiaceae->Cyanidium->Cyanidium caldarium`). - `terminal_tsn`: Taxonomic Serial Number (TSN)* of designated species (eg., `5550`). - `terminal_scientific_name`: scientific name (`<Genus> <species>`) of subject. - `terminal_vernacular`: vernacular or common name(s) of the subject, multiple names are separated by commas (eg., `rockskipper`, `Highland Small Rice Rat, Páramo Colilargo`). - `terminal_vernacular_lang`: language(s) of the vernacular name(s) provided; when there are multiple names, language is listed for each, separated by commas (eg., `English`, `English, English`, respectively for the vernacular name examples above). - `hierarchy_string_ranks`: string of ranks provided from highest to lowest, connected by arrows (eg., `Kingdom->Subkingdom->Phylum->Subphylum->Class->Order->Family->Genus->Species`). The remaining columns consist of the hierarchy string ranks describing the Linnaean taxonomy of the subject (as defined above), with `<Genus> <species>` filled in the `Species` column. *ITIS assigns a Taxonomic Serial Number (TSN) to each taxonomic rank; this is a stable and unique ID. `taxon.tab`: Tab-delimited file with taxonomic information for EOL images based on EOL page IDs. - `taxonID`: unique identifier for the file. - `source`: often `<source>:<id>` where the source corresponds to the domain of the `furtherInformationURL`. The ID likely corresponds to an ID at the source. - `furtherInformationURL`: URL with more information on the indicated taxon. - `acceptedNameUsageID`: `taxonID` for the name accepted to represent this entry. Less than a third of these are non-null - `parentNameUsageID`: `taxonID` of taxonomic rank above the indicated `taxonRank` in the hierarchy (eg., the `taxonID` of the genus `Atadinus` for the `Atadinus fallax (Boiss.) Hauenschild` entry). - `scientificName`: scientific name associated with the EOL page (`<canonicalName> <authority>`, authority as available). - `taxonRank`: lowest rank of the taxonomic tree indicated (eg., `genus` or `species`), occasionally not indicated, even for accepted names. - `taxonomicStatus`: whether the name is accepted by EOL or not (`accepted` or `not accepted`, correspond to existence of non-null `eolID` or `acceptedNameUsageID` entry, respectively). - `datasetID`: generally corresponds to the source identified in `source` column. - `canonicalName`: the name(s) associate with the `taxonRank` (eg., `<Genus> <species>` for species). - `authority`: usually name of person who assigned the name, with the year as available. - `eolID`: the EOL page ID (only non-null when `taxonomicStatus` is accepted by EOL). - `Landmark`: numeric values, meaning unknown, mostly null. - `higherClassification`: labeling in the EOL Dynamic Hierarchy above the `taxonRank` (eg., `Life|Cellular Organisms|Eukaryota|Opisthokonta|Metazoa|Bilateria|Protostomia|Ecdysozoa|Arthropoda|Pancrustacea|Hexapoda|Insecta|Pterygota|Neoptera|Endopterygota|Coleoptera|Adephaga|Carabidae|Paussus`). `licenses.csv`: File with license, source, and copyright holder associated to each image from EOL listed in `catalog.csv`; `treeoflife_id` is the shared unique identifier to link the two files. Columns are - `treeoflife_id`, `eol_content_id`, and `eol_page_id` are as defined above. - `md5`: MD5 hash of the image. - `medium_source_url`: URL pointing to source of image. - `eol_full_size_copy_url`: URL to access the full-sized image; this is the URL from which the image was downloaded for this dataset (see [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) for more information on this process). - `license_name`: name of license attached to the image (eg., `cc-by`). - `copyright_owner`: copyright holder for the image, filled with `not provided` if no copyright owner was provided. - `license_link`: URL to the listed license, left null in the case that `License Name` is `No known copyright restrictions`. - `title`: title provided for the image, filled with `not provided` if no title was provided. ### Data Splits As noted above, the `split` column of `catalog.csv` indicates to which split each image belongs. Note that `train_small` is a 1M-image, uniformly sampled, subset of `train` used for fine-tuned ablation training and all entries with this label are also listed with the `train` label. The `val` label is applied to images used for validation. 10 biologically-relevant datasets were used for various tests of [BioCLIP](https://huggingface.co/imageomics/bioclip) (which was trained on this dataset), they are described (briefly) and linked to below. #### Test Sets - [Meta-Album](https://paperswithcode.com/dataset/meta-album): Specifically, we used the Plankton, Insects, Insects 2, PlantNet, Fungi, PlantVillage, Medicinal Leaf, and PlantDoc datasets from Set-0 through Set-2 (Set-3 was still not released as of our publication/evaluation (Nov. 2023). - [Birds 525](https://www.kaggle.com/datasets/gpiosenka/100-bird-species): We evaluated on the 2,625 test images provided with the dataset. - [Rare Species](https://huggingface.co/datasets/imageomics/rare-species): A new dataset we curated for the purpose of testing this model and to contribute to the ML for Conservation community. It consists of 400 species labeled Near Threatened through Extinct in the Wild by the [IUCN Red List](https://www.iucnredlist.org/), with 30 images per species. For more information, see our dataset, [Rare Species](https://huggingface.co/datasets/imageomics/rare-species). For more information about the contents of these datasets, see Table 2 and associated sections of [our paper](https://doi.org/10.48550/arXiv.2311.18803). ## Dataset Creation ### Curation Rationale Previously, the largest ML-ready biology image dataset was [iNat21](https://github.com/visipedia/inat_comp/tree/master/2021), which consists of 2.7M images of 10K species. This is significant breadth when comparing to popular general-domain datasets, such as [ImageNet-1K](https://huggingface.co/datasets/imagenet-1k); 10K species are rather limited when considering the vast scope of biology. For context, in 2022, [The International Union for Conservation of Nature (IUCN)](https://www.iucnredlist.org/) reported over 2M total described species, with over 10K distinct species of birds and reptiles alone. Thus, the lesser species diversity of iNat21 limits its potential for pre-training a foundation model for the entire tree of life. With this focus on species diversity and the need for high-quality images of biological organisms, we looked to the [Encyclopedia of Life Project (EOL)](https://eol.org/). EOL is an image aggregator that collaborates with a variety of institutions to source and label millions of images. After downloading 6.6M images from EOL, we were able to expand our dataset to cover an additional 440K taxa. Insects (of the class Insecta with 1M+ species), birds (of the class Aves with 10K+ species) and reptiles (of the class Reptilia with 10K+ species) are examples of highly diverse subtrees with many more species than other taxonomic classes. This imbalance among subtrees in the tree of life present challenges in training a foundation model that can recognize extremely fine-grained visual representations of these classes. To help address this challenge for insects, we incorporated [BIOSCAN-1M](https://zenodo.org/doi/10.5281/zenodo.8030064), a recent dataset of 1M expert-labeled lab images of insects, covering 494 different families. The added variety of lab images, rather than in situ images (as in iNat21), further diversifies the _image_ distribution of TreeOfLife-10M. Overall, this dataset contains approximately 454K unique taxonomic labels of the more than 2M recorded by [IUCN](iucnredlist.org) in 2022. To the best of our knowledge, this is still the most diverse and largest such ML-ready dataset available, hence our curation. ### Source Data [iNat21 data](https://github.com/visipedia/inat_comp/tree/master/2021#data) was downloaded, unzipped, and our compilation scripts pointed to the training split. As per their [terms of use](https://github.com/visipedia/inat_comp/tree/master/2021#terms-of-use), the data is catalogued, but not reproduced, here. [BIOSCAN-1M](https://zenodo.org/doi/10.5281/zenodo.8030064): Collection of insect images hand-labeled by experts. [EOL](https://eol.org/): Biological image aggregator. #### Initial Data Collection and Normalization [iNat21 training data](https://github.com/visipedia/inat_comp/tree/master/2021#data) and [BIOSCAN-1M data](https://zenodo.org/doi/10.5281/zenodo.8030064) were downloaded and assigned `treeoflife_id`s for unique identification within the TreeOfLife-10M dataset. The iNat21 training data is formatted into a webdataset format prior to `treeoflife_id` assignments, since this is also used for a comparison to [BioCLIP](https://huggingface.co/imageomics/bioclip) as trained on the full TreeOfLife-10M dataset. For more detailed information on this process, please see [How to Create TreeOfLife-10M](https://github.com/Imageomics/bioclip/tree/main/docs/imageomics/treeoflife10m.md#how-to-create-treeoflife-10m) in the BioCLIP GitHub repo. First, media manifest data was sourced from EOL using [this script](https://github.com/Imageomics/bioclip/blob/main/scripts/get_media_manifest.py). The media manifest includes EOL content and page IDs from which to connect the taxonomic information, along with source URLs and licensing information. The `EOL Full-Size Copy URL` was then used to download all the images, naming each `<eol_content_id>_<eol_page_id>_eol_full-size-copy.jpg` for reference back to the media manifest. [Scripts](https://github.com/Imageomics/bioclip/tree/main/scripts/evobio10m) to perform these downloads and [instructions](https://github.com/Imageomics/bioclip/blob/main/docs/imageomics/treeoflife10m.md) can be found in the [BioCLIP GitHub repository](https://github.com/Imageomics/bioclip). See [below](#Annotation-Process) for details of annotation following data collection. Species selected for the Rare Species dataset were removed from this dataset (see [Initial Data Collection and Normalization of Rare Species](https://huggingface.co/datasets/imageomics/rare-species#initial-data-collection-and-normalization)). ### Annotations #### Annotation Process Annotations were primarily sourced from image source providers. For iNat21 and BIOSCAN-1M images, the labels provided by those sources were used. - iNat21: iNaturalist English vernacular names and taxa were used. - BIOSCAN-1M: Linnaean taxonomic rankings were applied as labeled in the [BIOSCAN-1M dataset](https://zenodo.org/doi/10.5281/zenodo.8030064), which is all hand-labeled by experts. Note that the dataset provides other ranks (not considered in the 7-rank Linnaean taxonomy), such as tribe, which were not included in this dataset. For images from EOL, the scientific name (`genus-species`) was used to look up the higher-order taxa from the following sources as listed: BIOSCAN-1M metadata, EOL aggregate datasets (described below), then match this against the ITIS hierarchy for the higher-order taxa standardization. A small number of these are [homonyms](https://en.wikipedia.org/wiki/Homonym_(biology)), for which a list was generated to ensure proper matching of higher-order taxa (manual homonym resolution is in class `NameUpgrader` in the [naming script](https://github.com/Imageomics/bioclip/blob/main/src/imageomics/naming.py)). After these resources were exhausted, any remaining unresolved taxa were fed through the [Global Names Resolver (GNR) API](https://resolver.globalnames.org/api). Despite our efforts, we discovered after training that some hemihomonyms were mislabeled at higher-level taxa (family up to kingdom). This impacts approximately 0.1-0.2% of our data. We are in the process of developing a more robust solution to taxonomic labeling which will also account for re-naming (as is currently in process for many bird species). We intend to release a patch alongside the solution. This process allowed us to reach full taxa labels for 84% of images. To put this in perspective, 10% of images in TreeOfLife-10M are only labeled to the `family` level (no `genus-species` designations) as part of BIOSCAN-1M, so this places a cap on the taxa coverage. Taxonomic ranking also is not entirely standardized and agreed-upon throughout the biology community, so most gaps are more indicative of lack of consensus on label than missing information. #### Who are the annotators? Samuel Stevens, Jiaman Wu, Matthew J. Thompson, and Elizabeth G. Campolongo ### Personal and Sensitive Information N/A ## Considerations for Using the Data ### Social Impact of Dataset The hope is that this dataset could be helpful in conservation efforts or biodiversity research. ### Discussion of Biases and Other Known Limitations This dataset is imbalanced in its representation of various species with the greatest representation available for those in the phyla _Arthropoda_, _Tracheophyta_, and _Chordata_ (see our [interactive treemap from phylum to family](https://huggingface.co/imageomics/treeoflife-10m/raw/main/phyla_ToL_tree.html) for further details of this distribution). This class imbalance is both a result of availability of images and actual variance in class diversity. Additionally, as noted above, there are 2M+ estimated species according to [IUCN](iucnredlist.org), so overall taxonomic coverage is still limited (though it far surpasses the species diversity of other well-known animal datasets). Not all data is labeled to the species level, and some entries are more or less precise. For instance, the `species` column occasionally has entries such as "sp. ___(get ex)" with some string following. This seems to be used to indicate the species is unknown, but various specimens/images are known to be the same species. Additionally, for `species` values containing an `x` between names, this is indicative of a hybrid that is a cross of the two species listed on either side of the `x`. Due to the additional information provided about the higher order taxa, these labeling anomalies still present valuable information providing links between these classes. As stated above, 84% of images have full taxa labels. However, due to the incomplete standardization and agreement on the taxonomic hierarchy throughout the biology community, most gaps are more indicative of lack of consensus on label than missing information. Note that BIOSCAN-1M’s label granularity may still be limited for insects, as 98.6% of BIOSCAN-1M’s images are labeled to the family level but only 22.5% and 7.5% of the images have genus or species indicated, respectively. Lack of label granularity is an inherent challenge. ## Additional Information ### Dataset Curators Samuel Stevens, Jiaman Wu, Matthew J. Thompson, and Elizabeth G. Campolongo ### Licensing Information The data (images and text) contain a variety of licensing restrictions mostly within the CC family. Each image and text in this dataset is provided under the least restrictive terms allowed by its licensing requirements as provided to us (i.e, we impose no additional restrictions past those specified by licenses in the license file). Please see the [iNat21 terms of use](https://github.com/visipedia/inat_comp/tree/master/2021#terms-of-use) for full information on use of their images. All BIOSCAN-1M images are licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/). EOL images contain a variety of licenses ranging from [CC0](https://creativecommons.org/publicdomain/zero/1.0/) to [CC BY-NC-SA](https://creativecommons.org/licenses/by-nc-sa/4.0/). For license and citation information by image, see our [license file](https://huggingface.co/datasets/imageomics/treeoflife-10m/blob/main/metadata/licenses.csv). **Note**: Due to licensing restrictions discovered after training, approximately 30K of the images used to train BioCLIP (about 0.3%) cannot be republished here and links to original content are no longer available. Overall, 14 families that were included in training BioCLIP are not republished in this dataset, a loss of 0.38% of the taxa diversity. This dataset (the compilation) has been marked as dedicated to the public domain by applying the [CC0 Public Domain Waiver](https://creativecommons.org/publicdomain/zero/1.0/). However, images may be licensed under different terms (as noted above). ### Citation Information ``` @dataset{treeoflife_10m, author = {Samuel Stevens and Jiaman Wu and Matthew J Thompson and Elizabeth G Campolongo and Chan Hee Song and David Edward Carlyn and Li Dong and Wasila M Dahdul and Charles Stewart and Tanya Berger-Wolf and Wei-Lun Chao and Yu Su}, title = {TreeOfLife-10M}, year = {2023}, url = {https://huggingface.co/datasets/imageomics/TreeOfLife-10M}, doi = {10.57967/hf/1972}, publisher = {Hugging Face} } ``` Please also cite our paper: ``` @inproceedings{stevens2024bioclip, title = {{B}io{CLIP}: A Vision Foundation Model for the Tree of Life}, author = {Samuel Stevens and Jiaman Wu and Matthew J Thompson and Elizabeth G Campolongo and Chan Hee Song and David Edward Carlyn and Li Dong and Wasila M Dahdul and Charles Stewart and Tanya Berger-Wolf and Wei-Lun Chao and Yu Su}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {19412-19424} } ``` Please be sure to also cite the original data sources and all constituent parts as appropriate. - iNat21: ``` @misc{inat2021, author={Van Horn, Grant and Mac Aodha, Oisin}, title={iNat Challenge 2021 - FGVC8}, publisher={Kaggle}, year={2021}, url={https://kaggle.com/competitions/inaturalist-2021} } ``` - BIOSCAN-1M: ``` @inproceedings{gharaee2023step, title={A Step Towards Worldwide Biodiversity Assessment: The {BIOSCAN-1M} Insect Dataset}, booktitle = {Advances in Neural Information Processing Systems ({NeurIPS}) Datasets \& Benchmarks Track}, author={Gharaee, Z. and Gong, Z. and Pellegrino, N. and Zarubiieva, I. and Haurum, J. B. and Lowe, S. C. and McKeown, J. T. A. and Ho, C. Y. and McLeod, J. and Wei, Y. C. and Agda, J. and Ratnasingham, S. and Steinke, D. and Chang, A. X. and Taylor, G. W. and Fieguth, P.}, year={2023}, } ``` - EOL: Encyclopedia of Life. Available from http://eol.org. Accessed 29 July 2023. For license and citation information by image, see our [license file](https://huggingface.co/datasets/imageomics/treeoflife-10m/blob/main/metadata/licenses.csv). - ITIS: Retrieved July, 20 2023, from the Integrated Taxonomic Information System (ITIS) on-line database, www.itis.gov, CC0 https://doi.org/10.5066/F7KH0KBK ### Contributions The [Imageomics Institute](https://imageomics.org) is funded by the US National Science Foundation's Harnessing the Data Revolution (HDR) program under [Award #2118240](https://www.nsf.gov/awardsearch/showAward?AWD_ID=2118240) (Imageomics: A New Frontier of Biological Information Powered by Knowledge-Guided Machine Learning). Any opinions, findings and conclusions or recommendations expressed in this material are those of the author(s) and do not necessarily reflect the views of the National Science Foundation.

boettiger-lab/ca-30x30

boettiger-lab

--- license: bsd-2-clause ---

eriktks/conll2003

eriktks

--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - extended|other-reuters-corpus task_categories: - token-classification task_ids: - named-entity-recognition - part-of-speech paperswithcode_id: conll-2003 pretty_name: CoNLL-2003 dataset_info: features: - name: id dtype: string - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': '"' '1': '''''' '2': '#' '3': $ '4': ( '5': ) '6': ',' '7': . '8': ':' '9': '``' '10': CC '11': CD '12': DT '13': EX '14': FW '15': IN '16': JJ '17': JJR '18': JJS '19': LS '20': MD '21': NN '22': NNP '23': NNPS '24': NNS '25': NN|SYM '26': PDT '27': POS '28': PRP '29': PRP$ '30': RB '31': RBR '32': RBS '33': RP '34': SYM '35': TO '36': UH '37': VB '38': VBD '39': VBG '40': VBN '41': VBP '42': VBZ '43': WDT '44': WP '45': WP$ '46': WRB - name: chunk_tags sequence: class_label: names: '0': O '1': B-ADJP '2': I-ADJP '3': B-ADVP '4': I-ADVP '5': B-CONJP '6': I-CONJP '7': B-INTJ '8': I-INTJ '9': B-LST '10': I-LST '11': B-NP '12': I-NP '13': B-PP '14': I-PP '15': B-PRT '16': I-PRT '17': B-SBAR '18': I-SBAR '19': B-UCP '20': I-UCP '21': B-VP '22': I-VP - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC '7': B-MISC '8': I-MISC config_name: conll2003 splits: - name: train num_bytes: 6931345 num_examples: 14041 - name: validation num_bytes: 1739223 num_examples: 3250 - name: test num_bytes: 1582054 num_examples: 3453 download_size: 982975 dataset_size: 10252622 train-eval-index: - config: conll2003 task: token-classification task_id: entity_extraction splits: train_split: train eval_split: test col_mapping: tokens: tokens ner_tags: tags metrics: - type: seqeval name: seqeval --- # Dataset Card for "conll2003" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://www.aclweb.org/anthology/W03-0419/](https://www.aclweb.org/anthology/W03-0419/) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 4.85 MB - **Size of the generated dataset:** 10.26 MB - **Total amount of disk used:** 15.11 MB ### Dataset Summary The shared task of CoNLL-2003 concerns language-independent named entity recognition. We will concentrate on four types of named entities: persons, locations, organizations and names of miscellaneous entities that do not belong to the previous three groups. The CoNLL-2003 shared task data files contain four columns separated by a single space. Each word has been put on a separate line and there is an empty line after each sentence. The first item on each line is a word, the second a part-of-speech (POS) tag, the third a syntactic chunk tag and the fourth the named entity tag. The chunk tags and the named entity tags have the format I-TYPE which means that the word is inside a phrase of type TYPE. Only if two phrases of the same type immediately follow each other, the first word of the second phrase will have tag B-TYPE to show that it starts a new phrase. A word with tag O is not part of a phrase. Note the dataset uses IOB2 tagging scheme, whereas the original dataset uses IOB1. For more details see https://www.clips.uantwerpen.be/conll2003/ner/ and https://www.aclweb.org/anthology/W03-0419 ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### conll2003 - **Size of downloaded dataset files:** 4.85 MB - **Size of the generated dataset:** 10.26 MB - **Total amount of disk used:** 15.11 MB An example of 'train' looks as follows. ``` { "chunk_tags": [11, 12, 12, 21, 13, 11, 11, 21, 13, 11, 12, 13, 11, 21, 22, 11, 12, 17, 11, 21, 17, 11, 12, 12, 21, 22, 22, 13, 11, 0], "id": "0", "ner_tags": [0, 3, 4, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "pos_tags": [12, 22, 22, 38, 15, 22, 28, 38, 15, 16, 21, 35, 24, 35, 37, 16, 21, 15, 24, 41, 15, 16, 21, 21, 20, 37, 40, 35, 21, 7], "tokens": ["The", "European", "Commission", "said", "on", "Thursday", "it", "disagreed", "with", "German", "advice", "to", "consumers", "to", "shun", "British", "lamb", "until", "scientists", "determine", "whether", "mad", "cow", "disease", "can", "be", "transmitted", "to", "sheep", "."] } ``` The original data files have `-DOCSTART-` lines used to separate documents, but these lines are removed here. Indeed `-DOCSTART-` is a special line that acts as a boundary between two different documents, and it is filtered out in this implementation. ### Data Fields The data fields are the same among all splits. #### conll2003 - `id`: a `string` feature. - `tokens`: a `list` of `string` features. - `pos_tags`: a `list` of classification labels (`int`). Full tagset with indices: ```python {'"': 0, "''": 1, '#': 2, '$': 3, '(': 4, ')': 5, ',': 6, '.': 7, ':': 8, '``': 9, 'CC': 10, 'CD': 11, 'DT': 12, 'EX': 13, 'FW': 14, 'IN': 15, 'JJ': 16, 'JJR': 17, 'JJS': 18, 'LS': 19, 'MD': 20, 'NN': 21, 'NNP': 22, 'NNPS': 23, 'NNS': 24, 'NN|SYM': 25, 'PDT': 26, 'POS': 27, 'PRP': 28, 'PRP$': 29, 'RB': 30, 'RBR': 31, 'RBS': 32, 'RP': 33, 'SYM': 34, 'TO': 35, 'UH': 36, 'VB': 37, 'VBD': 38, 'VBG': 39, 'VBN': 40, 'VBP': 41, 'VBZ': 42, 'WDT': 43, 'WP': 44, 'WP$': 45, 'WRB': 46} ``` - `chunk_tags`: a `list` of classification labels (`int`). Full tagset with indices: ```python {'O': 0, 'B-ADJP': 1, 'I-ADJP': 2, 'B-ADVP': 3, 'I-ADVP': 4, 'B-CONJP': 5, 'I-CONJP': 6, 'B-INTJ': 7, 'I-INTJ': 8, 'B-LST': 9, 'I-LST': 10, 'B-NP': 11, 'I-NP': 12, 'B-PP': 13, 'I-PP': 14, 'B-PRT': 15, 'I-PRT': 16, 'B-SBAR': 17, 'I-SBAR': 18, 'B-UCP': 19, 'I-UCP': 20, 'B-VP': 21, 'I-VP': 22} ``` - `ner_tags`: a `list` of classification labels (`int`). Full tagset with indices: ```python {'O': 0, 'B-PER': 1, 'I-PER': 2, 'B-ORG': 3, 'I-ORG': 4, 'B-LOC': 5, 'I-LOC': 6, 'B-MISC': 7, 'I-MISC': 8} ``` ### Data Splits | name |train|validation|test| |---------|----:|---------:|---:| |conll2003|14041| 3250|3453| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information From the [CoNLL2003 shared task](https://www.clips.uantwerpen.be/conll2003/ner/) page: > The English data is a collection of news wire articles from the Reuters Corpus. The annotation has been done by people of the University of Antwerp. Because of copyright reasons we only make available the annotations. In order to build the complete data sets you will need access to the Reuters Corpus. It can be obtained for research purposes without any charge from NIST. The copyrights are defined below, from the [Reuters Corpus page](https://trec.nist.gov/data/reuters/reuters.html): > The stories in the Reuters Corpus are under the copyright of Reuters Ltd and/or Thomson Reuters, and their use is governed by the following agreements: > > [Organizational agreement](https://trec.nist.gov/data/reuters/org_appl_reuters_v4.html) > > This agreement must be signed by the person responsible for the data at your organization, and sent to NIST. > > [Individual agreement](https://trec.nist.gov/data/reuters/ind_appl_reuters_v4.html) > > This agreement must be signed by all researchers using the Reuters Corpus at your organization, and kept on file at your organization. ### Citation Information ``` @inproceedings{tjong-kim-sang-de-meulder-2003-introduction, title = "Introduction to the {C}o{NLL}-2003 Shared Task: Language-Independent Named Entity Recognition", author = "Tjong Kim Sang, Erik F. and De Meulder, Fien", booktitle = "Proceedings of the Seventh Conference on Natural Language Learning at {HLT}-{NAACL} 2003", year = "2003", url = "https://www.aclweb.org/anthology/W03-0419", pages = "142--147", } ``` ### Contributions Thanks to [@jplu](https://github.com/jplu), [@vblagoje](https://github.com/vblagoje), [@lhoestq](https://github.com/lhoestq) for adding this dataset.

japanese-asr/whisper_transcriptions.mls.wer_10.0.vectorized

japanese-asr

--- dataset_info: - config_name: subset_0 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95550219596 num_examples: 62101 download_size: 43092578892 dataset_size: 95550219596 - config_name: subset_1 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95892233884 num_examples: 62323 download_size: 43217224829 dataset_size: 95892233884 - config_name: subset_10 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659534424 num_examples: 62172 download_size: 43197712726 dataset_size: 95659534424 - config_name: subset_100 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95570234896 num_examples: 62114 download_size: 43084233453 dataset_size: 95570234896 - config_name: subset_101 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95741000524 num_examples: 62225 download_size: 43183665345 dataset_size: 95741000524 - config_name: subset_102 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95732487892 num_examples: 62219 download_size: 43229537725 dataset_size: 95732487892 - config_name: subset_103 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95776664816 num_examples: 62248 download_size: 43187441638 dataset_size: 95776664816 - config_name: subset_104 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95930500816 num_examples: 62348 download_size: 43294625977 dataset_size: 95930500816 - config_name: subset_105 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95836868972 num_examples: 62287 download_size: 43251807028 dataset_size: 95836868972 - config_name: subset_106 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95940716900 num_examples: 62355 download_size: 43289304103 dataset_size: 95940716900 - config_name: subset_107 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95782476488 num_examples: 62252 download_size: 43209137820 dataset_size: 95782476488 - config_name: subset_108 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 96007104792 num_examples: 62398 download_size: 43221018658 dataset_size: 96007104792 - config_name: subset_109 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95764776944 num_examples: 62240 download_size: 43162176171 dataset_size: 95764776944 - config_name: subset_11 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95749669360 num_examples: 62230 download_size: 43193067430 dataset_size: 95749669360 - config_name: subset_110 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95826353540 num_examples: 62281 download_size: 43217482451 dataset_size: 95826353540 - config_name: subset_111 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95910493660 num_examples: 62335 download_size: 43268379463 dataset_size: 95910493660 - config_name: subset_112 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95782539616 num_examples: 62252 download_size: 43198507530 dataset_size: 95782539616 - config_name: subset_113 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95496693376 num_examples: 62066 download_size: 43106662052 dataset_size: 95496693376 - config_name: subset_114 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 16920876 num_examples: 11 download_size: 7573002 dataset_size: 16920876 - config_name: subset_115 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95639177564 num_examples: 62159 download_size: 43180784518 dataset_size: 95639177564 - config_name: subset_116 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95625267448 num_examples: 62150 download_size: 43124129761 dataset_size: 95625267448 - config_name: subset_117 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95545048296 num_examples: 62098 download_size: 43082968259 dataset_size: 95545048296 - config_name: subset_118 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95866827908 num_examples: 62307 download_size: 43167164098 dataset_size: 95866827908 - config_name: subset_119 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 96068332252 num_examples: 62437 download_size: 43339136980 dataset_size: 96068332252 - config_name: subset_12 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95728691164 num_examples: 62217 download_size: 43198747627 dataset_size: 95728691164 - config_name: subset_120 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95722632700 num_examples: 62213 download_size: 43167373358 dataset_size: 95722632700 - config_name: subset_121 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95732191100 num_examples: 62219 download_size: 43221505796 dataset_size: 95732191100 - config_name: subset_122 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95699024432 num_examples: 62198 download_size: 43219580053 dataset_size: 95699024432 - config_name: subset_123 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95713523564 num_examples: 62207 download_size: 43177149081 dataset_size: 95713523564 - config_name: subset_124 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95463256840 num_examples: 62044 download_size: 43081995426 dataset_size: 95463256840 - config_name: subset_125 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95597812312 num_examples: 62132 download_size: 43093919552 dataset_size: 95597812312 - config_name: subset_126 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95798796016 num_examples: 62262 download_size: 43254288601 dataset_size: 95798796016 - config_name: subset_127 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95674872576 num_examples: 62182 download_size: 43251503801 dataset_size: 95674872576 - config_name: subset_128 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95741950380 num_examples: 62225 download_size: 43150675085 dataset_size: 95741950380 - config_name: subset_129 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95902821264 num_examples: 62330 download_size: 43266797081 dataset_size: 95902821264 - config_name: subset_13 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95706484544 num_examples: 62202 download_size: 43194357797 dataset_size: 95706484544 - config_name: subset_130 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 13845812 num_examples: 9 download_size: 6597728 dataset_size: 13845812 - config_name: subset_131 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95385820008 num_examples: 61994 download_size: 43049793791 dataset_size: 95385820008 - config_name: subset_132 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95718111696 num_examples: 62210 download_size: 43160367467 dataset_size: 95718111696 - config_name: subset_133 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95642427284 num_examples: 62161 download_size: 43145455128 dataset_size: 95642427284 - config_name: subset_134 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95783162736 num_examples: 62252 download_size: 43157288094 dataset_size: 95783162736 - config_name: subset_135 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95905643680 num_examples: 62332 download_size: 43211878248 dataset_size: 95905643680 - config_name: subset_136 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95602572980 num_examples: 62135 download_size: 43148250609 dataset_size: 95602572980 - config_name: subset_137 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95742569912 num_examples: 62226 download_size: 43196126465 dataset_size: 95742569912 - config_name: subset_138 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95784277468 num_examples: 62253 download_size: 43213036863 dataset_size: 95784277468 - config_name: subset_14 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95484035440 num_examples: 62058 download_size: 43038787620 dataset_size: 95484035440 - config_name: subset_15 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95847923004 num_examples: 62295 download_size: 43269622880 dataset_size: 95847923004 - config_name: subset_16 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143676345616 num_examples: 93380 download_size: 64763101794 dataset_size: 143676345616 - config_name: subset_17 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143218562076 num_examples: 93081 download_size: 64543519703 dataset_size: 143218562076 - config_name: subset_18 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 1538508 num_examples: 1 download_size: 888657 dataset_size: 1538508 - config_name: subset_19 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143234313008 num_examples: 93092 download_size: 64590945738 dataset_size: 143234313008 - config_name: subset_2 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95692976304 num_examples: 62194 download_size: 43156432229 dataset_size: 95692976304 - config_name: subset_20 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143387469416 num_examples: 93192 download_size: 64657130955 dataset_size: 143387469416 - config_name: subset_21 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143761745188 num_examples: 93435 download_size: 64848639452 dataset_size: 143761745188 - config_name: subset_22 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143510788288 num_examples: 93272 download_size: 64664207735 dataset_size: 143510788288 - config_name: subset_23 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143745597332 num_examples: 93425 download_size: 64881327829 dataset_size: 143745597332 - config_name: subset_24 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143524148912 num_examples: 93280 download_size: 64658212505 dataset_size: 143524148912 - config_name: subset_25 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143893466228 num_examples: 93521 download_size: 64887011756 dataset_size: 143893466228 - config_name: subset_26 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143679361468 num_examples: 93381 download_size: 64845399473 dataset_size: 143679361468 - config_name: subset_27 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143578388120 num_examples: 93316 download_size: 64733082218 dataset_size: 143578388120 - config_name: subset_28 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143336154232 num_examples: 93158 download_size: 64663766459 dataset_size: 143336154232 - config_name: subset_29 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 7691452 num_examples: 5 download_size: 3459998 dataset_size: 7691452 - config_name: subset_3 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95679747492 num_examples: 62185 download_size: 43162138038 dataset_size: 95679747492 - config_name: subset_30 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143445434128 num_examples: 93230 download_size: 64632174781 dataset_size: 143445434128 - config_name: subset_31 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143557489496 num_examples: 93302 download_size: 64701593443 dataset_size: 143557489496 - config_name: subset_32 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143480746600 num_examples: 93252 download_size: 64739797925 dataset_size: 143480746600 - config_name: subset_33 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143804688340 num_examples: 93463 download_size: 64883427549 dataset_size: 143804688340 - config_name: subset_34 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143763133852 num_examples: 93435 download_size: 64878027444 dataset_size: 143763133852 - config_name: subset_35 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143471499924 num_examples: 93247 download_size: 64668279919 dataset_size: 143471499924 - config_name: subset_36 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143578658920 num_examples: 93316 download_size: 64771308961 dataset_size: 143578658920 - config_name: subset_37 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143421843384 num_examples: 93214 download_size: 64702071071 dataset_size: 143421843384 - config_name: subset_38 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143684196348 num_examples: 93385 download_size: 64784473635 dataset_size: 143684196348 - config_name: subset_39 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143680679576 num_examples: 93382 download_size: 64742283095 dataset_size: 143680679576 - config_name: subset_4 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95688480364 num_examples: 62191 download_size: 43186075154 dataset_size: 95688480364 - config_name: subset_40 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 12306560 num_examples: 8 download_size: 5824713 dataset_size: 12306560 - config_name: subset_41 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143692662464 num_examples: 93390 download_size: 64709902673 dataset_size: 143692662464 - config_name: subset_42 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143203990624 num_examples: 93072 download_size: 64613043749 dataset_size: 143203990624 - config_name: subset_43 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143423685888 num_examples: 93216 download_size: 64706208398 dataset_size: 143423685888 - config_name: subset_44 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143599898184 num_examples: 93330 download_size: 64731002218 dataset_size: 143599898184 - config_name: subset_45 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143523564744 num_examples: 93280 download_size: 64697514930 dataset_size: 143523564744 - config_name: subset_46 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143657253604 num_examples: 93367 download_size: 64832235795 dataset_size: 143657253604 - config_name: subset_47 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143635083108 num_examples: 93353 download_size: 64816566584 dataset_size: 143635083108 - config_name: subset_48 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143498198048 num_examples: 93264 download_size: 64761835832 dataset_size: 143498198048 - config_name: subset_49 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95628254736 num_examples: 62152 download_size: 43114668093 dataset_size: 95628254736 - config_name: subset_5 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95761408264 num_examples: 62238 download_size: 43098449131 dataset_size: 95761408264 - config_name: subset_50 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95710114492 num_examples: 62205 download_size: 43145722727 dataset_size: 95710114492 - config_name: subset_51 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95718176136 num_examples: 62210 download_size: 43219455050 dataset_size: 95718176136 - config_name: subset_52 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95945517480 num_examples: 62358 download_size: 43266431091 dataset_size: 95945517480 - config_name: subset_53 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659331056 num_examples: 62172 download_size: 43159537104 dataset_size: 95659331056 - config_name: subset_54 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95733778168 num_examples: 62220 download_size: 43168252529 dataset_size: 95733778168 - config_name: subset_55 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95529164348 num_examples: 62087 download_size: 43137593293 dataset_size: 95529164348 - config_name: subset_56 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 12308272 num_examples: 8 download_size: 6100142 dataset_size: 12308272 - config_name: subset_57 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95725368820 num_examples: 62215 download_size: 43172851860 dataset_size: 95725368820 - config_name: subset_58 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95675366136 num_examples: 62182 download_size: 43119589688 dataset_size: 95675366136 - config_name: subset_59 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95757684168 num_examples: 62236 download_size: 43189671985 dataset_size: 95757684168 - config_name: subset_6 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95578098092 num_examples: 62119 download_size: 43139859949 dataset_size: 95578098092 - config_name: subset_60 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95700890356 num_examples: 62199 download_size: 43168843386 dataset_size: 95700890356 - config_name: subset_61 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95730743624 num_examples: 62218 download_size: 43225423665 dataset_size: 95730743624 - config_name: subset_62 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95939249240 num_examples: 62354 download_size: 43194512512 dataset_size: 95939249240 - config_name: subset_63 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95771529340 num_examples: 62245 download_size: 43196958015 dataset_size: 95771529340 - config_name: subset_64 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95848159444 num_examples: 62295 download_size: 43215788957 dataset_size: 95848159444 - config_name: subset_65 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95882062420 num_examples: 62317 download_size: 43207070631 dataset_size: 95882062420 - config_name: subset_66 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95871828072 num_examples: 62310 download_size: 43225588983 dataset_size: 95871828072 - config_name: subset_67 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95709466896 num_examples: 62204 download_size: 43120587410 dataset_size: 95709466896 - config_name: subset_68 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95761289000 num_examples: 62238 download_size: 43168961328 dataset_size: 95761289000 - config_name: subset_69 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95724204184 num_examples: 62214 download_size: 43179130241 dataset_size: 95724204184 - config_name: subset_7 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 1538156 num_examples: 1 download_size: 820398 dataset_size: 1538156 - config_name: subset_70 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95609034668 num_examples: 62139 download_size: 43117847437 dataset_size: 95609034668 - config_name: subset_71 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95387596792 num_examples: 61996 download_size: 43021151166 dataset_size: 95387596792 - config_name: subset_72 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 4615244 num_examples: 3 download_size: 2452533 dataset_size: 4615244 - config_name: subset_73 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95846947264 num_examples: 62294 download_size: 43209608729 dataset_size: 95846947264 - config_name: subset_74 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95818688740 num_examples: 62275 download_size: 43205934001 dataset_size: 95818688740 - config_name: subset_75 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95775232460 num_examples: 62247 download_size: 43190536605 dataset_size: 95775232460 - config_name: subset_76 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95665581880 num_examples: 62176 download_size: 43152943289 dataset_size: 95665581880 - config_name: subset_77 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95538306996 num_examples: 62093 download_size: 43186488482 dataset_size: 95538306996 - config_name: subset_78 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95653366336 num_examples: 62168 download_size: 43143452346 dataset_size: 95653366336 - config_name: subset_79 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95676339900 num_examples: 62183 download_size: 43128557833 dataset_size: 95676339900 - config_name: subset_8 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95715343992 num_examples: 62208 download_size: 43164885461 dataset_size: 95715343992 - config_name: subset_80 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95766599296 num_examples: 62242 download_size: 43239930128 dataset_size: 95766599296 - config_name: subset_81 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143321630332 num_examples: 93149 download_size: 64626209893 dataset_size: 143321630332 - config_name: subset_82 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143413608572 num_examples: 93209 download_size: 64621538517 dataset_size: 143413608572 - config_name: subset_83 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143531418364 num_examples: 93285 download_size: 64801287818 dataset_size: 143531418364 - config_name: subset_84 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143436760360 num_examples: 93224 download_size: 64683558260 dataset_size: 143436760360 - config_name: subset_85 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143693790772 num_examples: 93391 download_size: 64884349404 dataset_size: 143693790772 - config_name: subset_86 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143485525272 num_examples: 93256 download_size: 64696999488 dataset_size: 143485525272 - config_name: subset_87 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143365510504 num_examples: 93178 download_size: 64633922570 dataset_size: 143365510504 - config_name: subset_88 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143459907372 num_examples: 93239 download_size: 64646778148 dataset_size: 143459907372 - config_name: subset_89 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143713229680 num_examples: 93404 download_size: 64788831986 dataset_size: 143713229680 - config_name: subset_9 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95562629284 num_examples: 62109 download_size: 43123134026 dataset_size: 95562629284 - config_name: subset_90 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143379593708 num_examples: 93187 download_size: 64733038170 dataset_size: 143379593708 - config_name: subset_91 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95696250128 num_examples: 62196 download_size: 43134085960 dataset_size: 95696250128 - config_name: subset_92 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95934407652 num_examples: 62351 download_size: 43224929875 dataset_size: 95934407652 - config_name: subset_93 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95753580284 num_examples: 62233 download_size: 43222236201 dataset_size: 95753580284 - config_name: subset_94 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95891874916 num_examples: 62323 download_size: 43252770071 dataset_size: 95891874916 - config_name: subset_95 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659464728 num_examples: 62172 download_size: 43086228614 dataset_size: 95659464728 - config_name: subset_96 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95794821896 num_examples: 62260 download_size: 43179370699 dataset_size: 95794821896 - config_name: subset_97 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95622506640 num_examples: 62148 download_size: 43156846644 dataset_size: 95622506640 - config_name: subset_98 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 13845628 num_examples: 9 download_size: 6713409 dataset_size: 13845628 - config_name: subset_99 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95636401316 num_examples: 62157 download_size: 43147436863 dataset_size: 95636401316 configs: - config_name: subset_0 data_files: - split: train path: subset_0/train-* - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

bigscience/xP3mt

bigscience

--- annotations_creators: - expert-generated - crowdsourced language: - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso - ny - or - pa - pt - rn - rw - sn - st - sw - ta - te - tn - ts - tum - tw - ur - vi - wo - xh - yo - zh - zu programming_language: - C - C++ - C# - Go - Java - JavaScript - Lua - PHP - Python - Ruby - Rust - Scala - TypeScript license: - apache-2.0 multilinguality: - multilingual pretty_name: xP3 size_categories: - 100M<n<1B task_categories: - other --- # Dataset Card for xP3 ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Additional Information](#additional-information) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository:** https://github.com/bigscience-workshop/xmtf - **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Niklas Muennighoff](mailto:[email protected]) ### Dataset Summary > xP3 (Crosslingual Public Pool of Prompts) is a collection of prompts & datasets across 46 of languages & 16 NLP tasks. It is used for the training of BLOOMZ and mT0, multilingual language models capable of following human instructions in dozens of languages zero-shot. - **Creation:** The dataset can be recreated using instructions available [here](https://github.com/bigscience-workshop/xmtf#create-xp3). We provide this version to save processing time and ease reproducibility. - **Languages:** 46 (Can be extended by [recreating with more splits](https://github.com/bigscience-workshop/xmtf#create-xp3)) - **xP3 Dataset Family:** <table> <tr> <th>Name</th> <th>Explanation</th> <th>Example models</th> </tr> <tr> <td><a href=https://huggingface.co/datasets/Muennighoff/xP3x>xP3x</a></t> <td>Mixture of 17 tasks in 277 languages with English prompts</td> <td>WIP - Join us at Project Aya @<a href=https://cohere.for.ai/>C4AI</a> to help!</td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3>xP3</a></t> <td>Mixture of 13 training tasks in 46 languages with English prompts</td> <td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a> & <a href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a></t> <td>Mixture of 13 training tasks in 46 languages with prompts in 20 languages (machine-translated from English)</td> <td><a href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a> & <a href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3all>xP3all</a></t> <td>xP3 + evaluation datasets adding an additional 3 tasks for a total of 16 tasks in 46 languages with English prompts</td> <td></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3megds>xP3megds</a></t> <td><a href=https://github.com/bigscience-workshop/Megatron-DeepSpeed>Megatron-DeepSpeed</a> processed version of xP3</td> <td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/Muennighoff/P3>P3</a></t> <td>Repreprocessed version of the English-only <a href=https://huggingface.co/datasets/bigscience/P3>P3</a> with 8 training tasks</td> <td><a href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a> & <a href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td> </tr> </table> ## Dataset Structure ### Data Instances An example of "train" looks as follows: ```json { "inputs": "Oración 1: Fue académico en literatura metafísica, teología y ciencias clásicas.\Oración 2: Fue académico en literatura metafísica, teología y ciencia clásica.\nPregunta: ¿La oración 1 parafrasea la oración 2? ¿Si o no?", "targets": "Sí" } ``` ### Data Fields The data fields are the same among all splits: - `inputs`: the natural language input fed to the model - `targets`: the natural language target that the model has to generate ### Data Splits The below table summarizes sizes per language (computed from the `merged_{lang}.jsonl` files). Due to languages like `tw` only being single sentence translation samples from Flores, their byte percentage is significantly lower than their sample percentage. We machine-translated prompts for monolingual datasets, thus languages with only crosslingual datasets (e.g. Translation) do not have non-English prompts. Languages without non-English prompts are equivalent to [xP3](https://huggingface.co/datasets/bigscience/xP3). |Language|Kilobytes|%|Samples|%|Non-English prompts| |--------|------:|-:|---:|-:|-:| |tw|106288|0.11|265071|0.33| | |bm|107056|0.11|265180|0.33| | |ak|108096|0.11|265071|0.33| | |ca|110608|0.11|271191|0.34| | |eu|113008|0.12|281199|0.35| | |fon|113072|0.12|265063|0.33| | |st|114080|0.12|265063|0.33| | |ki|115040|0.12|265180|0.33| | |tum|116032|0.12|265063|0.33| | |wo|122560|0.13|365063|0.46| | |ln|126304|0.13|365060|0.46| | |as|156256|0.16|265063|0.33| | |or|161472|0.17|265063|0.33| | |kn|165456|0.17|265063|0.33| | |ml|175040|0.18|265864|0.33| | |rn|192992|0.2|318189|0.4| | |nso|229712|0.24|915051|1.14| | |tn|235536|0.24|915054|1.14| | |lg|235936|0.24|915021|1.14| | |rw|249360|0.26|915043|1.14| | |ts|250256|0.26|915044|1.14| | |sn|252496|0.26|865056|1.08| | |xh|254672|0.26|915058|1.14| | |zu|263712|0.27|915061|1.14| | |ny|272128|0.28|915063|1.14| | |ig|325440|0.33|950097|1.19|✅| |yo|339664|0.35|913021|1.14|✅| |ne|398144|0.41|315754|0.39|✅| |pa|529632|0.55|339210|0.42|✅| |sw|561392|0.58|1114439|1.39|✅| |gu|566576|0.58|347499|0.43|✅| |mr|674000|0.69|417269|0.52|✅| |bn|854864|0.88|428725|0.54|✅| |ta|943440|0.97|410633|0.51|✅| |te|1384016|1.42|573354|0.72|✅| |ur|1944416|2.0|855756|1.07|✅| |vi|3113184|3.2|1667306|2.08|✅| |code|4330752|4.46|2707724|3.38| | |hi|4469712|4.6|1543441|1.93|✅| |id|4538768|4.67|2582272|3.22|✅| |zh|4604112|4.74|3571636|4.46|✅| |ar|4703968|4.84|2148970|2.68|✅| |fr|5558912|5.72|5055942|6.31|✅| |pt|6130016|6.31|3562772|4.45|✅| |es|7579424|7.8|5151349|6.43|✅| |en|39252528|40.4|32740750|40.87| | |total|97150128|100.0|80100816|100.0|✅| ## Dataset Creation ### Source Data #### Training datasets - Code Miscellaneous - [CodeComplex](https://huggingface.co/datasets/codeparrot/codecomplex) - [Docstring Corpus](https://huggingface.co/datasets/teven/code_docstring_corpus) - [GreatCode](https://huggingface.co/datasets/great_code) - [State Changes](https://huggingface.co/datasets/Fraser/python-state-changes) - Closed-book QA - [Hotpot QA](https://huggingface.co/datasets/hotpot_qa) - [Trivia QA](https://huggingface.co/datasets/trivia_qa) - [Web Questions](https://huggingface.co/datasets/web_questions) - [Wiki QA](https://huggingface.co/datasets/wiki_qa) - Extractive QA - [Adversarial QA](https://huggingface.co/datasets/adversarial_qa) - [CMRC2018](https://huggingface.co/datasets/cmrc2018) - [DRCD](https://huggingface.co/datasets/clue) - [DuoRC](https://huggingface.co/datasets/duorc) - [MLQA](https://huggingface.co/datasets/mlqa) - [Quoref](https://huggingface.co/datasets/quoref) - [ReCoRD](https://huggingface.co/datasets/super_glue) - [ROPES](https://huggingface.co/datasets/ropes) - [SQuAD v2](https://huggingface.co/datasets/squad_v2) - [xQuAD](https://huggingface.co/datasets/xquad) - TyDI QA - [Primary](https://huggingface.co/datasets/khalidalt/tydiqa-primary) - [Goldp](https://huggingface.co/datasets/khalidalt/tydiqa-goldp) - Multiple-Choice QA - [ARC](https://huggingface.co/datasets/ai2_arc) - [C3](https://huggingface.co/datasets/c3) - [CoS-E](https://huggingface.co/datasets/cos_e) - [Cosmos](https://huggingface.co/datasets/cosmos) - [DREAM](https://huggingface.co/datasets/dream) - [MultiRC](https://huggingface.co/datasets/super_glue) - [OpenBookQA](https://huggingface.co/datasets/openbookqa) - [PiQA](https://huggingface.co/datasets/piqa) - [QUAIL](https://huggingface.co/datasets/quail) - [QuaRel](https://huggingface.co/datasets/quarel) - [QuaRTz](https://huggingface.co/datasets/quartz) - [QASC](https://huggingface.co/datasets/qasc) - [RACE](https://huggingface.co/datasets/race) - [SciQ](https://huggingface.co/datasets/sciq) - [Social IQA](https://huggingface.co/datasets/social_i_qa) - [Wiki Hop](https://huggingface.co/datasets/wiki_hop) - [WiQA](https://huggingface.co/datasets/wiqa) - Paraphrase Identification - [MRPC](https://huggingface.co/datasets/super_glue) - [PAWS](https://huggingface.co/datasets/paws) - [PAWS-X](https://huggingface.co/datasets/paws-x) - [QQP](https://huggingface.co/datasets/qqp) - Program Synthesis - [APPS](https://huggingface.co/datasets/codeparrot/apps) - [CodeContests](https://huggingface.co/datasets/teven/code_contests) - [JupyterCodePairs](https://huggingface.co/datasets/codeparrot/github-jupyter-text-code-pairs) - [MBPP](https://huggingface.co/datasets/Muennighoff/mbpp) - [NeuralCodeSearch](https://huggingface.co/datasets/neural_code_search) - [XLCoST](https://huggingface.co/datasets/codeparrot/xlcost-text-to-code) - Structure-to-text - [Common Gen](https://huggingface.co/datasets/common_gen) - [Wiki Bio](https://huggingface.co/datasets/wiki_bio) - Sentiment - [Amazon](https://huggingface.co/datasets/amazon_polarity) - [App Reviews](https://huggingface.co/datasets/app_reviews) - [IMDB](https://huggingface.co/datasets/imdb) - [Rotten Tomatoes](https://huggingface.co/datasets/rotten_tomatoes) - [Yelp](https://huggingface.co/datasets/yelp_review_full) - Simplification - [BiSECT](https://huggingface.co/datasets/GEM/BiSECT) - Summarization - [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail) - [Gigaword](https://huggingface.co/datasets/gigaword) - [MultiNews](https://huggingface.co/datasets/multi_news) - [SamSum](https://huggingface.co/datasets/samsum) - [Wiki-Lingua](https://huggingface.co/datasets/GEM/wiki_lingua) - [XLSum](https://huggingface.co/datasets/GEM/xlsum) - [XSum](https://huggingface.co/datasets/xsum) - Topic Classification - [AG News](https://huggingface.co/datasets/ag_news) - [DBPedia](https://huggingface.co/datasets/dbpedia_14) - [TNEWS](https://huggingface.co/datasets/clue) - [TREC](https://huggingface.co/datasets/trec) - [CSL](https://huggingface.co/datasets/clue) - Translation - [Flores-200](https://huggingface.co/datasets/Muennighoff/flores200) - [Tatoeba](https://huggingface.co/datasets/Helsinki-NLP/tatoeba_mt) - Word Sense disambiguation - [WiC](https://huggingface.co/datasets/super_glue) - [XL-WiC](https://huggingface.co/datasets/pasinit/xlwic) #### Evaluation datasets (included in [xP3all](https://huggingface.co/datasets/bigscience/xP3all) except for NLI & HumanEval) - Natural Language Inference (NLI) - [ANLI](https://huggingface.co/datasets/anli) - [CB](https://huggingface.co/datasets/super_glue) - [RTE](https://huggingface.co/datasets/super_glue) - [XNLI](https://huggingface.co/datasets/xnli) - Coreference Resolution - [Winogrande](https://huggingface.co/datasets/winogrande) - [XWinograd](https://huggingface.co/datasets/Muennighoff/xwinograd) - Program Synthesis - [HumanEval](https://huggingface.co/datasets/openai_humaneval) - Sentence Completion - [COPA](https://huggingface.co/datasets/super_glue) - [Story Cloze](https://huggingface.co/datasets/story_cloze) - [XCOPA](https://huggingface.co/datasets/xcopa) - [XStoryCloze](https://huggingface.co/datasets/Muennighoff/xstory_cloze) ## Additional Information ### Licensing Information The dataset is released under Apache 2.0. ### Citation Information ```bibtex @misc{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Niklas Muennighoff and Thomas Wang and Lintang Sutawika and Adam Roberts and Stella Biderman and Teven Le Scao and M Saiful Bari and Sheng Shen and Zheng-Xin Yong and Hailey Schoelkopf and Xiangru Tang and Dragomir Radev and Alham Fikri Aji and Khalid Almubarak and Samuel Albanie and Zaid Alyafeai and Albert Webson and Edward Raff and Colin Raffel}, year={2022}, eprint={2211.01786}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to the contributors of [promptsource](https://github.com/bigscience-workshop/promptsource/graphs/contributors) for adding many prompts used in this dataset.

google/fleurs

google

--- annotations_creators: - expert-generated - crowdsourced - machine-generated language_creators: - crowdsourced - expert-generated language: - afr - amh - ara - asm - ast - azj - bel - ben - bos - cat - ceb - cmn - ces - cym - dan - deu - ell - eng - spa - est - fas - ful - fin - tgl - fra - gle - glg - guj - hau - heb - hin - hrv - hun - hye - ind - ibo - isl - ita - jpn - jav - kat - kam - kea - kaz - khm - kan - kor - ckb - kir - ltz - lug - lin - lao - lit - luo - lav - mri - mkd - mal - mon - mar - msa - mlt - mya - nob - npi - nld - nso - nya - oci - orm - ory - pan - pol - pus - por - ron - rus - bul - snd - slk - slv - sna - som - srp - swe - swh - tam - tel - tgk - tha - tur - ukr - umb - urd - uzb - vie - wol - xho - yor - yue - zul license: - cc-by-4.0 multilinguality: - multilingual size_categories: - 10K<n<100K task_categories: - automatic-speech-recognition task_ids: [] pretty_name: 'The Cross-lingual TRansfer Evaluation of Multilingual Encoders for Speech (XTREME-S) benchmark is a benchmark designed to evaluate speech representations across languages, tasks, domains and data regimes. It covers 102 languages from 10+ language families, 3 different domains and 4 task families: speech recognition, translation, classification and retrieval.' tags: - speech-recognition --- # FLEURS ## Dataset Description - **Fine-Tuning script:** [pytorch/speech-recognition](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition) - **Paper:** [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://arxiv.org/abs/2205.12446) - **Total amount of disk used:** ca. 350 GB Fleurs is the speech version of the [FLoRes machine translation benchmark](https://arxiv.org/abs/2106.03193). We use 2009 n-way parallel sentences from the FLoRes dev and devtest publicly available sets, in 102 languages. Training sets have around 10 hours of supervision. Speakers of the train sets are different than speakers from the dev/test sets. Multilingual fine-tuning is used and ”unit error rate” (characters, signs) of all languages is averaged. Languages and results are also grouped into seven geographical areas: - **Western Europe**: *Asturian, Bosnian, Catalan, Croatian, Danish, Dutch, English, Finnish, French, Galician, German, Greek, Hungarian, Icelandic, Irish, Italian, Kabuverdianu, Luxembourgish, Maltese, Norwegian, Occitan, Portuguese, Spanish, Swedish, Welsh* - **Eastern Europe**: *Armenian, Belarusian, Bulgarian, Czech, Estonian, Georgian, Latvian, Lithuanian, Macedonian, Polish, Romanian, Russian, Serbian, Slovak, Slovenian, Ukrainian* - **Central-Asia/Middle-East/North-Africa**: *Arabic, Azerbaijani, Hebrew, Kazakh, Kyrgyz, Mongolian, Pashto, Persian, Sorani-Kurdish, Tajik, Turkish, Uzbek* - **Sub-Saharan Africa**: *Afrikaans, Amharic, Fula, Ganda, Hausa, Igbo, Kamba, Lingala, Luo, Northern-Sotho, Nyanja, Oromo, Shona, Somali, Swahili, Umbundu, Wolof, Xhosa, Yoruba, Zulu* - **South-Asia**: *Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Nepali, Oriya, Punjabi, Sindhi, Tamil, Telugu, Urdu* - **South-East Asia**: *Burmese, Cebuano, Filipino, Indonesian, Javanese, Khmer, Lao, Malay, Maori, Thai, Vietnamese* - **CJK languages**: *Cantonese and Mandarin Chinese, Japanese, Korean* ## How to use & Supported Tasks ### How to use The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. For example, to download the Hindi config, simply specify the corresponding language config name (i.e., "hi_in" for Hindi): ```python from datasets import load_dataset fleurs = load_dataset("google/fleurs", "hi_in", split="train") ``` Using the datasets library, you can also stream the dataset on-the-fly by adding a `streaming=True` argument to the `load_dataset` function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. ```python from datasets import load_dataset fleurs = load_dataset("google/fleurs", "hi_in", split="train", streaming=True) print(next(iter(fleurs))) ``` *Bonus*: create a [PyTorch dataloader](https://huggingface.co/docs/datasets/use_with_pytorch) directly with your own datasets (local/streamed). Local: ```python from datasets import load_dataset from torch.utils.data.sampler import BatchSampler, RandomSampler fleurs = load_dataset("google/fleurs", "hi_in", split="train") batch_sampler = BatchSampler(RandomSampler(fleurs), batch_size=32, drop_last=False) dataloader = DataLoader(fleurs, batch_sampler=batch_sampler) ``` Streaming: ```python from datasets import load_dataset from torch.utils.data import DataLoader fleurs = load_dataset("google/fleurs", "hi_in", split="train") dataloader = DataLoader(fleurs, batch_size=32) ``` To find out more about loading and preparing audio datasets, head over to [hf.co/blog/audio-datasets](https://huggingface.co/blog/audio-datasets). ### Example scripts Train your own CTC or Seq2Seq Automatic Speech Recognition models on FLEURS with `transformers` - [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition). Fine-tune your own Language Identification models on FLEURS with `transformers` - [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/audio-classification) ### 1. Speech Recognition (ASR) ```py from datasets import load_dataset fleurs_asr = load_dataset("google/fleurs", "af_za") # for Afrikaans # to download all data for multi-lingual fine-tuning uncomment following line # fleurs_asr = load_dataset("google/fleurs", "all") # see structure print(fleurs_asr) # load audio sample on the fly audio_input = fleurs_asr["train"][0]["audio"] # first decoded audio sample transcription = fleurs_asr["train"][0]["transcription"] # first transcription # use `audio_input` and `transcription` to fine-tune your model for ASR # for analyses see language groups all_language_groups = fleurs_asr["train"].features["lang_group_id"].names lang_group_id = fleurs_asr["train"][0]["lang_group_id"] all_language_groups[lang_group_id] ``` ### 2. Language Identification LangID can often be a domain classification, but in the case of FLEURS-LangID, recordings are done in a similar setting across languages and the utterances correspond to n-way parallel sentences, in the exact same domain, making this task particularly relevant for evaluating LangID. The setting is simple, FLEURS-LangID is splitted in train/valid/test for each language. We simply create a single train/valid/test for LangID by merging all. ```py from datasets import load_dataset fleurs_langID = load_dataset("google/fleurs", "all") # to download all data # see structure print(fleurs_langID) # load audio sample on the fly audio_input = fleurs_langID["train"][0]["audio"] # first decoded audio sample language_class = fleurs_langID["train"][0]["lang_id"] # first id class language = fleurs_langID["train"].features["lang_id"].names[language_class] # use audio_input and language_class to fine-tune your model for audio classification ``` ### 3. Retrieval Retrieval provides n-way parallel speech and text data. Similar to how XTREME for text leverages Tatoeba to evaluate bitext mining a.k.a sentence translation retrieval, we use Retrieval to evaluate the quality of fixed-size representations of speech utterances. Our goal is to incentivize the creation of fixed-size speech encoder for speech retrieval. The system has to retrieve the English "key" utterance corresponding to the speech translation of "queries" in 15 languages. Results have to be reported on the test sets of Retrieval whose utterances are used as queries (and keys for English). We augment the English keys with a large number of utterances to make the task more difficult. ```py from datasets import load_dataset fleurs_retrieval = load_dataset("google/fleurs", "af_za") # for Afrikaans # to download all data for multi-lingual fine-tuning uncomment following line # fleurs_retrieval = load_dataset("google/fleurs", "all") # see structure print(fleurs_retrieval) # load audio sample on the fly audio_input = fleurs_retrieval["train"][0]["audio"] # decoded audio sample text_sample_pos = fleurs_retrieval["train"][0]["transcription"] # positive text sample text_sample_neg = fleurs_retrieval["train"][1:20]["transcription"] # negative text samples # use `audio_input`, `text_sample_pos`, and `text_sample_neg` to fine-tune your model for retrieval ``` Users can leverage the training (and dev) sets of FLEURS-Retrieval with a ranking loss to build better cross-lingual fixed-size representations of speech. ## Dataset Structure We show detailed information the example configurations `af_za` of the dataset. All other configurations have the same structure. ### Data Instances **af_za** - Size of downloaded dataset files: 1.47 GB - Size of the generated dataset: 1 MB - Total amount of disk used: 1.47 GB An example of a data instance of the config `af_za` looks as follows: ``` {'id': 91, 'num_samples': 385920, 'path': '/home/patrick/.cache/huggingface/datasets/downloads/extracted/310a663d52322700b3d3473cbc5af429bd92a23f9bc683594e70bc31232db39e/home/vaxelrod/FLEURS/oss2_obfuscated/af_za/audio/train/17797742076841560615.wav', 'audio': {'path': '/home/patrick/.cache/huggingface/datasets/downloads/extracted/310a663d52322700b3d3473cbc5af429bd92a23f9bc683594e70bc31232db39e/home/vaxelrod/FLEURS/oss2_obfuscated/af_za/audio/train/17797742076841560615.wav', 'array': array([ 0.0000000e+00, 0.0000000e+00, 0.0000000e+00, ..., -1.1205673e-04, -8.4638596e-05, -1.2731552e-04], dtype=float32), 'sampling_rate': 16000}, 'raw_transcription': 'Dit is nog nie huidiglik bekend watter aantygings gemaak sal word of wat owerhede na die seun gelei het nie maar jeugmisdaad-verrigtinge het in die federale hof begin', 'transcription': 'dit is nog nie huidiglik bekend watter aantygings gemaak sal word of wat owerhede na die seun gelei het nie maar jeugmisdaad-verrigtinge het in die federale hof begin', 'gender': 0, 'lang_id': 0, 'language': 'Afrikaans', 'lang_group_id': 3} ``` ### Data Fields The data fields are the same among all splits. - **id** (int): ID of audio sample - **num_samples** (int): Number of float values - **path** (str): Path to the audio file - **audio** (dict): Audio object including loaded audio array, sampling rate and path ot audio - **raw_transcription** (str): The non-normalized transcription of the audio file - **transcription** (str): Transcription of the audio file - **gender** (int): Class id of gender - **lang_id** (int): Class id of language - **lang_group_id** (int): Class id of language group ### Data Splits Every config only has the `"train"` split containing of *ca.* 1000 examples, and a `"validation"` and `"test"` split each containing of *ca.* 400 examples. ## Dataset Creation We collect between one and three recordings for each sentence (2.3 on average), and buildnew train-dev-test splits with 1509, 150 and 350 sentences for train, dev and test respectively. ## Considerations for Using the Data ### Social Impact of Dataset This dataset is meant to encourage the development of speech technology in a lot more languages of the world. One of the goal is to give equal access to technologies like speech recognition or speech translation to everyone, meaning better dubbing or better access to content from the internet (like podcasts, streaming or videos). ### Discussion of Biases Most datasets have a fair distribution of gender utterances (e.g. the newly introduced FLEURS dataset). While many languages are covered from various regions of the world, the benchmark misses many languages that are all equally important. We believe technology built through FLEURS should generalize to all languages. ### Other Known Limitations The dataset has a particular focus on read-speech because common evaluation benchmarks like CoVoST-2 or LibriSpeech evaluate on this type of speech. There is sometimes a known mismatch between performance obtained in a read-speech setting and a more noisy setting (in production for instance). Given the big progress that remains to be made on many languages, we believe better performance on FLEURS should still correlate well with actual progress made for speech understanding. ## Additional Information All datasets are licensed under the [Creative Commons license (CC-BY)](https://creativecommons.org/licenses/). ### Citation Information You can access the FLEURS paper at https://arxiv.org/abs/2205.12446. Please cite the paper when referencing the FLEURS corpus as: ``` @article{fleurs2022arxiv, title = {FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech}, author = {Conneau, Alexis and Ma, Min and Khanuja, Simran and Zhang, Yu and Axelrod, Vera and Dalmia, Siddharth and Riesa, Jason and Rivera, Clara and Bapna, Ankur}, journal={arXiv preprint arXiv:2205.12446}, url = {https://arxiv.org/abs/2205.12446}, year = {2022}, ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten) and [@aconneau](https://github.com/aconneau) for adding this dataset.

nyu-visionx/Cambrian-10M

nyu-visionx

--- task_categories: - visual-question-answering - question-answering language: - en size_categories: - 1M<n<10M license: apache-2.0 --- # Cambrian-10M Dataset **Please see paper & website for more information:** - https://cambrian-mllm.github.io/ - https://arxiv.org/abs/2406.16860 ## Overview Cambrian-10M is a comprehensive dataset designed for instruction tuning, particularly in multimodal settings involving visual interaction data. The dataset is crafted to address the scarcity of high-quality multimodal instruction-tuning data and to maintain the language abilities of multimodal large language models (LLMs). ## Data Collection ### Multimodal Data Sources Unlike language data, multimodal instruction-tuning data is much rarer and harder to collect. To address this, we leverage existing multimodal benchmarks and datasets involving visual interaction data, such as Visual Question Answering (VQA) and Optical Character Recognition (OCR) data. This approach helps mitigate the catastrophic forgetting commonly observed when fine-tuning multimodal LLMs. ### Language-Only Instruction-Following Data To ensure the preservation of language capabilities, we also collect a small volume of high-quality language-only instruction-following data from the community. ### Targeted Internet Data Collection Engine We introduce a data engine designed to create large-scale, reliable, high-quality knowledge-based multimodal instruction tuning data. The engine works as follows: 1. **Field and Subfield Selection**: The engine selects a target field and subfield, such as “Physics”. 2. **Topic Identification**: An LLM like GPT-4 identifies topics within the field (e.g., “Newton’s Laws”). 3. **Reliable Source Search**: The engine searches reliable sources like Wikipedia for each topic. 4. **Text-Image Association Extraction**: The parser extracts image-caption-text tuples from the sources. 5. **Q&A Pair Generation**: The caption-text is fed to an LLM, such as GPT-3.5, to generate instruction-type Q&A pairs about the image. These Q&A pairs, along with the images, form our VQA dataset. ### GPT Rewriting We also incorporate recent MLLMs such as GPT-4v and GPT-4o to generate extended responses and free-form instruction tuning data. To play with gpt generated data, use [gpt4v_77k](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/gpt4v_77k.jsonl), Curated [gpt4o_60k](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/gpt4o_60k.jsonl) - [gpt4v_77k](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/gpt4v_77k.jsonl) contains more extended responses from Cambrian-10M. - [gpt4o_60k](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/gpt4o_60k.jsonl) contains more creative data in visual interactions. ## Cambrian-10M Composition The Cambrian-10M dataset consists of approximately 9.784 million data points, offering a diverse range of data for various research applications. The composition of the dataset is visualized in Fig. 9. ## Cambrian-7M We make an initial effort to study data curation. In particular, we find the following data ratio to perform most optimally - **Language**: 21.00% - **General**: 34.52% - **OCR**: 27.22% - **Counting**: 8.71% - **Math**: 7.20% - **Code**: 0.87% - **Science**: 0.88%  ## Getting Started with Cambrian Data Before you start, ensure you have sufficient storage space to download and process the data. Cambrian-10M contains a total of 10 million images collected from previous datasets, an internet data engine, and GPT-generated instruction tuning data. Follow these steps to get started: 1. **Download the Data Repository** Download the data repository. Note that due to Hugging Face policy constraints, the data folder is archived into tar files. We also split the `allava` and `data_engine` data into smaller tar files because they exceed the 50 GB size limit. 2. **Merge Tar Files** To explore the Cambrian-10M dataset, first merge the different parts of `allava` and `data_engine` together: ```bash python merge_tars.py ``` 3. **Extract Tar Files** Then, extract all the tar files into the current directory: ```bash python extract.py ``` 4. **Training with Cambrian** You can train with the raw [Cambrian10M](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/Cambrian10M.jsonl), Curated [Cambrian7M](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/resolve/main/jsons/Cambrian7M.jsonl). We recommend using the Curated [Cambrian7M with system prompt](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M/blob/main/jsons/Cambrian7M_withsystemprompt.jsonl) that also alleviates 'answer machine' problem.

tasksource/mmlu

tasksource

--- license: apache-2.0 task_categories: - text-classification - multiple-choice - question-answering task_ids: - multiple-choice-qa - open-domain-qa - closed-domain-qa language: - en tags: - multi-task - multitask - mmlu - hendrycks_test pretty_name: mmlu --- MMLU (`hendrycks_test` on huggingface) without auxiliary train. It is much lighter (7MB vs 162MB) and faster than the original implementation, in which auxiliary train is loaded (+ duplicated!) by default for all the configs in the original version, making it quite heavy. We use this version in [tasksource](https://huggingface.co/tasksource). Reference to original dataset: Measuring Massive Multitask Language Understanding - https://github.com/hendrycks/test ``` @article{hendryckstest2021, title={Measuring Massive Multitask Language Understanding}, author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt}, journal={Proceedings of the International Conference on Learning Representations (ICLR)}, year={2021} } ```

locuslab/TOFU

locuslab

--- annotations_creators: - machine-generated language: - en language_creators: - machine-generated license: mit multilinguality: - monolingual pretty_name: TOFU size_categories: - 1K<n<10K source_datasets: - original tags: - unlearning - question answering - TOFU - NLP - LLM task_categories: - question-answering task_ids: - closed-domain-qa configs: - config_name: full data_files: full.json default: true - config_name: forget01 data_files: forget01.json - config_name: forget05 data_files: forget05.json - config_name: forget10 data_files: forget10.json - config_name: retain90 data_files: retain90.json - config_name: retain95 data_files: retain95.json - config_name: retain99 data_files: retain99.json - config_name: world_facts data_files: world_facts.json - config_name: real_authors data_files: real_authors.json - config_name: forget01_perturbed data_files: forget01_perturbed.json - config_name: forget05_perturbed data_files: forget05_perturbed.json - config_name: forget10_perturbed data_files: forget10_perturbed.json - config_name: retain_perturbed data_files: retain_perturbed.json - config_name: world_facts_perturbed data_files: world_facts_perturbed.json - config_name: real_authors_perturbed data_files: real_authors_perturbed.json --- # TOFU: Task of Fictitious Unlearning 🍢 The TOFU dataset serves as a benchmark for evaluating unlearning performance of large language models on realistic tasks. The dataset comprises question-answer pairs based on autobiographies of 200 different authors that do not exist and are completely fictitiously generated by the GPT-4 model. The goal of the task is to unlearn a fine-tuned model on various fractions of the forget set. ## Quick Links - [**Website**](https://locuslab.github.io/tofu): The landing page for TOFU - [**arXiv Paper**](http://arxiv.org/abs/2401.06121): Detailed information about the TOFU dataset and its significance in unlearning tasks. - [**GitHub Repository**](https://github.com/locuslab/tofu): Access the source code, fine-tuning scripts, and additional resources for the TOFU dataset. - [**Dataset on Hugging Face**](https://huggingface.co/datasets/locuslab/TOFU): Direct link to download the TOFU dataset. - [**Leaderboard on Hugging Face Spaces**](https://huggingface.co/spaces/locuslab/tofu_leaderboard): Current rankings and submissions for the TOFU dataset challenges. - [**Summary on Twitter**](https://x.com/_akhaliq/status/1745643293839327268): A concise summary and key takeaways from the project. ## Applicability 🚀 The dataset is in QA format, making it ideal for use with popular chat models such as Llama2, Mistral, or Qwen. However, it also works for any other large language model. The corresponding code base is written for the Llama2 chat, and Phi-1.5 models, but can be easily adapted to other models. ## Loading the Dataset To load the dataset, use the following code: ```python from datasets import load_dataset dataset = load_dataset("locuslab/TOFU", "full") ``` ### Available forget sets are: - `forget01`: Forgetting 1% of the original dataset, all entries correspond to a single author. - `forget05`: Forgetting 5% of the original dataset, all entries correspond to a single author. - `forget10`: Forgetting 10% of the original dataset, all entries correspond to a single author. Retain sets corresponding to each forget set are also available, which can be used to train an Oracle model. ## Codebase The code for training the models and the availability of all fine-tuned models can be found at our [GitHub repository](https://github.com/locuslab/tofu). ## Citing Our Work If you find our codebase and dataset beneficial, please cite our work: ``` @misc{tofu2024, title={TOFU: A Task of Fictitious Unlearning for LLMs}, author={Pratyush Maini and Zhili Feng and Avi Schwarzschild and Zachary C. Lipton and J. Zico Kolter}, year={2024}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```

isp-uv-es/WorldFloodsv2

isp-uv-es

--- license: cc-by-nc-4.0 pipeline_tag: image-segmentation tags: - remote sensing - sentinel2 - landsat - floods --- # *WorldFloodsv2* dataset This repository contains the *WorldFloodsv2* dataset released with the publication: > E. Portalés-Julià, G. Mateo-García, C. Purcell, and L. Gómez-Chova [Global flood extent segmentation in optical satellite images](https://www.nature.com/articles/s41598-023-47595-7). _Scientific Reports 13, 20316_ (2023). DOI: 10.1038/s41598-023-47595-7. The [*WorldFloodsv2* database](https://www.nature.com/articles/s41598-023-47595-7) contains 509 pairs of Sentinel-2 images and flood segmentation masks. Splitted in train, val and test sets. It requires approximately 76GB of hard-disk storage. <img src="worldfloods_v2.png" alt="licence" width="65%"/> ## Download the dataset ``` huggingface-cli download --cache-dir /path/to/cachedir --local-dir /path/to/localdir/WorldFloodsv2 --repo-type dataset isp-uv-es/WorldFloodsv2 ``` ## Explore the dataset The [exploring *WorldFloodsv2*](https://spaceml-org.github.io/ml4floods/content/prep/exploring_worldfloods.html) tutorial in the [ml4floods](https://github.com/spaceml-org/ml4floods) package shows how to process the dataset and plot the images and masks. ## Licence The *WorldFloods* database and all pre-trained models are released under a [Creative Commons non-commercial licence](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) ## Cite If you find this work useful, please cite: ``` @article{portales-julia_global_2023, title = {Global flood extent segmentation in optical satellite images}, volume = {13}, issn = {2045-2322}, doi = {10.1038/s41598-023-47595-7}, number = {1}, urldate = {2023-11-30}, journal = {Scientific Reports}, author = {Portalés-Julià, Enrique and Mateo-García, Gonzalo and Purcell, Cormac and Gómez-Chova, Luis}, month = nov, year = {2023}, pages = {20316}, } ```

CALM/arwiki

CALM

--- pretty_name: Wikipedia Arabic dumps dataset. language: - ar license: - unknown multilinguality: - monolingual --- # Arabic Wiki Dataset ## Dataset Summary This dataset is extracted using [`wikiextractor`](https://github.com/attardi/wikiextractor) tool, from [Wikipedia Arabic pages](https://dumps.wikimedia.org/arwiki/). ## Supported Tasks and Leaderboards Intended to train **Arabic** language models on MSA (Modern Standard Arabic). ## Dataset Structure The dataset is structured into 2 folders: - `arwiki_20211213_txt`: dataset is divided into subfolders each of which contains no more than 100 documents. - `arwiki_20211213_txt_single`: all documents merged together in a single txt file. ## Dataset Statistics #### Extracts from **December 13, 2021**: | documents | vocabulary | words | | --- | --- | --- | | 1,136,455 | 5,446,560 | 175,566,016 | ## Usage Load all dataset from the single txt file: ```python load_dataset('CALM/arwiki', data_files='arwiki_2021_txt_single/arwiki_20211213.txt') # OR with stream load_dataset('CALM/arwiki', data_files='arwiki_2021_txt_single/arwiki_20211213.txt', streaming=True) ``` Load a smaller subset from the individual txt files: ```python load_dataset('CALM/arwiki', data_files='arwiki_2021_txt/AA/arwiki_20211213_1208.txt') # OR with stream load_dataset('CALM/arwiki', data_files='arwiki_2021_txt/AA/arwiki_20211213_1208.txt', streaming=True) ```

asahi417/seamless-align-enA-jaA.speaker-embedding.xlsr-2b

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16310450373 num_examples: 2073 download_size: 16362791193 dataset_size: 16310450373 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14507997777 num_examples: 1961 download_size: 14554505952 dataset_size: 14507997777 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14129720831 num_examples: 1757 download_size: 14173975107 dataset_size: 14129720831 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14993273606 num_examples: 1873 download_size: 15040705190 dataset_size: 14993273606 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15427157956 num_examples: 1868 download_size: 15475633129 dataset_size: 15427157956 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15482076366 num_examples: 1879 download_size: 15530574846 dataset_size: 15482076366 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15390676969 num_examples: 1901 download_size: 15439431804 dataset_size: 15390676969 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15184436320 num_examples: 1875 download_size: 15231369480 dataset_size: 15184436320 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15272910298 num_examples: 1880 download_size: 15320755279 dataset_size: 15272910298 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14914011605 num_examples: 1854 download_size: 14961302329 dataset_size: 14914011605 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15180068428 num_examples: 1834 download_size: 15228372695 dataset_size: 15180068428 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14466035226 num_examples: 1770 download_size: 14511537163 dataset_size: 14466035226 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13101664907 num_examples: 1779 download_size: 13144308567 dataset_size: 13101664907 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15611661731 num_examples: 1908 download_size: 15659409356 dataset_size: 15611661731 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15278480945 num_examples: 1877 download_size: 15327096988 dataset_size: 15278480945 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15724141438 num_examples: 1924 download_size: 15772924053 dataset_size: 15724141438 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15575717731 num_examples: 1930 download_size: 15625880579 dataset_size: 15575717731 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15882425444 num_examples: 1940 download_size: 15931108324 dataset_size: 15882425444 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15508119355 num_examples: 1902 download_size: 15558088350 dataset_size: 15508119355 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15790391750 num_examples: 1910 download_size: 15839269103 dataset_size: 15790391750 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15442029172 num_examples: 1901 download_size: 15490765116 dataset_size: 15442029172 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15796646573 num_examples: 1911 download_size: 15846588578 dataset_size: 15796646573 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15363910769 num_examples: 1867 download_size: 15412415056 dataset_size: 15363910769 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14593616895 num_examples: 1916 download_size: 14640738281 dataset_size: 14593616895 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564344621 num_examples: 1774 download_size: 14609587966 dataset_size: 14564344621 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15707595472 num_examples: 1895 download_size: 15757411615 dataset_size: 15707595472 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15173277199 num_examples: 1851 download_size: 15220532819 dataset_size: 15173277199 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15999251579 num_examples: 1923 download_size: 16048976124 dataset_size: 15999251579 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15601517059 num_examples: 1886 download_size: 15649292085 dataset_size: 15601517059 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15779512647 num_examples: 1928 download_size: 15829615675 dataset_size: 15779512647 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15356045351 num_examples: 1903 download_size: 15404217390 dataset_size: 15356045351 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15746607635 num_examples: 1902 download_size: 15796480801 dataset_size: 15746607635 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15375262005 num_examples: 1890 download_size: 15423317041 dataset_size: 15375262005 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14491367899 num_examples: 1752 download_size: 14536131741 dataset_size: 14491367899 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13188431829 num_examples: 1769 download_size: 13231483897 dataset_size: 13188431829 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15116628991 num_examples: 1830 download_size: 15164906379 dataset_size: 15116628991 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15597505674 num_examples: 1882 download_size: 15646436161 dataset_size: 15597505674 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15682009564 num_examples: 1918 download_size: 15731148123 dataset_size: 15682009564 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15253685409 num_examples: 1886 download_size: 15302350698 dataset_size: 15253685409 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15689301205 num_examples: 1912 download_size: 15739304449 dataset_size: 15689301205 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15581938369 num_examples: 1888 download_size: 15631772490 dataset_size: 15581938369 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15412182385 num_examples: 1875 download_size: 15460732037 dataset_size: 15412182385 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15360445304 num_examples: 1866 download_size: 15408941456 dataset_size: 15360445304 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15290751173 num_examples: 1863 download_size: 15339201722 dataset_size: 15290751173 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15256641544 num_examples: 1859 download_size: 15305102287 dataset_size: 15256641544 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12993946901 num_examples: 1734 download_size: 13035965994 dataset_size: 12993946901 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14712168776 num_examples: 1766 download_size: 14758529545 dataset_size: 14712168776 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15597842345 num_examples: 1865 download_size: 15647499851 dataset_size: 15597842345 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15493296202 num_examples: 1893 download_size: 15541947212 dataset_size: 15493296202 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15528880887 num_examples: 1894 download_size: 15578798622 dataset_size: 15528880887 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11610659779 num_examples: 1381 download_size: 11647759826 dataset_size: 11610659779 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14365778430 num_examples: 1914 download_size: 14412046441 dataset_size: 14365778430 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13652391626 num_examples: 1862 download_size: 13697579329 dataset_size: 13652391626 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14220432427 num_examples: 1875 download_size: 14266917233 dataset_size: 14220432427 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14758117694 num_examples: 1937 download_size: 14806166262 dataset_size: 14758117694 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14263981046 num_examples: 1917 download_size: 14310683240 dataset_size: 14263981046 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14854535769 num_examples: 1929 download_size: 14902477949 dataset_size: 14854535769 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14108138618 num_examples: 1877 download_size: 14154663716 dataset_size: 14108138618 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13644053955 num_examples: 1761 download_size: 13688549900 dataset_size: 13644053955 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13872299017 num_examples: 1850 download_size: 13916933531 dataset_size: 13872299017 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13582453701 num_examples: 1790 download_size: 13627175034 dataset_size: 13582453701 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13368705263 num_examples: 1758 download_size: 13412036987 dataset_size: 13368705263 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14867350268 num_examples: 1898 download_size: 14914077907 dataset_size: 14867350268 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564112565 num_examples: 1943 download_size: 14612260797 dataset_size: 14564112565 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14403352351 num_examples: 1903 download_size: 14449996819 dataset_size: 14403352351 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14603029543 num_examples: 1912 download_size: 14650911489 dataset_size: 14603029543 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14673048791 num_examples: 1945 download_size: 14719897418 dataset_size: 14673048791 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14307378756 num_examples: 1899 download_size: 14353984563 dataset_size: 14307378756 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14710205080 num_examples: 1902 download_size: 14757936886 dataset_size: 14710205080 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14025445242 num_examples: 1805 download_size: 14071428675 dataset_size: 14025445242 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13945538622 num_examples: 1797 download_size: 13989843317 dataset_size: 13945538622 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13615084926 num_examples: 1757 download_size: 13659554271 dataset_size: 13615084926 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564415851 num_examples: 1893 download_size: 14609576153 dataset_size: 14564415851 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14755481346 num_examples: 1928 download_size: 14803386359 dataset_size: 14755481346 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14405715735 num_examples: 1863 download_size: 14452030865 dataset_size: 14405715735 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14459656749 num_examples: 1855 download_size: 14505278929 dataset_size: 14459656749 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14747294818 num_examples: 1890 download_size: 14794943834 dataset_size: 14747294818 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14583795374 num_examples: 1899 download_size: 14631576455 dataset_size: 14583795374 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13461749342 num_examples: 1835 download_size: 13505049439 dataset_size: 13461749342 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14996728508 num_examples: 1931 download_size: 15043987691 dataset_size: 14996728508 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13998657085 num_examples: 1784 download_size: 14043192313 dataset_size: 13998657085 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13997152060 num_examples: 1797 download_size: 14041809773 dataset_size: 13997152060 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13745374844 num_examples: 1757 download_size: 13787997899 dataset_size: 13745374844 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14470227992 num_examples: 1831 download_size: 14516259581 dataset_size: 14470227992 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14540526118 num_examples: 1891 download_size: 14588272101 dataset_size: 14540526118 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14936006712 num_examples: 1897 download_size: 14983643800 dataset_size: 14936006712 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15007636946 num_examples: 1897 download_size: 15056520164 dataset_size: 15007636946 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15007698844 num_examples: 1902 download_size: 15056591062 dataset_size: 15007698844 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14872319895 num_examples: 1875 download_size: 14917259741 dataset_size: 14872319895 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14727185951 num_examples: 1987 download_size: 14775476702 dataset_size: 14727185951 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15197781964 num_examples: 1951 download_size: 15247032911 dataset_size: 15197781964 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14076247457 num_examples: 1752 download_size: 14121778451 dataset_size: 14076247457 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14166667429 num_examples: 1780 download_size: 14212377834 dataset_size: 14166667429 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14663043837 num_examples: 1846 download_size: 14710380722 dataset_size: 14663043837 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13650359450 num_examples: 1723 download_size: 13694095020 dataset_size: 13650359450 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14667394581 num_examples: 1866 download_size: 14714877043 dataset_size: 14667394581 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15126039375 num_examples: 1893 download_size: 15174838075 dataset_size: 15126039375 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15160658347 num_examples: 1924 download_size: 15208466401 dataset_size: 15160658347 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14776270381 num_examples: 1881 download_size: 14823232990 dataset_size: 14776270381 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14820738246 num_examples: 1887 download_size: 14868333441 dataset_size: 14820738246 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13509749274 num_examples: 1810 download_size: 13554686583 dataset_size: 13509749274 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15012692080 num_examples: 1885 download_size: 15061442178 dataset_size: 15012692080 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13825585736 num_examples: 1728 download_size: 13869424308 dataset_size: 13825585736 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14059852714 num_examples: 1787 download_size: 14104565757 dataset_size: 14059852714 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14347818528 num_examples: 1790 download_size: 14393558940 dataset_size: 14347818528 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14454950614 num_examples: 1812 download_size: 14500831889 dataset_size: 14454950614 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15012253440 num_examples: 1877 download_size: 15060938596 dataset_size: 15012253440 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15063107203 num_examples: 1890 download_size: 15111909056 dataset_size: 15063107203 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14991421779 num_examples: 1873 download_size: 15038857831 dataset_size: 14991421779 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15139716092 num_examples: 1883 download_size: 15188419081 dataset_size: 15139716092 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15398369854 num_examples: 1916 download_size: 15447262341 dataset_size: 15398369854 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13642415322 num_examples: 1832 download_size: 13685996881 dataset_size: 13642415322 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15176201337 num_examples: 1903 download_size: 15224791080 dataset_size: 15176201337 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13922358727 num_examples: 1736 download_size: 13966560038 dataset_size: 13922358727 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15371189233 num_examples: 1887 download_size: 15419825117 dataset_size: 15371189233 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13830427317 num_examples: 1736 download_size: 13874422671 dataset_size: 13830427317 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14723538586 num_examples: 1829 download_size: 14770698909 dataset_size: 14723538586 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15010254373 num_examples: 1862 download_size: 15058831818 dataset_size: 15010254373 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15247986194 num_examples: 1914 download_size: 15296025961 dataset_size: 15247986194 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15110877308 num_examples: 1874 download_size: 15159532855 dataset_size: 15110877308 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15037318101 num_examples: 1871 download_size: 15085976191 dataset_size: 15037318101 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15137911072 num_examples: 1891 download_size: 15186694496 dataset_size: 15137911072 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14896343344 num_examples: 2009 download_size: 14944904571 dataset_size: 14896343344 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14886044351 num_examples: 1885 download_size: 14933598111 dataset_size: 14886044351 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15488479968 num_examples: 1913 download_size: 15537299076 dataset_size: 15488479968 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15484176671 num_examples: 1910 download_size: 15532974397 dataset_size: 15484176671 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15204999706 num_examples: 1887 download_size: 15253724799 dataset_size: 15204999706 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15046661582 num_examples: 1867 download_size: 15095251446 dataset_size: 15046661582 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15018316453 num_examples: 1881 download_size: 15067060203 dataset_size: 15018316453 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15000057699 num_examples: 1862 download_size: 15047257993 dataset_size: 15000057699 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15201873116 num_examples: 1897 download_size: 15250090060 dataset_size: 15201873116 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15311639315 num_examples: 1900 download_size: 15360401050 dataset_size: 15311639315 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15309755677 num_examples: 1886 download_size: 15358419262 dataset_size: 15309755677 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14569778419 num_examples: 1977 download_size: 14618200962 dataset_size: 14569778419 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15290839824 num_examples: 1913 download_size: 15339744563 dataset_size: 15290839824 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15397885579 num_examples: 1913 download_size: 15446720083 dataset_size: 15397885579 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15031825290 num_examples: 1886 download_size: 15080581026 dataset_size: 15031825290 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15285895893 num_examples: 1875 download_size: 15334493674 dataset_size: 15285895893 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15343527930 num_examples: 1900 download_size: 15392308839 dataset_size: 15343527930 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15015741095 num_examples: 1867 download_size: 15064356988 dataset_size: 15015741095 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15460278621 num_examples: 1900 download_size: 15509015959 dataset_size: 15460278621 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15474609177 num_examples: 1899 download_size: 15523317437 dataset_size: 15474609177 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15471182493 num_examples: 1904 download_size: 15519934699 dataset_size: 15471182493 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15562076261 num_examples: 1901 download_size: 15612040624 dataset_size: 15562076261 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

yzwang/X2I-subject-driven

yzwang

--- license: apache-2.0 task_categories: - text-to-image - image-to-image language: - en size_categories: - 1M<n<10M --- # X2I Dataset * Project Page: [https://vectorspacelab.github.io/OmniGen/](https://vectorspacelab.github.io/OmniGen/) * Github: [https://github.com/VectorSpaceLab/OmniGen](https://github.com/VectorSpaceLab/OmniGen) * Paper: [https://arxiv.org/abs/2409.11340](https://arxiv.org/abs/2409.11340) * Model: [https://huggingface.co/Shitao/OmniGen-v1](https://huggingface.co/Shitao/OmniGen-v1) To achieve robust multi-task processing capabilities, it is essential to train the **OmniGen** on large-scale and diverse datasets. However, in the field of unified image generation, a readily available dataset has yet to emerge. For this reason, we have curated a large-scale **unified image generation** dataset with unified format for the **first time**, which we refer to as the **X2I dataset**, meaning **"anything to image"**. | Task| Datastet| | :-------- | :-------- | | Multi-modal Instruction| [X2I-mm-instruction](https://huggingface.co/datasets/yzwang/X2I-mm-instruction) | | Subject-driven Editing | [X2I-subject-driven](https://huggingface.co/datasets/yzwang/X2I-subject-driven) | | In-context Learning | [X2I-in-context-learning](https://huggingface.co/datasets/yzwang/X2I-in-context-learning) | | Computer Vision | [X2I-computer-vision](https://huggingface.co/datasets/yzwang/X2I-computer-vision) | | Text to Image Generation| [X2I-text-to-image](https://huggingface.co/datasets/yzwang/X2I-text-to-image) | ## X2I-subject-driven - **Web-Image** A self-built subject-driven editing dataset with 36,316 & 45,425 & 111,734 samples. ```python ## meta file: web-image-1.jsonl && web-image-2.jsonl && web-image-3.jsonl cd retrieval tar -zxvf download_images.tar.gz tar -zxvf download_images_two.tar.gz ``` - **GRIT-Entity** A subject-driven editing dataset with 1,708,742 samples. ```python ## meta file: grit-entity.jsonl cd grit/images1 tar -zxvf 00034.tar.gz # tar -zxvf 00066.tar.gz # ... cd grit/images2 tar -zxvf 00034.tar.gz # tar -zxvf 00066.tar.gz # ... cd grit/images3 tar -zxvf 00168.tar.gz # tar -zxvf 00187.tar.gz # ... ``` - **GRIT-Entity-New** A self-built subject-driven editing dataset with 676,603 samples. This datasets is smaller than GRIT-Entity but with higher qualtiy. ```python ## meta file: grit-entity-new.jsonl cd character tar -xzvf character.tar.gz cd human/human2 tar -xzvf human2.tar.gz cd human/human3 tar -xzvf human3.tar.gz cd single cat single.tar.gz.* | tar -xzvf - cd double cat double.tar.gz.* | tar -xzvf - cd triple cat triple.tar.gz.* | tar -xzvf - ```

opentensor/openvalidators-test

opentensor

--- license: mit viewer: False size_categories: - 1M<n<10M --- # Dataset Card for Openvalidators dataset ## Dataset Description - **Repository:** https://github.com/opentensor/validators - **Homepage:** https://bittensor.com/ ### Dataset Summary The OpenValidators dataset, created by the OpenTensor Foundation, is a continuously growing collection of data generated by the [OpenValidators](https://github.com/opentensor/validators) project in [W&B](https://wandb.ai/opentensor-dev/openvalidators/table). It contains hundreds of thousands of records and serves researchers, data scientists, and miners in the Bittensor network. The dataset provides information on network performance, node behaviors, and wandb run details. Researchers can gain insights and detect patterns, while data scientists can use it for training models and analysis. Miners can use the generated data to fine-tune their models and enhance their incentives in the network. The dataset's continuous updates support collaboration and innovation in decentralized computing. ### How to use The `datasets` library allows you to load and pre-process your dataset in pure Python, at scale. The OpenValidators dataset gives you the granularity of extracting data by ************run_id************, by ************************************OpenValidators version************************************ and by ******************************************************************multiple OpenValidators versions.****************************************************************** The dataset can be downloaded and prepared in one call to your local drive by using the `load_dataset` function. **Downloading by run id** For example, to download the data for a specific run, simply specify the corresponding ********************************************OpenValidators version******************************************** and the ************************wandb run id************************ in the format `version/raw_data/run_id.parquet`: ```python from datasets import load_dataset version = '1.0.4' # OpenValidators version run_id = '0plco3n0' # WandB run id run_id_dataset = load_dataset('opentensor/openvalidators-test', data_files=f'{version}/raw_data/{run_id}.parquet') ``` _Please note that only completed run_ids are included in the dataset. Runs that are still in progress will be ingested shortly after they finish._ **Downloading by OpenValidators version** One can also leverage the `datasets` library to download all the runs within a determined ****************************OpenValidators**************************** version. That can be useful for researchers and data enthusiasts that are looking to do analysis in a specific ****************************OpenValidators**************************** version state. ```python from datasets import load_dataset version = '1.0.4' # Openvalidators version version_dataset = load_dataset('opentensor/openvalidators-test', data_files=f'{version}/raw_data/*') ``` **Downloading by multiple OpenValidators version** Utilizing the `datasets` library, users can efficiently download runs from multiple **OpenValidators** versions. By accessing data from various OpenValidators versions, users can undertake downstream tasks such as data fine-tuning for mining or to perform big data analysis. ```python from datasets import load_dataset versions = ['1.0.0', '1.0.1', '1.0.2', '1.0.4'] # Desired versions for extraction data_files = [f'{version}/raw_data/*' for version in versions] # Set data files directories dataset = load_dataset('opentensor/openvalidators-test', data_files={ 'test': data_files }) ``` **Analyzing metadata** All the state related to the details of the wandb data ingestion can be accessed easily using pandas and hugging face datasets structure. This data contains relevant information regarding the metadata of the run, including user information, config information and ingestion state. ```python import pandas as pd version = '1.0.4' # OpenValidators version for metadata analysis df = pd.read_csv(f'hf://datasets/opentensor/openvalidators-test/{version}/metadata.csv') ``` ## Dataset Structure ### Data Instances **versioned raw_data** The data is provided as-in the wandb logs, without further preprocessing or tokenization. This data is located at `version/raw_data` where each file is a wandb run. **metadata** This dataset defines the current state of the wandb data ingestion by **run id**. ### Data Fields **Raw data** The versioned raw_data collected from W&B follows the following schema: - `_runtime`: (float64) Runtime of the event - `_step`: (int64) Step of the event - `_timestamp`: (float64) Timestamp of the event - `answer_completions`: (list(string)) Completions of the answer_prompt - `answer_prompt`: (string) Prompt used to generate the answer - `answer_rewards`: (list(float64)) Rewards of the answer responses - `answer_times`: (list(float64)) Elapsed time of answer responses - `answer_uids`: (list(int32)) UIDs of nodes that answered the answer_prompt - `base_prompt`: (string) Bootstrap prompt - `best_answer`: (string) Best answer response - `best_followup`: (string) Best followup response - `block`: (float64) Subtensor current block - `followup_completions`: (list(string)) Completions of the base_prompt - `followup_rewards`: (list(float64)) Rewards of the followup responses - `followup_times`: (list(float64)) Ellapsed time of followup responses - `followup_uids`: (list(int64)) UIDs of nodes that answered the base_prompt - `gating_loss`: (float64) Gating model loss - `gating_scorings`: (list(float64)) Gating model scores - `moving_averaged_scores`: (list(float64)) Moving averaged scores at the time of the event - `set_weights`: (list(list(float64))) Processed weights of nodes by uid - `step_length`: (float64) Time difference from beginning of forward call to event logging **Metadata** - `run_id`: (string) Wandb Run Id - `completed`: (boolean) Flag indicating if the run_id is completed (finished, crashed or killed) - `downloaded`: (boolean) Flag indicating if the run_id data has been downloaded - `last_checkpoint`: (string) Last checkpoint of the run_id - `hotkey`: (string) Hotkey associated with the run_id - `openvalidators_version`: (string) Version of OpenValidators associated with the run_id - `problematic`: (boolean) Flag indicating if the run_id data had problems to be ingested - `problematic_reason`: (string) Reason for the run_id being problematic (Exception message) - `wandb_json_config`: (string) JSON configuration associated with the run_id in Wandb - `wandb_run_name`: (string) Name of the Wandb run - `wandb_user_info`: (string) Username information associated with the Wandb run - `wandb_tags`: (list) List of tags associated with the Wandb run - `wandb_createdAt`: (string) Timestamp of the run creation in Wandb ## Dataset Creation ### Curation Rationale This dataset was curated to provide a comprehensive and reliable collection of historical data obtained by the execution of different OpenValidators in the bittensor network. The goal is to support researchers, data scientists and developers with data generated in the network, facilitating the discovery of new insights, network analysis, troubleshooting, and data extraction for downstream tasks like mining. ### Source Data #### Initial Data Collection and Normalization The initial data collection process for this dataset involves recurrent collection by a specialized worker responsible for extracting data from wandb and ingesting it into the Hugging Face datasets structure. The collected data is organized based on the OpenValidators version and run ID to facilitate efficient data management and granular access. Each run is collected based on its corresponding OpenValidators version tag and grouped into version-specific folders. Within each version folder, a `metadata.csv` file is included to manage the collection state, while the raw data of each run is saved in the `.parquet` format with the file name corresponding to the run ID (e.g., `run_id.parquet`). Please note that the code for this data collection process will be released for transparency and reproducibility. #### Who are the source language producers? The language producers for this dataset are all the openvalidators that are logging their data into wandb in conjunction of other nodes of the bittensor network. The main wandb page where the data is sent can be accessed at https://wandb.ai/opentensor-dev/openvalidators/table. ### Licensing Information The dataset is licensed under the [MIT License](https://github.com/opentensor/validators/blob/main/LICENSE) ### Supported Tasks and Leaderboards [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]

L4NLP/LEval

L4NLP

--- license: gpl-3.0 task_categories: - summarization - question-answering - multiple-choice language: - en size_categories: - 1K<n<10K viewer: true tags: - Long_context --- ### *L-Eval: Instituting Standardized Evaluation for Long Context Language Models* L-Eval is a comprehensive long-context language models evaluation suite with 18 long document tasks across multiple domains that require reasoning over long texts, including summarization, question answering, in-context learning with long CoT examples, topic retrieval, and paper writing assistance. L-Eval is a high-quality test set with 411 long documents and 2043 query-response pairs. All samples in L-Eval have been manually annotated and checked by the authors. There have been many studies exploring the expansion of context length in large models. However, it remains to be explored whether these methods perform well enough in downstream tasks and whether they can surpass previous methods based on retrieval or chunking. We hope L-Eval could help researchers and developers track the progress of long-context language models (LCLMs) and understand the strengths/shortcomings of different methods. Dataset list: ``` ["coursera", "gsm100", "quality", "topic_retrieval_longchat", "tpo", "financial_qa", "gov_report_summ", "legal_contract_qa", "meeting_summ", "multidoc_qa", "narrative_qa", "natural_question", "news_summ", "paper_assistant", "patent_summ", "review_summ", "scientific_qa", "tv_show_summ"] ``` Detailed descriptions and how we collect the data can be found [https://github.com/OpenLMLab/LEval](https://github.com/OpenLMLab/LEval).

roneneldan/TinyStories

roneneldan

--- license: cdla-sharing-1.0 task_categories: - text-generation language: - en --- Dataset containing synthetically generated (by GPT-3.5 and GPT-4) short stories that only use a small vocabulary. Described in the following paper: https://arxiv.org/abs/2305.07759. The models referred to in the paper were trained on TinyStories-train.txt (the file tinystories-valid.txt can be used for validation loss). These models can be found on Huggingface, at roneneldan/TinyStories-1M/3M/8M/28M/33M/1Layer-21M. Additional resources: tinystories_all_data.tar.gz - contains a superset of the stories together with metadata and the prompt that was used to create each story. TinyStoriesV2-GPT4-train.txt - Is a new version of the dataset that is based on generations by GPT-4 only (the original dataset also has generations by GPT-3.5 which are of lesser quality). It contains all the examples in TinyStories.txt which were GPT-4 generated as a subset (but is significantly larger). Evaluation_prompts.yaml: List of prompts used to evaluate our models (see paper)

sal4ahm/RealCQA

sal4ahm

--- license: mit --- # RealCQA: Real-World Complex Question Answering Dataset This repository contains the dataset used in the paper "[RealCQA: Scientific Chart Question Answering as a Test-Bed for First-Order Logic](https://arxiv.org/pdf/2308.01979)" (ICDAR 2023). The dataset is designed to facilitate research in complex question answering, involving a diverse set of real-world images and associated textual question-answer pairs. ## Dataset Overview The RealCQA dataset consists of 28,266 images, and corresponding 2 million question-answer pairs organized into three complementary subsets. Each image is accompanied by a JSON file containing one or more question blocks. The dataset is structured to address a range of question-answering tasks that require an understanding of the visual content. ### Dataset Structure The dataset is organized into the following folders: - **Images** - `images`: Contains the first 10,000 images. - `images2`: Contains the next 10,000 images. - `images3`: Contains the remaining 8,266 images. - **JSON Files** - `jsons`: Contains the JSON files corresponding to the images in the `images` folder. - `jsons2`: Contains the JSON files corresponding to the images in the `images2` folder. - `jsons3`: Contains the JSON files corresponding to the images in the `images3` folder. - **QA Files** These are the QA created in our proposed dataset. - `qa`: Contains the QA files corresponding to the images in the `images` folder. - `qa2`: Contains the QA files corresponding to the images in the `images2` folder. - `qa3`: Contains the QA files corresponding to the images in the `images3` folder. ### File Details - **Images**: JPEG files named in the format `PMCxxxxxx_abc.jpg`, where `xxxxxx` represents the PubMed Central ID and `abc` represents an identifier specific to the image. - **JSON Files**: JSON files named in the same format as the images. These are groundtruth annotations from the https://chartinfo.github.io challenge, they provide annotations for chart type, text(OCR), text location, text type (axis/tick/legend), data used to plot the chart. - **QA Files**: QA files named in the same format as the images. Each QA file is a list of question blocks associated with the corresponding image we created in our proposed dataset. #### QA Structure Each QA file contains a list of question blocks in the following format: ```json [ { "taxonomy id": "2j", "QID": "16", "question": "Are all the bars in the chart visually horizontal?", "answer": "no", "answer_type": "Binary", "qa_id": "XbUzFtjqsEOF", "PMC_ID": "PMC8439477___g003" }, { "taxonomy id": "1a", "QID": "7a", "question": "What is the type of chart?", "answer": "Vertical Bar chart", "answer_type": "String", "qa_id": "wzcdDijkrHtt", "PMC_ID": "PMC8439477___g003" } ] ``` ### Dataset Loader To facilitate loading and using the dataset, we provide a custom dataset loader script, `dataset.py`. This script defines a PyTorch `Dataset` class to handle loading, preprocessing, and batching of the images and question-answer pairs. #### How to Use the Dataset Loader 1. **Setup and Requirements** Ensure you have the following Python packages installed: ```bash pip install torch torchvision Pillow ``` 2. **Dataset Loader Script** Use the provided `dataset.py` to load the dataset. The script is designed to load the dataset efficiently and handle both training and testing cases. ```python from dataset import RQADataset from torch.utils.data import DataLoader dataset = RQADataset(data_dir='.', split='train') # split='test' for RQA9357 split used in the paper # Test loading a single item print(f"Number of samples in dataset: {len(dataset)}") sample = dataset[0] print("Sample data:", sample) # Initialize DataLoader dataloader = DataLoader(dataset, batch_size=4, collate_fn=RQADataset.custom_collate) # Test DataLoader for batch in dataloader: print("Batch data:", batch) break # Load only one batch for testing ``` ### Citation If you use this dataset in your research, please cite the following paper: ```bibtex @InProceedings{10.1007/978-3-031-41682-8_5, author="Ahmed, Saleem and Jawade, Bhavin and Pandey, Shubham and Setlur, Srirangaraj and Govindaraju, Venu", editor="Fink, Gernot A. and Jain, Rajiv and Kise, Koichi and Zanibbi, Richard", title="RealCQA: Scientific Chart Question Answering as a Test-Bed for First-Order Logic", booktitle="Document Analysis and Recognition - ICDAR 2023", year="2023", publisher="Springer Nature Switzerland", address="Cham", pages="66--83", abstract="We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents. Despite efforts to tackle this problem using synthetic charts, solutions are limited by the shortage of annotated real-world data. To fill this gap, we introduce a benchmark and dataset for chart visual QA on real-world charts, offering a systematic analysis of the task and a novel taxonomy for template-based chart question creation. Our contribution includes the introduction of a new answer type, `list', with both ranked and unranked variations. Our study is conducted on a real-world chart dataset from scientific literature, showcasing higher visual complexity compared to other works. Our focus is on template-based QA and how it can serve as a standard for evaluating the first-order logic capabilities of models. The results of our experiments, conducted on a real-world out-of-distribution dataset, provide a robust evaluation of large-scale pre-trained models and advance the field of chart visual QA and formal logic verification for neural networks in general. Our code and dataset is publicly available (https://github.com/cse-ai-lab/RealCQA).", isbn="978-3-031-41682-8" } } ``` ### License This dataset is licensed under the [MIT License](LICENSE). By using this dataset, you agree to abide by its terms and conditions. ### Contact For any questions or issues, please contact the authors of the paper or open an issue in this repository.

lerobot/berkeley_gnm_cory_hall

lerobot

--- license: mit task_categories: - robotics tags: - LeRobot configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** https://arxiv.org/abs/1709.10489 - **License:** mit ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "unknown", "total_episodes": 7331, "total_frames": 156012, "total_tasks": 1, "total_videos": 7331, "total_chunks": 8, "chunks_size": 1000, "fps": 5, "splits": { "train": "0:7331" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.images.image": { "dtype": "video", "shape": [ 64, 86, 3 ], "names": [ "height", "width", "channel" ], "video_info": { "video.fps": 5.0, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "language_instruction": { "dtype": "string", "shape": [ 1 ], "names": null }, "observation.state": { "dtype": "float32", "shape": [ 9 ], "names": { "motors": [ "motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6", "motor_7", "motor_8" ] } }, "action": { "dtype": "float32", "shape": [ 7 ], "names": { "motors": [ "motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6" ] } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "next.reward": { "dtype": "float32", "shape": [ 1 ], "names": null }, "next.done": { "dtype": "bool", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex @inproceedings{kahn2018self, title={Self-supervised deep reinforcement learning with generalized computation graphs for robot navigation}, author={Kahn, Gregory and Villaflor, Adam and Ding, Bosen and Abbeel, Pieter and Levine, Sergey}, booktitle={2018 IEEE international conference on robotics and automation (ICRA)}, pages={5129--5136}, year={2018}, organization={IEEE} } ```

liwu/MNBVC

liwu

--- annotations_creators: - other language: - zh language_creators: - other license: - mit multilinguality: - monolingual pretty_name: MNBVC size_categories: - unknown source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling --- # Dataset Card for MNBVC ## Table of Contents - [Dataset Card for MNBVC](#dataset-card-for-mnbvc) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [数据集介绍](#数据集介绍) - [数据子集](#数据子集) - [数据格式](#数据格式) - [文本数据](#文本数据) - [问答数据](#问答数据) - [Contributions](#contributions) ## Dataset Description - **Homepage:** http://mnbvc.253874.net/ - **Repository:** https://github.com/esbatmop/MNBVC - **Paper:** N/A - **Leaderboard:** N/A - **Point of Contact:** N/A ### 数据集介绍 中文互联网上最古老最神秘(没有之一)的里屋社区于2023.1.1庄重宣布: 在英明神武的里屋管子带领下，决心发挥社区所长(哪都长)，帮助开源社区长期更新一份最大的中文互联网语料集。 Huggingface上的MNBVC数据集在逐渐更新中，请到[https://github.com/esbatmop/MNBVC](https://github.com/esbatmop/MNBVC) 获取未完成清洗的更多数据。 可以使用如下脚本加载： ```python from datasets import load_dataset dataset = load_dataset("liwu/MNBVC", 'law_judgement', split='train', streaming=True) next(iter(dataset)) # get the first line ``` ## 数据子集 MNBVC数据集包含数个子集： - `law_judgement`: 来自法律文书的文本。 - `gov_xuexiqiangguo`: 来自学习强国的文本。 - `gov_report`: 来自政府工作报告的文本。 - `co_ann_report`: 企业年报文本。 - `code_metadata`: 代码元数据。 - `qa_zhihu`: 来自[知乎](https://huggingface.co/datasets/wangrui6/Zhihu-KOL)的问答数据。 - `qa_wikihow`: 来自wikihow的问答数据。 - `qa_mfa`: 外交部问答数据。 - `news_peoples_daily`: 来自人民日报的文本数据。 - `wikipedia`: 来自维基百科的文本数据。 - `qa_stackexchange`: 来自StackExchange的问答数据。 - `qa_chatgpt`: 使用ChatGPT构造的问答语料，感谢[genggui001](https://github.com/genggui001)贡献语料。 - `math`: - `math_qa `: 和数学领域有关的问答数据。 - `emath` :中国数学爱好者论坛语料数据 - `math_chat`: 和数学领域有关的对话数据数据，可以提升模型Chain of Thought的能力。 - `crawler_oscar`: 从CommonCrawl中清洗出来的通用文本数据。 - `game` : 一些游戏的平行语料数据。 - `Hogwarts_legacy` : 霍格沃茨指遗 - `The_Wither_3` : 巫师三 ## 数据格式 目前MNBVC数据集包含如下几类数据： - 通用文本 - 问答语料 - 代码语料 - 多轮对话 - 论坛语料 - 平行语料 可以在[MNBVC的wiki页面](https://wiki.mnbvc.org/doku.php/%E7%8E%B0%E6%9C%89%E8%AF%AD%E6%96%99%E6%A0%BC%E5%BC%8F)上查看这几类数据的具体格式。 项目早期所上传的数据使用如下格式，以后这一格式会被废弃，相应数据也会重新上传： ```json { "text": datasets.Value("string"), "meta": datasets.Value("string") } ``` ### Contributions Thanks to the [Liwu community](http://mnbvc.253874.net/) for constructing this dataset. Thanks to [silver](https://github.com/silverriver) and [jiaming](https://huggingface.co/Yjiaming) for adding and uploading this dataset to Huggingface. ### Citation Please cite the repo if you use the data or code in this repo. ``` @misc{mnbvc, author = {{MOP-LIWU Community} and {MNBVC Team}}, title = {MNBVC: Massive Never-ending BT Vast Chinese corpus}, year = {2023}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/esbatmop/MNBVC}}, } ```

Stevross/mmlu

Stevross

--- annotations_creators: - no-annotation language_creators: - expert-generated language: - en license: - mit multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - question-answering task_ids: - multiple-choice-qa paperswithcode_id: mmlu pretty_name: Measuring Massive Multitask Language Understanding language_bcp47: - en-US dataset_info: - config_name: abstract_algebra features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 19328 num_examples: 100 - name: validation num_bytes: 2024 num_examples: 11 - name: dev num_bytes: 830 num_examples: 5 download_size: 166184960 dataset_size: 160623559 - config_name: anatomy features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 33121 num_examples: 135 - name: validation num_bytes: 3140 num_examples: 14 - name: dev num_bytes: 967 num_examples: 5 download_size: 166184960 dataset_size: 160638605 - config_name: astronomy features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 46771 num_examples: 152 - name: validation num_bytes: 5027 num_examples: 16 - name: dev num_bytes: 2076 num_examples: 5 download_size: 166184960 dataset_size: 160655251 - config_name: business_ethics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 33252 num_examples: 100 - name: validation num_bytes: 3038 num_examples: 11 - name: dev num_bytes: 2190 num_examples: 5 download_size: 166184960 dataset_size: 160639857 - config_name: clinical_knowledge features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 62754 num_examples: 265 - name: validation num_bytes: 6664 num_examples: 29 - name: dev num_bytes: 1210 num_examples: 5 download_size: 166184960 dataset_size: 160672005 - config_name: college_biology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 48797 num_examples: 144 - name: validation num_bytes: 4819 num_examples: 16 - name: dev num_bytes: 1532 num_examples: 5 download_size: 166184960 dataset_size: 160656525 - config_name: college_chemistry features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 24708 num_examples: 100 - name: validation num_bytes: 2328 num_examples: 8 - name: dev num_bytes: 1331 num_examples: 5 download_size: 166184960 dataset_size: 160629744 - config_name: college_computer_science features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 42641 num_examples: 100 - name: validation num_bytes: 4663 num_examples: 11 - name: dev num_bytes: 2765 num_examples: 5 download_size: 166184960 dataset_size: 160651446 - config_name: college_mathematics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 24711 num_examples: 100 - name: validation num_bytes: 2668 num_examples: 11 - name: dev num_bytes: 1493 num_examples: 5 download_size: 166184960 dataset_size: 160630249 - config_name: college_medicine features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 82397 num_examples: 173 - name: validation num_bytes: 7909 num_examples: 22 - name: dev num_bytes: 1670 num_examples: 5 download_size: 166184960 dataset_size: 160693353 - config_name: college_physics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 30181 num_examples: 102 - name: validation num_bytes: 3490 num_examples: 11 - name: dev num_bytes: 1412 num_examples: 5 download_size: 166184960 dataset_size: 160636460 - config_name: computer_security features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 27124 num_examples: 100 - name: validation num_bytes: 4549 num_examples: 11 - name: dev num_bytes: 1101 num_examples: 5 download_size: 166184960 dataset_size: 160634151 - config_name: conceptual_physics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 40709 num_examples: 235 - name: validation num_bytes: 4474 num_examples: 26 - name: dev num_bytes: 934 num_examples: 5 download_size: 166184960 dataset_size: 160647494 - config_name: econometrics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 46547 num_examples: 114 - name: validation num_bytes: 4967 num_examples: 12 - name: dev num_bytes: 1644 num_examples: 5 download_size: 166184960 dataset_size: 160654535 - config_name: electrical_engineering features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 25142 num_examples: 145 - name: validation num_bytes: 2903 num_examples: 16 - name: dev num_bytes: 972 num_examples: 5 download_size: 166184960 dataset_size: 160630394 - config_name: elementary_mathematics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 70108 num_examples: 378 - name: validation num_bytes: 8988 num_examples: 41 - name: dev num_bytes: 1440 num_examples: 5 download_size: 166184960 dataset_size: 160681913 - config_name: formal_logic features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 49785 num_examples: 126 - name: validation num_bytes: 6252 num_examples: 14 - name: dev num_bytes: 1757 num_examples: 5 download_size: 166184960 dataset_size: 160659171 - config_name: global_facts features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 18403 num_examples: 100 - name: validation num_bytes: 1865 num_examples: 10 - name: dev num_bytes: 1229 num_examples: 5 download_size: 166184960 dataset_size: 160622874 - config_name: high_school_biology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 109732 num_examples: 310 - name: validation num_bytes: 11022 num_examples: 32 - name: dev num_bytes: 1673 num_examples: 5 download_size: 166184960 dataset_size: 160723804 - config_name: high_school_chemistry features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 58464 num_examples: 203 - name: validation num_bytes: 7092 num_examples: 22 - name: dev num_bytes: 1220 num_examples: 5 download_size: 166184960 dataset_size: 160668153 - config_name: high_school_computer_science features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 44476 num_examples: 100 - name: validation num_bytes: 3343 num_examples: 9 - name: dev num_bytes: 2918 num_examples: 5 download_size: 166184960 dataset_size: 160652114 - config_name: high_school_european_history features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 270300 num_examples: 165 - name: validation num_bytes: 29632 num_examples: 18 - name: dev num_bytes: 11564 num_examples: 5 download_size: 166184960 dataset_size: 160912873 - config_name: high_school_geography features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 42034 num_examples: 198 - name: validation num_bytes: 4332 num_examples: 22 - name: dev num_bytes: 1403 num_examples: 5 download_size: 166184960 dataset_size: 160649146 - config_name: high_school_government_and_politics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 66074 num_examples: 193 - name: validation num_bytes: 7063 num_examples: 21 - name: dev num_bytes: 1779 num_examples: 5 download_size: 166184960 dataset_size: 160676293 - config_name: high_school_macroeconomics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 117687 num_examples: 390 - name: validation num_bytes: 13020 num_examples: 43 - name: dev num_bytes: 1328 num_examples: 5 download_size: 166184960 dataset_size: 160733412 - config_name: high_school_mathematics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 54854 num_examples: 270 - name: validation num_bytes: 5765 num_examples: 29 - name: dev num_bytes: 1297 num_examples: 5 download_size: 166184960 dataset_size: 160663293 - config_name: high_school_microeconomics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 75703 num_examples: 238 - name: validation num_bytes: 7553 num_examples: 26 - name: dev num_bytes: 1298 num_examples: 5 download_size: 166184960 dataset_size: 160685931 - config_name: high_school_physics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 59538 num_examples: 151 - name: validation num_bytes: 6771 num_examples: 17 - name: dev num_bytes: 1489 num_examples: 5 download_size: 166184960 dataset_size: 160669175 - config_name: high_school_psychology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 159407 num_examples: 545 - name: validation num_bytes: 17269 num_examples: 60 - name: dev num_bytes: 1905 num_examples: 5 download_size: 166184960 dataset_size: 160779958 - config_name: high_school_statistics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 110702 num_examples: 216 - name: validation num_bytes: 9997 num_examples: 23 - name: dev num_bytes: 2528 num_examples: 5 download_size: 166184960 dataset_size: 160724604 - config_name: high_school_us_history features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 296734 num_examples: 204 - name: validation num_bytes: 31706 num_examples: 22 - name: dev num_bytes: 8864 num_examples: 5 download_size: 166184960 dataset_size: 160938681 - config_name: high_school_world_history features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 378617 num_examples: 237 - name: validation num_bytes: 45501 num_examples: 26 - name: dev num_bytes: 4882 num_examples: 5 download_size: 166184960 dataset_size: 161030377 - config_name: human_aging features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 46098 num_examples: 223 - name: validation num_bytes: 4707 num_examples: 23 - name: dev num_bytes: 1008 num_examples: 5 download_size: 166184960 dataset_size: 160653190 - config_name: human_sexuality features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 32110 num_examples: 131 - name: validation num_bytes: 2421 num_examples: 12 - name: dev num_bytes: 1077 num_examples: 5 download_size: 166184960 dataset_size: 160636985 - config_name: international_law features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 53531 num_examples: 121 - name: validation num_bytes: 6473 num_examples: 13 - name: dev num_bytes: 2418 num_examples: 5 download_size: 166184960 dataset_size: 160663799 - config_name: jurisprudence features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 33986 num_examples: 108 - name: validation num_bytes: 3729 num_examples: 11 - name: dev num_bytes: 1303 num_examples: 5 download_size: 166184960 dataset_size: 160640395 - config_name: logical_fallacies features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 50117 num_examples: 163 - name: validation num_bytes: 5103 num_examples: 18 - name: dev num_bytes: 1573 num_examples: 5 download_size: 166184960 dataset_size: 160658170 - config_name: machine_learning features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 33880 num_examples: 112 - name: validation num_bytes: 3232 num_examples: 11 - name: dev num_bytes: 2323 num_examples: 5 download_size: 166184960 dataset_size: 160640812 - config_name: management features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 20002 num_examples: 103 - name: validation num_bytes: 1820 num_examples: 11 - name: dev num_bytes: 898 num_examples: 5 download_size: 166184960 dataset_size: 160624097 - config_name: marketing features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 63025 num_examples: 234 - name: validation num_bytes: 7394 num_examples: 25 - name: dev num_bytes: 1481 num_examples: 5 download_size: 166184960 dataset_size: 160673277 - config_name: medical_genetics features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 20864 num_examples: 100 - name: validation num_bytes: 3005 num_examples: 11 - name: dev num_bytes: 1089 num_examples: 5 download_size: 166184960 dataset_size: 160626335 - config_name: miscellaneous features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 147704 num_examples: 783 - name: validation num_bytes: 14330 num_examples: 86 - name: dev num_bytes: 699 num_examples: 5 download_size: 166184960 dataset_size: 160764110 - config_name: moral_disputes features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 107818 num_examples: 346 - name: validation num_bytes: 12420 num_examples: 38 - name: dev num_bytes: 1755 num_examples: 5 download_size: 166184960 dataset_size: 160723370 - config_name: moral_scenarios features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 374026 num_examples: 895 - name: validation num_bytes: 42338 num_examples: 100 - name: dev num_bytes: 2058 num_examples: 5 download_size: 166184960 dataset_size: 161019799 - config_name: nutrition features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 92410 num_examples: 306 - name: validation num_bytes: 8436 num_examples: 33 - name: dev num_bytes: 2085 num_examples: 5 download_size: 166184960 dataset_size: 160704308 - config_name: philosophy features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 80073 num_examples: 311 - name: validation num_bytes: 9184 num_examples: 34 - name: dev num_bytes: 988 num_examples: 5 download_size: 166184960 dataset_size: 160691622 - config_name: prehistory features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 89594 num_examples: 324 - name: validation num_bytes: 10285 num_examples: 35 - name: dev num_bytes: 1878 num_examples: 5 download_size: 166184960 dataset_size: 160703134 - config_name: professional_accounting features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 124550 num_examples: 282 - name: validation num_bytes: 14372 num_examples: 31 - name: dev num_bytes: 2148 num_examples: 5 download_size: 166184960 dataset_size: 160742447 - config_name: professional_law features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 1891762 num_examples: 1534 - name: validation num_bytes: 203519 num_examples: 170 - name: dev num_bytes: 6610 num_examples: 5 download_size: 166184960 dataset_size: 162703268 - config_name: professional_medicine features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 217561 num_examples: 272 - name: validation num_bytes: 23847 num_examples: 31 - name: dev num_bytes: 3807 num_examples: 5 download_size: 166184960 dataset_size: 160846592 - config_name: professional_psychology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 225899 num_examples: 612 - name: validation num_bytes: 29101 num_examples: 69 - name: dev num_bytes: 2267 num_examples: 5 download_size: 166184960 dataset_size: 160858644 - config_name: public_relations features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 28760 num_examples: 110 - name: validation num_bytes: 4566 num_examples: 12 - name: dev num_bytes: 1496 num_examples: 5 download_size: 166184960 dataset_size: 160636199 - config_name: security_studies features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 204844 num_examples: 245 - name: validation num_bytes: 22637 num_examples: 27 - name: dev num_bytes: 5335 num_examples: 5 download_size: 166184960 dataset_size: 160834193 - config_name: sociology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 66243 num_examples: 201 - name: validation num_bytes: 7184 num_examples: 22 - name: dev num_bytes: 1613 num_examples: 5 download_size: 166184960 dataset_size: 160676417 - config_name: us_foreign_policy features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 28443 num_examples: 100 - name: validation num_bytes: 3264 num_examples: 11 - name: dev num_bytes: 1611 num_examples: 5 download_size: 166184960 dataset_size: 160634695 - config_name: virology features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 38759 num_examples: 166 - name: validation num_bytes: 5463 num_examples: 18 - name: dev num_bytes: 1096 num_examples: 5 download_size: 166184960 dataset_size: 160646695 - config_name: world_religions features: - name: question dtype: string - name: choices sequence: string - name: answer dtype: class_label: names: '0': A '1': B '2': C '3': D splits: - name: auxiliary_train num_bytes: 160601377 num_examples: 99842 - name: test num_bytes: 25274 num_examples: 171 - name: validation num_bytes: 2765 num_examples: 19 - name: dev num_bytes: 670 num_examples: 5 download_size: 166184960 dataset_size: 160630086 --- # Dataset Card for MMLU ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository**: https://github.com/hendrycks/test - **Paper**: https://arxiv.org/abs/2009.03300 ### Dataset Summary [Measuring Massive Multitask Language Understanding](https://arxiv.org/pdf/2009.03300) by [Dan Hendrycks](https://people.eecs.berkeley.edu/~hendrycks/), [Collin Burns](http://collinpburns.com), [Steven Basart](https://stevenbas.art), Andy Zou, Mantas Mazeika, [Dawn Song](https://people.eecs.berkeley.edu/~dawnsong/), and [Jacob Steinhardt](https://www.stat.berkeley.edu/~jsteinhardt/) (ICLR 2021). This is a massive multitask test consisting of multiple-choice questions from various branches of knowledge. The test spans subjects in the humanities, social sciences, hard sciences, and other areas that are important for some people to learn. This covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability. A complete list of tasks: ['abstract_algebra', 'anatomy', 'astronomy', 'business_ethics', 'clinical_knowledge', 'college_biology', 'college_chemistry', 'college_computer_science', 'college_mathematics', 'college_medicine', 'college_physics', 'computer_security', 'conceptual_physics', 'econometrics', 'electrical_engineering', 'elementary_mathematics', 'formal_logic', 'global_facts', 'high_school_biology', 'high_school_chemistry', 'high_school_computer_science', 'high_school_european_history', 'high_school_geography', 'high_school_government_and_politics', 'high_school_macroeconomics', 'high_school_mathematics', 'high_school_microeconomics', 'high_school_physics', 'high_school_psychology', 'high_school_statistics', 'high_school_us_history', 'high_school_world_history', 'human_aging', 'human_sexuality', 'international_law', 'jurisprudence', 'logical_fallacies', 'machine_learning', 'management', 'marketing', 'medical_genetics', 'miscellaneous', 'moral_disputes', 'moral_scenarios', 'nutrition', 'philosophy', 'prehistory', 'professional_accounting', 'professional_law', 'professional_medicine', 'professional_psychology', 'public_relations', 'security_studies', 'sociology', 'us_foreign_policy', 'virology', 'world_religions'] ### Supported Tasks and Leaderboards | Model | Authors | Humanities | Social Science | STEM | Other | Average | |------------------------------------|----------|:-------:|:-------:|:-------:|:-------:|:-------:| | [UnifiedQA](https://arxiv.org/abs/2005.00700) | Khashabi et al., 2020 | 45.6 | 56.6 | 40.2 | 54.6 | 48.9 | [GPT-3](https://arxiv.org/abs/2005.14165) (few-shot) | Brown et al., 2020 | 40.8 | 50.4 | 36.7 | 48.8 | 43.9 | [GPT-2](https://arxiv.org/abs/2005.14165) | Radford et al., 2019 | 32.8 | 33.3 | 30.2 | 33.1 | 32.4 | Random Baseline | N/A | 25.0 | 25.0 | 25.0 | 25.0 | 25.0 | 25.0 ### Languages English ## Dataset Structure ### Data Instances An example from anatomy subtask looks as follows: ``` { "question": "What is the embryological origin of the hyoid bone?", "choices": ["The first pharyngeal arch", "The first and second pharyngeal arches", "The second pharyngeal arch", "The second and third pharyngeal arches"], "answer": "D" } ``` ### Data Fields - `question`: a string feature - `choices`: a list of 4 string features - `answer`: a ClassLabel feature ### Data Splits - `auxiliary_train`: auxiliary multiple-choice training questions from ARC, MC_TEST, OBQA, RACE, etc. - `dev`: 5 examples per subtask, meant for few-shot setting - `test`: there are at least 100 examples per subtask | | auxiliary_train | dev | val | test | | ----- | :------: | :-----: | :-----: | :-----: | | TOTAL | 99842 | 285 | 1531 | 14042 ## Dataset Creation ### Curation Rationale Transformer models have driven this recent progress by pretraining on massive text corpora, including all of Wikipedia, thousands of books, and numerous websites. These models consequently see extensive information about specialized topics, most of which is not assessed by existing NLP benchmarks. To bridge the gap between the wide-ranging knowledge that models see during pretraining and the existing measures of success, we introduce a new benchmark for assessing models across a diverse set of subjects that humans learn. ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [MIT License](https://github.com/hendrycks/test/blob/master/LICENSE) ### Citation Information If you find this useful in your research, please consider citing the test and also the [ETHICS](https://arxiv.org/abs/2008.02275) dataset it draws from: ``` @article{hendryckstest2021, title={Measuring Massive Multitask Language Understanding}, author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt}, journal={Proceedings of the International Conference on Learning Representations (ICLR)}, year={2021} } @article{hendrycks2021ethics, title={Aligning AI With Shared Human Values}, author={Dan Hendrycks and Collin Burns and Steven Basart and Andrew Critch and Jerry Li and Dawn Song and Jacob Steinhardt}, journal={Proceedings of the International Conference on Learning Representations (ICLR)}, year={2021} } ``` ### Contributions Thanks to [@andyzoujm](https://github.com/andyzoujm) for adding this dataset.

laion/strategic_game_chess

laion

--- tags: - game pretty_name: The Chess Dataset license: cc-by-4.0 --- # Chess > Recent advancements in artificial intelligence (AI) underscore the progress of reasoning and planning shown by recent generalist machine learning (ML) models. The progress can be boosted by datasets that can further boost these generic capabilities when used for training foundation models of various kind. This research initiative has generated extensive synthetic datasets from complex games — chess, Rubik's Cube, and mazes — to study facilitation and the advancement of these critical generic skills in AI models. This dataset contains 3.2 billion games, equating to approximately 608 billion individual moves. it is generated through self-play by Stockfish engine using Fugaku and we add initial moves to expand its diversity. Each game has three columns: 'Moves', 'Termination' and 'Result', - 'Move': recorded chess moves of the whole game. - 'Termination': include CHECKMATE, INSUFFICIENT_MATERIAL, ... etc. - Please check this for detail information https://python-chess.readthedocs.io/en/latest/core.html#chess.Outcome.termination - 'Result': result of this game, 1-0, 1/2-1/2, 0-1. ### Call for Collaboration We invite interested researchers and ML practitioners to explore these datasets' potential. Whether training GPT models from scratch or fine-tuning pre-existing models, we encourage the exploration of various pre-training and fine-tuning strategies using these game-based datasets standalone or as enhancement of other already composed large-scale data. Our team is prepared to assist in securing necessary GPU resources for these explorations. We are particularly interested in collaborators eager to pre-train models of small to medium scale on our game data, subsequently transition to standard text-based training, and then perform comparative analyses against models of similar architecture trained exclusively on text data. Conclusively, this initiative marks a significant stride toward intricate problem-solving and strategic planning in AI, extending an open invitation to the research community for collaborative advancement in this domain.

bigscience/xP3all

bigscience

--- annotations_creators: - expert-generated - crowdsourced language: - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso - ny - or - pa - pt - rn - rw - sn - st - sw - ta - te - tn - ts - tum - tw - ur - vi - wo - xh - yo - zh - zu programming_language: - C - C++ - C# - Go - Java - JavaScript - Lua - PHP - Python - Ruby - Rust - Scala - TypeScript license: - apache-2.0 multilinguality: - multilingual pretty_name: xP3 size_categories: - 100M<n<1B task_categories: - other --- # Dataset Card for xP3 ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Additional Information](#additional-information) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository:** https://github.com/bigscience-workshop/xmtf - **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Niklas Muennighoff](mailto:[email protected]) ### Dataset Summary > xP3 (Crosslingual Public Pool of Prompts) is a collection of prompts & datasets across 46 of languages & 16 NLP tasks. It is used for the training of BLOOMZ and mT0, multilingual language models capable of following human instructions in dozens of languages zero-shot. - **Creation:** The dataset can be recreated using instructions available [here](https://github.com/bigscience-workshop/xmtf#create-xp3). We provide this version to save processing time and ease reproducibility. - **Languages:** 46 (Can be extended by [recreating with more splits](https://github.com/bigscience-workshop/xmtf#create-xp3)) - **xP3 Dataset Family:** <table> <tr> <th>Name</th> <th>Explanation</th> <th>Example models</th> </tr> <tr> <td><a href=https://huggingface.co/datasets/Muennighoff/xP3x>xP3x</a></t> <td>Mixture of 17 tasks in 277 languages with English prompts</td> <td>WIP - Join us at Project Aya @<a href=https://cohere.for.ai/>C4AI</a> to help!</td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3>xP3</a></t> <td>Mixture of 13 training tasks in 46 languages with English prompts</td> <td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a> & <a href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a></t> <td>Mixture of 13 training tasks in 46 languages with prompts in 20 languages (machine-translated from English)</td> <td><a href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a> & <a href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3all>xP3all</a></t> <td>xP3 + evaluation datasets adding an additional 3 tasks for a total of 16 tasks in 46 languages with English prompts</td> <td></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/bigscience/xP3megds>xP3megds</a></t> <td><a href=https://github.com/bigscience-workshop/Megatron-DeepSpeed>Megatron-DeepSpeed</a> processed version of xP3</td> <td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a></td> </tr> <tr> <td><a href=https://huggingface.co/datasets/Muennighoff/P3>P3</a></t> <td>Repreprocessed version of the English-only <a href=https://huggingface.co/datasets/bigscience/P3>P3</a> with 8 training tasks</td> <td><a href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a> & <a href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td> </tr> </table> ## Dataset Structure ### Data Instances An example of "train" looks as follows: ```json { "inputs": "Sentence 1: Fue académico en literatura metafísica, teología y ciencias clásicas.\nSentence 2: Fue académico en literatura metafísica, teología y ciencia clásica.\nQuestion: Can we rewrite Sentence 1 to Sentence 2? Yes or No?", "targets": "Yes" } ``` ### Data Fields The data fields are the same among all splits: - `inputs`: the natural language input fed to the model - `targets`: the natural language target that the model has to generate ### Data Splits The below table summarizes sizes per language (computed from the `merged_{lang}.jsonl` files). Due to languages like `tw` only being single sentence translation samples from Flores, their byte percentage is significantly lower than their sample percentage. |Language|Kilobytes|%|Samples|%| |--------|------:|-:|---:|-:| |tw|106288|0.11|265071|0.33| |bm|107056|0.11|265180|0.33| |ak|108096|0.11|265071|0.33| |ca|110608|0.11|271191|0.33| |eu|113008|0.11|281199|0.35| |fon|113072|0.11|265063|0.33| |st|114080|0.11|265063|0.33| |ki|115040|0.12|265180|0.33| |tum|116032|0.12|265063|0.33| |wo|122560|0.12|365063|0.45| |ln|126304|0.13|365060|0.45| |as|156256|0.16|265063|0.33| |or|161472|0.16|265063|0.33| |kn|165456|0.17|265063|0.33| |ml|175040|0.18|265864|0.33| |rn|192992|0.19|318189|0.39| |nso|229712|0.23|915051|1.13| |tn|235536|0.24|915054|1.13| |lg|235936|0.24|915021|1.13| |rw|249360|0.25|915043|1.13| |ts|250256|0.25|915044|1.13| |sn|252496|0.25|865056|1.07| |xh|254672|0.26|915058|1.13| |zu|263712|0.26|915061|1.13| |ny|272128|0.27|915063|1.13| |ig|325232|0.33|950097|1.17| |yo|352784|0.35|918416|1.13| |ne|393680|0.39|315754|0.39| |pa|523248|0.52|339210|0.42| |gu|560688|0.56|347499|0.43| |sw|566656|0.57|1130481|1.4| |mr|666240|0.67|417269|0.52| |bn|832720|0.83|428843|0.53| |ta|926912|0.93|415433|0.51| |te|1343232|1.35|584590|0.72| |ur|1918272|1.92|855756|1.06| |vi|3102512|3.11|1672106|2.07| |code|4330752|4.34|2707724|3.34| |hi|4403568|4.41|1554667|1.92| |zh|4599440|4.61|3589234|4.43| |id|4612256|4.62|2643418|3.27| |ar|4683456|4.69|2160181|2.67| |fr|6591120|6.6|5316403|6.57| |pt|6886800|6.9|3752156|4.63| |es|8587920|8.6|5413205|6.69| |en|39252528|39.33|32740750|40.44| |total|99807184|100.0|80956089|100.0| ## Dataset Creation ### Source Data #### Training datasets - Code Miscellaneous - [CodeComplex](https://huggingface.co/datasets/codeparrot/codecomplex) - [Docstring Corpus](https://huggingface.co/datasets/teven/code_docstring_corpus) - [GreatCode](https://huggingface.co/datasets/great_code) - [State Changes](https://huggingface.co/datasets/Fraser/python-state-changes) - Closed-book QA - [Hotpot QA](https://huggingface.co/datasets/hotpot_qa) - [Trivia QA](https://huggingface.co/datasets/trivia_qa) - [Web Questions](https://huggingface.co/datasets/web_questions) - [Wiki QA](https://huggingface.co/datasets/wiki_qa) - Extractive QA - [Adversarial QA](https://huggingface.co/datasets/adversarial_qa) - [CMRC2018](https://huggingface.co/datasets/cmrc2018) - [DRCD](https://huggingface.co/datasets/clue) - [DuoRC](https://huggingface.co/datasets/duorc) - [MLQA](https://huggingface.co/datasets/mlqa) - [Quoref](https://huggingface.co/datasets/quoref) - [ReCoRD](https://huggingface.co/datasets/super_glue) - [ROPES](https://huggingface.co/datasets/ropes) - [SQuAD v2](https://huggingface.co/datasets/squad_v2) - [xQuAD](https://huggingface.co/datasets/xquad) - TyDI QA - [Primary](https://huggingface.co/datasets/khalidalt/tydiqa-primary) - [Goldp](https://huggingface.co/datasets/khalidalt/tydiqa-goldp) - Multiple-Choice QA - [ARC](https://huggingface.co/datasets/ai2_arc) - [C3](https://huggingface.co/datasets/c3) - [CoS-E](https://huggingface.co/datasets/cos_e) - [Cosmos](https://huggingface.co/datasets/cosmos) - [DREAM](https://huggingface.co/datasets/dream) - [MultiRC](https://huggingface.co/datasets/super_glue) - [OpenBookQA](https://huggingface.co/datasets/openbookqa) - [PiQA](https://huggingface.co/datasets/piqa) - [QUAIL](https://huggingface.co/datasets/quail) - [QuaRel](https://huggingface.co/datasets/quarel) - [QuaRTz](https://huggingface.co/datasets/quartz) - [QASC](https://huggingface.co/datasets/qasc) - [RACE](https://huggingface.co/datasets/race) - [SciQ](https://huggingface.co/datasets/sciq) - [Social IQA](https://huggingface.co/datasets/social_i_qa) - [Wiki Hop](https://huggingface.co/datasets/wiki_hop) - [WiQA](https://huggingface.co/datasets/wiqa) - Paraphrase Identification - [MRPC](https://huggingface.co/datasets/super_glue) - [PAWS](https://huggingface.co/datasets/paws) - [PAWS-X](https://huggingface.co/datasets/paws-x) - [QQP](https://huggingface.co/datasets/qqp) - Program Synthesis - [APPS](https://huggingface.co/datasets/codeparrot/apps) - [CodeContests](https://huggingface.co/datasets/teven/code_contests) - [JupyterCodePairs](https://huggingface.co/datasets/codeparrot/github-jupyter-text-code-pairs) - [MBPP](https://huggingface.co/datasets/Muennighoff/mbpp) - [NeuralCodeSearch](https://huggingface.co/datasets/neural_code_search) - [XLCoST](https://huggingface.co/datasets/codeparrot/xlcost-text-to-code) - Structure-to-text - [Common Gen](https://huggingface.co/datasets/common_gen) - [Wiki Bio](https://huggingface.co/datasets/wiki_bio) - Sentiment - [Amazon](https://huggingface.co/datasets/amazon_polarity) - [App Reviews](https://huggingface.co/datasets/app_reviews) - [IMDB](https://huggingface.co/datasets/imdb) - [Rotten Tomatoes](https://huggingface.co/datasets/rotten_tomatoes) - [Yelp](https://huggingface.co/datasets/yelp_review_full) - Simplification - [BiSECT](https://huggingface.co/datasets/GEM/BiSECT) - Summarization - [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail) - [Gigaword](https://huggingface.co/datasets/gigaword) - [MultiNews](https://huggingface.co/datasets/multi_news) - [SamSum](https://huggingface.co/datasets/samsum) - [Wiki-Lingua](https://huggingface.co/datasets/GEM/wiki_lingua) - [XLSum](https://huggingface.co/datasets/GEM/xlsum) - [XSum](https://huggingface.co/datasets/xsum) - Topic Classification - [AG News](https://huggingface.co/datasets/ag_news) - [DBPedia](https://huggingface.co/datasets/dbpedia_14) - [TNEWS](https://huggingface.co/datasets/clue) - [TREC](https://huggingface.co/datasets/trec) - [CSL](https://huggingface.co/datasets/clue) - Translation - [Flores-200](https://huggingface.co/datasets/Muennighoff/flores200) - [Tatoeba](https://huggingface.co/datasets/Helsinki-NLP/tatoeba_mt) - Word Sense disambiguation - [WiC](https://huggingface.co/datasets/super_glue) - [XL-WiC](https://huggingface.co/datasets/pasinit/xlwic) #### Evaluation datasets (included in [xP3all](https://huggingface.co/datasets/bigscience/xP3all) except for HumanEval) - Natural Language Inference - [ANLI](https://huggingface.co/datasets/anli) - [CB](https://huggingface.co/datasets/super_glue) - [RTE](https://huggingface.co/datasets/super_glue) - [XNLI](https://huggingface.co/datasets/xnli) - Coreference Resolution - [Winogrande](https://huggingface.co/datasets/winogrande) - [XWinograd](https://huggingface.co/datasets/Muennighoff/xwinograd) - Program Synthesis - [HumanEval](https://huggingface.co/datasets/openai_humaneval) - Sentence Completion - [COPA](https://huggingface.co/datasets/super_glue) - [Story Cloze](https://huggingface.co/datasets/story_cloze) - [XCOPA](https://huggingface.co/datasets/xcopa) - [XStoryCloze](https://huggingface.co/datasets/Muennighoff/xstory_cloze) #### Additional [xP3all](https://huggingface.co/datasets/bigscience/xP3all) datasets - Coreference Resolution - [WSC (Fixed)](https://huggingface.co/datasets/super_glue) - Sentence Completion - [HellaSwag](https://huggingface.co/datasets/hellaswag) - Translation - [MultiEurlex](https://huggingface.co/datasets/multi_eurlex) ## Additional Information ### Licensing Information The dataset is released under Apache 2.0. ### Citation Information ```bibtex @misc{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Niklas Muennighoff and Thomas Wang and Lintang Sutawika and Adam Roberts and Stella Biderman and Teven Le Scao and M Saiful Bari and Sheng Shen and Zheng-Xin Yong and Hailey Schoelkopf and Xiangru Tang and Dragomir Radev and Alham Fikri Aji and Khalid Almubarak and Samuel Albanie and Zaid Alyafeai and Albert Webson and Edward Raff and Colin Raffel}, year={2022}, eprint={2211.01786}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to the contributors of [promptsource](https://github.com/bigscience-workshop/promptsource/graphs/contributors) for adding many prompts used in this dataset.

lerobot/stanford_robocook

lerobot

--- license: mit task_categories: - robotics tags: - LeRobot configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** https://hshi74.github.io/robocook/ - **Paper:** https://arxiv.org/abs/2306.14447 - **License:** mit ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "unknown", "total_episodes": 2460, "total_frames": 112980, "total_tasks": 9, "total_videos": 9840, "total_chunks": 3, "chunks_size": 1000, "fps": 5, "splits": { "train": "0:2460" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.images.image_1": { "dtype": "video", "shape": [ 256, 256, 3 ], "names": [ "height", "width", "channel" ], "video_info": { "video.fps": 5.0, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.image_2": { "dtype": "video", "shape": [ 256, 256, 3 ], "names": [ "height", "width", "channel" ], "video_info": { "video.fps": 5.0, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.image_4": { "dtype": "video", "shape": [ 256, 256, 3 ], "names": [ "height", "width", "channel" ], "video_info": { "video.fps": 5.0, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "observation.images.image_3": { "dtype": "video", "shape": [ 256, 256, 3 ], "names": [ "height", "width", "channel" ], "video_info": { "video.fps": 5.0, "video.codec": "av1", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "language_instruction": { "dtype": "string", "shape": [ 1 ], "names": null }, "observation.state": { "dtype": "float32", "shape": [ 8 ], "names": { "motors": [ "motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6", "motor_7" ] } }, "action": { "dtype": "float32", "shape": [ 7 ], "names": { "motors": [ "motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6" ] } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "next.reward": { "dtype": "float32", "shape": [ 1 ], "names": null }, "next.done": { "dtype": "bool", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex @article{shi2023robocook, title={RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools}, author={Shi, Haochen and Xu, Huazhe and Clarke, Samuel and Li, Yunzhu and Wu, Jiajun}, journal={arXiv preprint arXiv:2306.14447}, year={2023} } ```

qmeeus/vp-er-10l

qmeeus

--- dataset_info: - config_name: cs features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string splits: - name: train num_bytes: 3968868756 num_examples: 12000 download_size: 3963196917 dataset_size: 3968868756 - config_name: de features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 3498200501 num_examples: 12000 download_size: 3487997831 dataset_size: 3498200501 - config_name: en features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4000276474 num_examples: 12000 download_size: 3984332876 dataset_size: 4000276474 - config_name: es features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4138004589 num_examples: 12000 download_size: 4128702065 dataset_size: 4138004589 - config_name: fr features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 3915210199 num_examples: 12000 download_size: 3906302179 dataset_size: 3915210199 - config_name: hu features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4174219387 num_examples: 12000 download_size: 4167484051 dataset_size: 4174219387 - config_name: it features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4732854879 num_examples: 12000 download_size: 4722455587 dataset_size: 4732854879 - config_name: nl features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 3162694343 num_examples: 12000 download_size: 3154090731 dataset_size: 3162694343 - config_name: pl features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4041042730 num_examples: 12000 download_size: 4033450852 dataset_size: 4041042730 - config_name: ro features: - name: audio_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: language dtype: string - name: transcription dtype: string - name: translation dtype: string - name: wer dtype: float32 splits: - name: train num_bytes: 4341972777 num_examples: 12000 download_size: 4334737748 dataset_size: 4341972777 configs: - config_name: cs data_files: - split: train path: cs/train-* - config_name: de data_files: - split: train path: de/train-* - config_name: en data_files: - split: train path: en/train-* - config_name: es data_files: - split: train path: es/train-* - config_name: fr data_files: - split: train path: fr/train-* - config_name: hu data_files: - split: train path: hu/train-* - config_name: it data_files: - split: train path: it/train-* - config_name: nl data_files: - split: train path: nl/train-* - config_name: pl data_files: - split: train path: pl/train-* - config_name: ro data_files: - split: train path: ro/train-* language: - cs - de - en - es - fr - hu - it - nl - pl - ro tags: - speech-to-text - speech-translation - automatic-speech-recognition - language-detection --- # Dataset Card for "vp-er-10l" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

asahi417/seamless-align-enA-jaA.speaker-embedding.hubert-xl

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10876520133 num_examples: 2073 download_size: 10908762452 dataset_size: 10876520133 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9674569297 num_examples: 1961 download_size: 9700306271 dataset_size: 9674569297 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9422313471 num_examples: 1757 download_size: 9447085440 dataset_size: 9422313471 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9998168326 num_examples: 1873 download_size: 10027347383 dataset_size: 9998168326 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10287499716 num_examples: 1868 download_size: 10317718412 dataset_size: 10287499716 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10324121806 num_examples: 1879 download_size: 10354352259 dataset_size: 10324121806 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10263173609 num_examples: 1901 download_size: 10293587612 dataset_size: 10263173609 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10125643360 num_examples: 1875 download_size: 10152113436 dataset_size: 10125643360 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10184641498 num_examples: 1880 download_size: 10213159494 dataset_size: 10184641498 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9945312725 num_examples: 1854 download_size: 9974410300 dataset_size: 9945312725 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10122729548 num_examples: 1834 download_size: 10152878773 dataset_size: 10122729548 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9646581786 num_examples: 1770 download_size: 9675397019 dataset_size: 9646581786 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8736765067 num_examples: 1779 download_size: 8761578004 dataset_size: 8736765067 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10410535331 num_examples: 1908 download_size: 10439335513 dataset_size: 10410535331 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10188356145 num_examples: 1877 download_size: 10218696271 dataset_size: 10188356145 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10485541758 num_examples: 1924 download_size: 10513113708 dataset_size: 10485541758 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10386567011 num_examples: 1930 download_size: 10417054414 dataset_size: 10386567011 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10591092324 num_examples: 1940 download_size: 10619534397 dataset_size: 10591092324 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10341488955 num_examples: 1902 download_size: 10371862024 dataset_size: 10341488955 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10529719750 num_examples: 1910 download_size: 10558882034 dataset_size: 10529719750 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10297417332 num_examples: 1901 download_size: 10327810400 dataset_size: 10297417332 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10533890733 num_examples: 1911 download_size: 10565451687 dataset_size: 10533890733 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10245323889 num_examples: 1867 download_size: 10275576648 dataset_size: 10245323889 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9731662335 num_examples: 1916 download_size: 9759429233 dataset_size: 9731662335 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9712138541 num_examples: 1774 download_size: 9737568085 dataset_size: 9712138541 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10474507472 num_examples: 1895 download_size: 10504742139 dataset_size: 10474507472 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10118201359 num_examples: 1851 download_size: 10145835390 dataset_size: 10118201359 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10668996219 num_examples: 1923 download_size: 10699951985 dataset_size: 10668996219 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10403769859 num_examples: 1886 download_size: 10429558449 dataset_size: 10403769859 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10522465607 num_examples: 1928 download_size: 10554133951 dataset_size: 10522465607 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10240079911 num_examples: 1903 download_size: 10269077911 dataset_size: 10240079911 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10500522515 num_examples: 1902 download_size: 10532042696 dataset_size: 10500522515 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10252894005 num_examples: 1890 download_size: 10281784120 dataset_size: 10252894005 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9663474139 num_examples: 1752 download_size: 9690866335 dataset_size: 9663474139 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8794624469 num_examples: 1769 download_size: 8820465273 dataset_size: 8794624469 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10080425471 num_examples: 1830 download_size: 10110566138 dataset_size: 10080425471 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10401094794 num_examples: 1882 download_size: 10429416473 dataset_size: 10401094794 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10457446364 num_examples: 1918 download_size: 10485865817 dataset_size: 10457446364 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10171821729 num_examples: 1886 download_size: 10202198422 dataset_size: 10171821729 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10462308565 num_examples: 1912 download_size: 10492670895 dataset_size: 10462308565 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10390714049 num_examples: 1888 download_size: 10420979533 dataset_size: 10390714049 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10277513585 num_examples: 1875 download_size: 10307787783 dataset_size: 10277513585 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10243012984 num_examples: 1866 download_size: 10273259941 dataset_size: 10243012984 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10196538053 num_examples: 1863 download_size: 10226765925 dataset_size: 10196538053 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10173792264 num_examples: 1859 download_size: 10204033126 dataset_size: 10173792264 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8664933141 num_examples: 1734 download_size: 8691667368 dataset_size: 8664933141 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9810713416 num_examples: 1766 download_size: 9838770886 dataset_size: 9810713416 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10401318825 num_examples: 1865 download_size: 10431447945 dataset_size: 10401318825 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10331604042 num_examples: 1893 download_size: 10361931781 dataset_size: 10331604042 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10355333367 num_examples: 1894 download_size: 10385663684 dataset_size: 10355333367 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7742492099 num_examples: 1381 download_size: 7765334663 dataset_size: 7742492099 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9579730430 num_examples: 1914 download_size: 9608255090 dataset_size: 9579730430 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9104014026 num_examples: 1862 download_size: 9132206904 dataset_size: 9104014026 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9482806827 num_examples: 1875 download_size: 9511062893 dataset_size: 9482806827 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9841358654 num_examples: 1937 download_size: 9870990138 dataset_size: 9841358654 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9511847926 num_examples: 1917 download_size: 9541482048 dataset_size: 9511847926 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9905653849 num_examples: 1929 download_size: 9935188764 dataset_size: 9905653849 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9407924858 num_examples: 1877 download_size: 9436227201 dataset_size: 9407924858 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9098451395 num_examples: 1761 download_size: 9126314203 dataset_size: 9098451395 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9250656777 num_examples: 1850 download_size: 9277818541 dataset_size: 9250656777 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9057374661 num_examples: 1790 download_size: 9085397757 dataset_size: 9057374661 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8914837743 num_examples: 1758 download_size: 8941549659 dataset_size: 8914837743 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9914198268 num_examples: 1898 download_size: 9941362425 dataset_size: 9914198268 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9711988405 num_examples: 1943 download_size: 9741716068 dataset_size: 9711988405 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9604785951 num_examples: 1903 download_size: 9634373630 dataset_size: 9604785951 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9737938983 num_examples: 1912 download_size: 9767484883 dataset_size: 9737938983 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9784631511 num_examples: 1945 download_size: 9811517276 dataset_size: 9784631511 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9540786756 num_examples: 1899 download_size: 9570365681 dataset_size: 9540786756 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9809407640 num_examples: 1902 download_size: 9838834622 dataset_size: 9809407640 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9352779642 num_examples: 1805 download_size: 9380734578 dataset_size: 9352779642 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9299494462 num_examples: 1797 download_size: 9326535503 dataset_size: 9299494462 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9079133566 num_examples: 1757 download_size: 9106984613 dataset_size: 9079133566 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9712189291 num_examples: 1893 download_size: 9739807425 dataset_size: 9712189291 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9839600386 num_examples: 1928 download_size: 9869138790 dataset_size: 9839600386 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9606360855 num_examples: 1863 download_size: 9635729919 dataset_size: 9606360855 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9642330669 num_examples: 1855 download_size: 9670222801 dataset_size: 9642330669 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9834140258 num_examples: 1890 download_size: 9863506751 dataset_size: 9834140258 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9725112494 num_examples: 1899 download_size: 9754592391 dataset_size: 9725112494 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8976885342 num_examples: 1835 download_size: 9002538999 dataset_size: 8976885342 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10000473788 num_examples: 1931 download_size: 10029772079 dataset_size: 10000473788 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9334915645 num_examples: 1784 download_size: 9362744529 dataset_size: 9334915645 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9333912380 num_examples: 1797 download_size: 9361822687 dataset_size: 9333912380 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9166016124 num_examples: 1757 download_size: 9189912083 dataset_size: 9166016124 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9649379352 num_examples: 1831 download_size: 9678549281 dataset_size: 9649379352 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9696258598 num_examples: 1891 download_size: 9725722759 dataset_size: 9696258598 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9959981112 num_examples: 1897 download_size: 9989307992 dataset_size: 9959981112 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10007747026 num_examples: 1897 download_size: 10038312177 dataset_size: 10007747026 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10007788444 num_examples: 1902 download_size: 10038354205 dataset_size: 10007788444 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9917511575 num_examples: 1875 download_size: 9941157796 dataset_size: 9917511575 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9820733471 num_examples: 1987 download_size: 9850269724 dataset_size: 9820733471 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10134544844 num_examples: 1951 download_size: 10165322891 dataset_size: 10134544844 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9386655137 num_examples: 1752 download_size: 9414301949 dataset_size: 9386655137 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9446951589 num_examples: 1780 download_size: 9474700273 dataset_size: 9446951589 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9777957117 num_examples: 1846 download_size: 9807128019 dataset_size: 9777957117 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9102655130 num_examples: 1723 download_size: 9129263935 dataset_size: 9102655130 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9780858901 num_examples: 1866 download_size: 9810124485 dataset_size: 9780858901 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10086702415 num_examples: 1893 download_size: 10117190006 dataset_size: 10086702415 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10109788587 num_examples: 1924 download_size: 10137705027 dataset_size: 10109788587 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9853462061 num_examples: 1881 download_size: 9882384601 dataset_size: 9853462061 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9883115206 num_examples: 1887 download_size: 9912433454 dataset_size: 9883115206 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9008892954 num_examples: 1810 download_size: 9037072334 dataset_size: 9008892954 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10053484869 num_examples: 1909 download_size: 10084064374 dataset_size: 10053484869 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9219503176 num_examples: 1728 download_size: 9246364553 dataset_size: 9219503176 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9375723434 num_examples: 1787 download_size: 9401019242 dataset_size: 9375723434 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9567750688 num_examples: 1790 download_size: 9596745445 dataset_size: 9567750688 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9639191254 num_examples: 1812 download_size: 9668262467 dataset_size: 9639191254 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10010824960 num_examples: 1877 download_size: 10041256612 dataset_size: 10010824960 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10044736643 num_examples: 1890 download_size: 10075237919 dataset_size: 10044736643 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9996933459 num_examples: 1873 download_size: 10026116707 dataset_size: 9996933459 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10095822332 num_examples: 1883 download_size: 10126245840 dataset_size: 10095822332 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10268303934 num_examples: 1916 download_size: 10298810059 dataset_size: 10268303934 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9097360602 num_examples: 1832 download_size: 9122322351 dataset_size: 9097360602 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10120152697 num_examples: 1903 download_size: 10150083596 dataset_size: 10120152697 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9284035527 num_examples: 1736 download_size: 9311653969 dataset_size: 9284035527 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10250178033 num_examples: 1887 download_size: 10280517538 dataset_size: 10250178033 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9222731957 num_examples: 1736 download_size: 9249882756 dataset_size: 9222731957 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9818296986 num_examples: 1829 download_size: 9847340045 dataset_size: 9818296986 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10009491493 num_examples: 1862 download_size: 10039851706 dataset_size: 10009491493 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10168022034 num_examples: 1914 download_size: 10196509154 dataset_size: 10168022034 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10076591228 num_examples: 1874 download_size: 10106985644 dataset_size: 10076591228 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10027538901 num_examples: 1871 download_size: 10057947606 dataset_size: 10027538901 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10094618912 num_examples: 1891 download_size: 10125094585 dataset_size: 10094618912 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9933535024 num_examples: 2009 download_size: 9963487174 dataset_size: 9933535024 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9926663871 num_examples: 1885 download_size: 9955941714 dataset_size: 9926663871 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10328392928 num_examples: 1913 download_size: 10358834523 dataset_size: 10328392928 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10325523231 num_examples: 1910 download_size: 10355953098 dataset_size: 10325523231 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10139356186 num_examples: 1887 download_size: 10169781380 dataset_size: 10139356186 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10033769422 num_examples: 1867 download_size: 10064131883 dataset_size: 10033769422 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10014868133 num_examples: 1881 download_size: 10045337903 dataset_size: 10014868133 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10002691939 num_examples: 1862 download_size: 10029974377 dataset_size: 10002691939 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10137271516 num_examples: 1897 download_size: 10166450449 dataset_size: 10137271516 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10210468115 num_examples: 1900 download_size: 10240900582 dataset_size: 10210468115 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10209211677 num_examples: 1886 download_size: 10239579862 dataset_size: 10209211677 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9715767539 num_examples: 1977 download_size: 9745666870 dataset_size: 9715767539 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10196598544 num_examples: 1913 download_size: 10227130013 dataset_size: 10196598544 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10267980939 num_examples: 1913 download_size: 10298448201 dataset_size: 10267980939 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10023876490 num_examples: 1886 download_size: 10054355442 dataset_size: 10023876490 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10193300693 num_examples: 1875 download_size: 10223629532 dataset_size: 10193300693 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10231732730 num_examples: 1900 download_size: 10262173245 dataset_size: 10231732730 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10013150375 num_examples: 1867 download_size: 10043533360 dataset_size: 10013150375 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10309586781 num_examples: 1900 download_size: 10339981006 dataset_size: 10309586781 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10319142937 num_examples: 1899 download_size: 10349514733 dataset_size: 10319142937 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10316858013 num_examples: 1904 download_size: 10347258013 dataset_size: 10316858013 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10377469541 num_examples: 1901 download_size: 10407826150 dataset_size: 10377469541 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

xiegeo/uspto-mol

xiegeo

--- configs: - config_name: default data_files: - split: all path: "data/**/*" --- # An intermediate dataset for US molecular patent grants Retrieves patent grant data from USPTO weekly releases `bulkdata.uspto.gov/data/patent/grant/redbook/{year}` and keeps only patents with `.mol` files for downstream data mining use cases. Compared to existing work such as [https://github.com/learningmatter-mit/PatentChem/tree/main]. We keep all files of a patent grant, especially `.til` image files. We also share the data as a git lfs repo instead of a single `.zip` file to allow easier access. ## The data directory ``` bash data/{year}/{weekly}/{sub_dir}/{filename}.ZIP ``` Each file is a full patent grant with original redbook directory structure preserved. `weekly` is the weekly release date. Expect inconsistencies for the formate of `weekly` and depth in `sub_dir` over time. See [https://www.uspto.gov/learning-and-resources/xml-resources] for DTD and Red Book Viewer. ## Data quality Ideally, USPTO provides the ground truth on chemical structure annotations for the molecular drawings. But the raw data quality appears poor. Some outlandish annotations such as chemical structure annotations on non-chemistry related images suggest an automated annotation process with little human QA is used to annotate the drawings. A report on improving data quality is left as a future work. (seeking calibrators) ## Related resources - (2023) Automated patent extraction powers generative modeling in focused chemical spaces [https://github.com/learningmatter-mit/PatentChem] - (2014) Processing USPTO Patent Data [https://github.com/funginstitute/patentprocessor/] [https://funginstitute.berkeley.edu/wp-content/uploads/2014/06/patentprocessor.pdf]: How to extract information from the `.xml` file - (2011) SCRIPDB: a portal for easy access to syntheses, chemicals and reactions in patents [https://pmc.ncbi.nlm.nih.gov/articles/PMC3245107/]: extensive data analytics, but database and website no longer exist. ## The DATA-CHANGELOG.md file This file is written by `update_data.py` to log statistics from each processed weekly. ## How to update the dataset `python update_data.py --from_year 2024` will search for new weeklies from 2024 to current year, add them to the data directory and push to upstream. Please only use this project's root directory as the working directory. You can also copy pre-downloaded weeklies here to avoid re-downloading them. ``` bash $ python update_data.py -h usage: update_data.py [-h] [--quick] [--keep] [--stream] [--verbose] [--from_year FROM_YEAR] [--to_year TO_YEAR] Downloads and filters patent files for mol files from USPTO website, then adds them to a dataset options: -h, --help show this help message and exit --quick only processed at most one new weekly file, you can also create a file named 'quick' (touch quick) to enable this flag during runtime to exit after finishing processing the current weekly file --keep keep the original downloaded files --stream remove all pushed lfs files and objects locally. DO NOT USE WHEN RUNNING PARALLEL SCRIPTS --verbose print verbose logs --from_year FROM_YEAR start from this year (default 2001 is the earliest available) --to_year TO_YEAR end at this year (default current year) ```

andstor/the_pile_github

andstor

--- annotations_creators: - no-annotation language: - en language_creators: - found license: - other multilinguality: - monolingual pretty_name: The Pile GitHub size_categories: [] source_datasets: - original tags: [] task_categories: - text-generation - fill-mask - text-classification task_ids: [] --- # Dataset Card for The Pile GitHub ## Table of Contents - [Dataset Card for Smart Contracts](#dataset-card-for-the-pile-github) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Additional Information](#additional-information) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [ElutherAI](https://pile.eleuther.ai) - **Repository:** [GitHub](https://github.com/andstor/the-pile-github) - **Paper:** [arXiv](https://arxiv.org/abs/2101.00027) - **Leaderboard:** [Needs More Information] - **Point of Contact:** [Needs More Information] ### Dataset Summary This is the GitHub subset of EleutherAi/The Pile dataset and contains GitHub repositories. The programming languages are identified using the [guesslang library](https://github.com/yoeo/guesslang). A total of 54 programming languages are included in the dataset. ### Supported Tasks and Leaderboards [More Information Needed] ### Languages The following languages are covered by the dataset: ``` 'Assembly', 'Batchfile', 'C', 'C#', 'C++', 'CMake', 'COBOL', 'CSS', 'CSV', 'Clojure', 'CoffeeScript', 'DM', 'Dart', 'Dockerfile', 'Elixir', 'Erlang', 'Fortran', 'Go', 'Groovy', 'HTML', 'Haskell', 'INI', 'JSON', 'Java', 'JavaScript', 'Julia', 'Kotlin', 'Lisp', 'Lua', 'Makefile', 'Markdown', 'Matlab', 'None', 'OCaml', 'Objective-C', 'PHP', 'Pascal', 'Perl', 'PowerShell', 'Prolog', 'Python', 'R', 'Ruby', 'Rust', 'SQL', 'Scala', 'Shell', 'Swift', 'TOML', 'TeX', 'TypeScript', 'Verilog', 'Visual Basic', 'XML', 'YAML' ``` The [guesslang library](https://github.com/yoeo/guesslang) is used to identify the programming languages. It has a guessing accuracy of above 90%. Hence, there will be some misclassifications in the language identification. ## Dataset Structure ### Data Instances [More Information Needed] ``` { 'text': ..., 'meta': {'language': ...} } ``` ### Data Fields - `text` (`string`): the source code. - `meta` (`dict`): the metadata of the source code. - `language` (`string`): the programming language of the source code. ### Data Splits [More Information Needed] | | train | validation | test | |-------------------------|------:|-----------:|-----:| | Input Sentences | | | | | Average Sentence Length | | | | ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data The data is purely a subset of the [EleutherAI/The Pile dataset](https://huggingface.co/datasets/the_pile). See the original [dataset](https://arxiv.org/abs/2201.07311) for more details. ## Additional Information ### Licensing Information The Pile dataset was released on January 1st, 2021. It is licensed under the MIT License. See the [dataset](https://arxiv.org/abs/2201.07311) for more details. ### Citation Information Provide the [BibTex](http://www.bibtex.org/)-formatted reference for the dataset. For example: ``` @article{pile, title={The {P}ile: An 800GB Dataset of Diverse Text for Language Modeling}, author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and Presser, Shawn and Leahy, Connor}, journal={arXiv preprint arXiv:2101.00027}, year={2020} } ``` ### Contributions Thanks to [@andstor](https://github.com/andstor) for adding this dataset.

yahma/alpaca-cleaned

yahma

--- license: cc-by-4.0 language: - en tags: - instruction-finetuning pretty_name: Alpaca-Cleaned task_categories: - text-generation --- # Dataset Card for Alpaca-Cleaned - **Repository:** https://github.com/gururise/AlpacaDataCleaned ## Dataset Description This is a cleaned version of the original Alpaca Dataset released by Stanford. The following issues have been identified in the original release and fixed in this dataset: 1. **Hallucinations:** Many instructions in the original dataset had instructions referencing data on the internet, which just caused GPT3 to hallucinate an answer. ``` "instruction":"Summarize the given article in 200 Words.", "input": "https://www.bbc.com/news/world-51461830", "output": "The recent protests in Belarus are part of a growing wave of discontent against the rule of Alexander Lukashenko, who has led the country since 1994. Demonstrations against his government have been ongoing since August, and come in the wake of an election widely seen as rigged. As police and security forces have cracked down on protesters, the movement has only grown, with hundreds of thousands of people taking to the streets to call for new leadership. Human rights activists have accused the government of using extreme violence in order prosecute protesters, leading to an international outcry and sanctions from the European Union. As the situation in Belarus continues to unfold, the international community is monitoring the situation closely - hoping for a peaceful resolution, while also standing firm against the oppressive tactics employed by the Belarusian state." "instruction": "Classify the following shape according to simple geometry.", "input": "<Picture Attached>", "output": "Triangle" "instruction": "Given a recent news article, write a headline for it.", "input": "https://www.news.example.com/article-1", "output": "\"NASA Launches a Mars 2020 Mission to Search for Signs of Ancient Life\"" ``` 2. **Merged Instructions:** There were many instructions that were merged together in the original dataset for some reason. ``` "instruction": "Should I invest in stocks?", "input": "", "output": "It depends on your individual situation. Investing in stocks carries a certain amount of risk but can also offer potential rewards. Make sure to research the different types of stocks, understand the risks and rewards, and develop a plan that works for you.\n##\n18. Instruction: Identify the noun in the following sentence:\n18. Input:\nThe large apple was delicious.\n18. Output:\nApple" ``` 3. **Empty outputs:** Some entries in the original dataset had empty outputs. ``` "instruction": "Calculate the area of the following shape in square centimeters.", "input": "rectangle of size 4 cm x 5 cm", "output": "" ``` 4. **Empty code examples:** Some descriptions in the original dataset were missing code examples, making it difficult to understand the intended behavior of the code. 5. **Instructions to generate images:** Some descriptions in the original dataset included instructions to generate images, something obviously not possible. ``` "instruction": "Create a graphic or logo that visually represents the word \"courage\".", "input": "", "output": "<No Output>" ``` 6. **N/A outputs:** Some code snippets in the original dataset had N/A outputs. 7. **Inconsistent input field:** The original dataset had inconsistent usage of the input field when it was supposed to be empty. ``` "input":"<no input>" "input":"No input" "input":"noinput" "input":"<noinput>" ``` 8. **Wrong answers:** Some instructions/questions in the original dataset had incorrect answers. About 80% of the math problems are estimated to have incorrect answers. ``` "instruction": "Calculate the median of the following data set.", "input": "1, 2, 4, 5, 8, 9", "output": "5" "instruction": "Convert 25m to km.", "input": "", "output": "25km" ``` 9. **Non-Sensical/Unclear instructions:** Many instructions are unclear, we try to clarify (or re-write) if instructions are non-sensical. Instructions that are slightly unclear, but where one could deduce the meaning are not altered. ``` "instruction": "Freeze the following sample of yogurt for 10 minutes.", "input": "Yogurt sample", "output": "<noinput>" "instruction": "Increase the font size to 12 points.", "input": "", "output": "The font size has been increased to 12 points." ``` 10. **Extraneous escape and control characters:** The original dataset had several entries with extraneous escape and control characters. ### Original Alpaca Dataset Summary Alpaca is a dataset of 52,000 instructions and demonstrations generated by OpenAI's `text-davinci-003` engine. This instruction data can be used to conduct instruction-tuning for language models and make the language model follow instruction better. The authors built on the data generation pipeline from [Self-Instruct framework](https://github.com/yizhongw/self-instruct) and made the following modifications: - The `text-davinci-003` engine to generate the instruction data instead of `davinci`. - A [new prompt](https://github.com/tatsu-lab/stanford_alpaca/blob/main/prompt.txt) was written that explicitly gave the requirement of instruction generation to `text-davinci-003`. - Much more aggressive batch decoding was used, i.e., generating 20 instructions at once, which significantly reduced the cost of data generation. - The data generation pipeline was simplified by discarding the difference between classification and non-classification instructions. - Only a single instance was generated for each instruction, instead of 2 to 3 instances as in Self-Instruct. This produced an instruction-following dataset with 52K examples obtained at a much lower cost (less than $500). In a preliminary study, the authors also found that the 52K generated data to be much more diverse than the data released by [Self-Instruct](https://github.com/yizhongw/self-instruct/blob/main/data/seed_tasks.jsonl). ### Supported Tasks and Leaderboards The Alpaca dataset designed for instruction training pretrained language models. ### Languages The data in Alpaca are in English (BCP-47 en). ## Dataset Structure ### Data Instances An example of "train" looks as follows: ```json { "instruction": "Create a classification task by clustering the given list of items.", "input": "Apples, oranges, bananas, strawberries, pineapples", "output": "Class 1: Apples, Oranges\nClass 2: Bananas, Strawberries\nClass 3: Pineapples", "text": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nCreate a classification task by clustering the given list of items.\n\n### Input:\nApples, oranges, bananas, strawberries, pineapples\n\n### Response:\nClass 1: Apples, Oranges\nClass 2: Bananas, Strawberries\nClass 3: Pineapples", } ``` ### Data Fields The data fields are as follows: * `instruction`: describes the task the model should perform. Each of the 52K instructions is unique. * `input`: optional context or input for the task. For example, when the instruction is "Summarize the following article", the input is the article. Around 40% of the examples have an input. * `output`: the answer to the instruction as generated by `text-davinci-003`. * `text`: the `instruction`, `input` and `output` formatted with the [prompt template](https://github.com/tatsu-lab/stanford_alpaca#data-release) used by the authors for fine-tuning their models. ### Data Splits | | train | |---------------|------:| | alpaca | 52002 | ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset Excerpt the [blog post](https://crfm.stanford.edu/2023/03/13/alpaca.html) accompanying the release of this dataset: > We believe that releasing the above assets will enable the academic community to perform controlled scientific studies on instruction-following language models, resulting in better science and ultimately new techniques to address the existing deficiencies with these models. At the same time, any release carries some risk. First, we recognize that releasing our training recipe reveals the feasibility of certain capabilities. On one hand, this enables more people (including bad actors) to create models that could cause harm (either intentionally or not). On the other hand, this awareness might incentivize swift defensive action, especially from the academic community, now empowered by the means to perform deeper safety research on such models. Overall, we believe that the benefits for the research community outweigh the risks of this particular release. Given that we are releasing the training recipe, we believe that releasing the data, model weights, and training code incur minimal further risk, given the simplicity of the recipe. At the same time, releasing these assets has enormous benefits for reproducible science, so that the academic community can use standard datasets, models, and code to perform controlled comparisons and to explore extensions. Deploying an interactive demo for Alpaca also poses potential risks, such as more widely disseminating harmful content and lowering the barrier for spam, fraud, or disinformation. We have put into place two risk mitigation strategies. First, we have implemented a content filter using OpenAI’s content moderation API, which filters out harmful content as defined by OpenAI’s usage policies. Second, we watermark all the model outputs using the method described in Kirchenbauer et al. 2023, so that others can detect (with some probability) whether an output comes from Alpaca 7B. Finally, we have strict terms and conditions for using the demo; it is restricted to non-commercial uses and to uses that follow LLaMA’s license agreement. We understand that these mitigation measures can be circumvented once we release the model weights or if users train their own instruction-following models. However, by installing these mitigations, we hope to advance the best practices and ultimately develop community norms for the responsible deployment of foundation models. ### Discussion of Biases [More Information Needed] ### Other Known Limitations The `alpaca` data is generated by a language model (`text-davinci-003`) and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections. ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode). ### Citation Information ``` @misc{alpaca, author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto }, title = {Stanford Alpaca: An Instruction-following LLaMA model}, year = {2023}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}}, } ``` ### Contributions [More Information Needed]

sentence-transformers/parallel-sentences-ccmatrix

sentence-transformers

--- size_categories: - 1B<n<10B task_categories: - feature-extraction - sentence-similarity pretty_name: CCMatrix tags: - sentence-transformers dataset_info: - config_name: en-af features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1148266566 num_examples: 8694461 download_size: 832696872 dataset_size: 1148266566 - config_name: en-ar features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 14226823350 num_examples: 49697322 download_size: 8765479032 dataset_size: 14226823350 - config_name: en-ast features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 637434232 num_examples: 2956618 download_size: 453215367 dataset_size: 637434232 - config_name: en-az features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 177938263 num_examples: 1251254 download_size: 124360060 dataset_size: 177938263 - config_name: en-be features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 542841152 num_examples: 1885446 download_size: 142253337 dataset_size: 542841152 - config_name: en-bg features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 11961705756 num_examples: 44635282 download_size: 7160113672 dataset_size: 11961705756 - config_name: en-bn features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 2053120318 num_examples: 10074620 download_size: 1098221602 dataset_size: 2053120318 - config_name: en-br features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 86947450 num_examples: 454175 download_size: 34384705 dataset_size: 86947450 - config_name: en-ca features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 3837708529 num_examples: 21284430 download_size: 2751851357 dataset_size: 3837708529 - config_name: en-ceb features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 234354977 num_examples: 962549 download_size: 49981947 dataset_size: 234354977 - config_name: en-cs features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 10277621210 num_examples: 56307029 download_size: 7607844854 dataset_size: 10277621210 - config_name: en-da features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 9093768397 num_examples: 52273664 download_size: 6510153593 dataset_size: 9093768397 - config_name: en-de features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 51555584594 num_examples: 247470736 download_size: 36674461807 dataset_size: 51555584594 - config_name: en-el features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 14907671089 num_examples: 49262631 download_size: 8919934254 dataset_size: 14907671089 - config_name: en-eo features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 2967819260 num_examples: 15418393 download_size: 2168808728 dataset_size: 2967819260 - config_name: en-es features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 100839563812 num_examples: 409061333 download_size: 69967087456 dataset_size: 100839563812 - config_name: en-et features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 3615519238 num_examples: 22007049 download_size: 2628823101 dataset_size: 3615519238 - config_name: en-eu features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 821387539 num_examples: 7778871 download_size: 606760358 dataset_size: 821387539 - config_name: en-fa features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 5720870387 num_examples: 24597533 download_size: 3493927697 dataset_size: 5720870387 - config_name: en-fi features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 6003531112 num_examples: 35982562 download_size: 4339586568 dataset_size: 6003531112 - config_name: en-fr features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 76362272973 num_examples: 328595738 download_size: 52468991292 dataset_size: 76362272973 - config_name: en-fy features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 192234316 num_examples: 1372321 download_size: 93352000 dataset_size: 192234316 - config_name: en-ga features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 225464892 num_examples: 1076420 download_size: 45935095 dataset_size: 225464892 - config_name: en-gd features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 114460109 num_examples: 310351 download_size: 24846114 dataset_size: 114460109 - config_name: en-gl features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1746914916 num_examples: 13178507 download_size: 1294690325 dataset_size: 1746914916 - config_name: en-ha features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1381532117 num_examples: 5861080 download_size: 314288607 dataset_size: 1381532117 - config_name: en-he features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4410235248 num_examples: 25228938 download_size: 2861838829 dataset_size: 4410235248 - config_name: en-hi features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4083378822 num_examples: 15127900 download_size: 2132432520 dataset_size: 4083378822 - config_name: en-hr features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 3218511310 num_examples: 18797643 download_size: 2368836034 dataset_size: 3218511310 - config_name: en-hu features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 6820144152 num_examples: 36435409 download_size: 4937653466 dataset_size: 6820144152 - config_name: en-id features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 15124269935 num_examples: 70545705 download_size: 10343250018 dataset_size: 15124269935 - config_name: en-ig features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 9470472 num_examples: 80385 download_size: 4927497 dataset_size: 9470472 - config_name: en-ilo features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 97134614 num_examples: 335469 download_size: 25965608 dataset_size: 97134614 - config_name: en-is features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1006043191 num_examples: 8723145 download_size: 726436377 dataset_size: 1006043191 - config_name: en-it features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 34781986566 num_examples: 146240552 download_size: 24249713724 dataset_size: 34781986566 - config_name: en-ja features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 6088805781 num_examples: 40883733 download_size: 4379531648 dataset_size: 6088805781 - config_name: en-jv features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 281788171 num_examples: 819280 download_size: 43299173 dataset_size: 281788171 - config_name: en-ko features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 2895213164 num_examples: 19358582 download_size: 2111224807 dataset_size: 2895213164 - config_name: en-la features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 93121864 num_examples: 1114190 download_size: 72143426 dataset_size: 93121864 - config_name: en-lb features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4552854478 num_examples: 11978495 download_size: 762899421 dataset_size: 4552854478 - config_name: en-lt features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4141127566 num_examples: 23298470 download_size: 3004038735 dataset_size: 4141127566 - config_name: en-lv features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 3297623891 num_examples: 16685969 download_size: 2397129326 dataset_size: 3297623891 - config_name: en-mg features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 272623294 num_examples: 1736359 download_size: 177355627 dataset_size: 272623294 - config_name: en-mk features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 2780199285 num_examples: 12040173 download_size: 1672182611 dataset_size: 2780199285 - config_name: en-ml features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1372569050 num_examples: 6809956 download_size: 704237919 dataset_size: 1372569050 - config_name: en-mr features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 464346053 num_examples: 2874211 download_size: 248129592 dataset_size: 464346053 - config_name: en-ms features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1599412862 num_examples: 10730648 download_size: 1124736238 dataset_size: 1599412862 - config_name: en-ne features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 124241733 num_examples: 708316 download_size: 65140507 dataset_size: 124241733 - config_name: en-nl features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 20167977866 num_examples: 106695917 download_size: 14404091096 dataset_size: 20167977866 - config_name: en-no features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 7658217005 num_examples: 47801406 download_size: 5558513486 dataset_size: 7658217005 - config_name: en-oc features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 142791359 num_examples: 1730828 download_size: 109912116 dataset_size: 142791359 - config_name: en-or features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 17904200 num_examples: 96595 download_size: 8406901 dataset_size: 17904200 - config_name: en-pl features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 14630774653 num_examples: 74070714 download_size: 10663782153 dataset_size: 14630774653 - config_name: en-pt features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 41115105368 num_examples: 173743166 download_size: 28862370774 dataset_size: 41115105368 - config_name: en-ro features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 12075310975 num_examples: 55607023 download_size: 8615952576 dataset_size: 12075310975 - config_name: en-ru features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 42356783826 num_examples: 139937785 download_size: 25636989987 dataset_size: 42356783826 - config_name: en-sd features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 335072671 num_examples: 1717573 download_size: 197842483 dataset_size: 335072671 - config_name: en-si features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 960598149 num_examples: 6270800 download_size: 548699294 dataset_size: 960598149 - config_name: en-sk features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 6584874005 num_examples: 38096241 download_size: 4879550406 dataset_size: 6584874005 - config_name: en-sl features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4487888666 num_examples: 27406782 download_size: 3305678350 dataset_size: 4487888666 - config_name: en-so features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 49524014 num_examples: 222793 download_size: 30280185 dataset_size: 49524014 - config_name: en-sq features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 3723203721 num_examples: 22358158 download_size: 2627564869 dataset_size: 3723203721 - config_name: en-sr features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 4455973990 num_examples: 26510872 download_size: 3135382266 dataset_size: 4455973990 - config_name: en-su features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 31745713 num_examples: 271736 download_size: 18535781 dataset_size: 31745713 - config_name: en-sv features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 12787309195 num_examples: 77008059 download_size: 9187888944 dataset_size: 12787309195 - config_name: en-sw features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 874785438 num_examples: 5756664 download_size: 617058117 dataset_size: 874785438 - config_name: en-ta features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1604830149 num_examples: 7291118 download_size: 790660374 dataset_size: 1604830149 - config_name: en-tl features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 385586424 num_examples: 3113828 download_size: 282939008 dataset_size: 385586424 - config_name: en-tr features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 7629424945 num_examples: 47045956 download_size: 5549531679 dataset_size: 7629424945 - config_name: en-uk features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 5045729411 num_examples: 20240171 download_size: 3145670206 dataset_size: 5045729411 - config_name: en-ur features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 1029899312 num_examples: 6094149 download_size: 643507216 dataset_size: 1029899312 - config_name: en-vi features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 11459576669 num_examples: 50092444 download_size: 7526497393 dataset_size: 11459576669 - config_name: en-xh features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 10632555903 num_examples: 18980689 download_size: 951644540 dataset_size: 10632555903 - config_name: en-yi features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 175142487 num_examples: 275076 download_size: 24791912 dataset_size: 175142487 - config_name: en-zh features: - name: english dtype: string - name: non_english dtype: string splits: - name: train num_bytes: 13169778580 num_examples: 71383325 download_size: 9897543738 dataset_size: 13169778580 configs: - config_name: en-af data_files: - split: train path: en-af/train-* - config_name: en-ar data_files: - split: train path: en-ar/train-* - config_name: en-ast data_files: - split: train path: en-ast/train-* - config_name: en-az data_files: - split: train path: en-az/train-* - config_name: en-be data_files: - split: train path: en-be/train-* - config_name: en-bg data_files: - split: train path: en-bg/train-* - config_name: en-bn data_files: - split: train path: en-bn/train-* - config_name: en-br data_files: - split: train path: en-br/train-* - config_name: en-ca data_files: - split: train path: en-ca/train-* - config_name: en-ceb data_files: - split: train path: en-ceb/train-* - config_name: en-cs data_files: - split: train path: en-cs/train-* - config_name: en-da data_files: - split: train path: en-da/train-* - config_name: en-de data_files: - split: train path: en-de/train-* - config_name: en-el data_files: - split: train path: en-el/train-* - config_name: en-eo data_files: - split: train path: en-eo/train-* - config_name: en-es data_files: - split: train path: en-es/train-* - config_name: en-et data_files: - split: train path: en-et/train-* - config_name: en-eu data_files: - split: train path: en-eu/train-* - config_name: en-fa data_files: - split: train path: en-fa/train-* - config_name: en-fi data_files: - split: train path: en-fi/train-* - config_name: en-fr data_files: - split: train path: en-fr/train-* - config_name: en-fy data_files: - split: train path: en-fy/train-* - config_name: en-ga data_files: - split: train path: en-ga/train-* - config_name: en-gd data_files: - split: train path: en-gd/train-* - config_name: en-gl data_files: - split: train path: en-gl/train-* - config_name: en-ha data_files: - split: train path: en-ha/train-* - config_name: en-he data_files: - split: train path: en-he/train-* - config_name: en-hi data_files: - split: train path: en-hi/train-* - config_name: en-hr data_files: - split: train path: en-hr/train-* - config_name: en-hu data_files: - split: train path: en-hu/train-* - config_name: en-id data_files: - split: train path: en-id/train-* - config_name: en-ig data_files: - split: train path: en-ig/train-* - config_name: en-ilo data_files: - split: train path: en-ilo/train-* - config_name: en-is data_files: - split: train path: en-is/train-* - config_name: en-it data_files: - split: train path: en-it/train-* - config_name: en-ja data_files: - split: train path: en-ja/train-* - config_name: en-jv data_files: - split: train path: en-jv/train-* - config_name: en-ko data_files: - split: train path: en-ko/train-* - config_name: en-la data_files: - split: train path: en-la/train-* - config_name: en-lb data_files: - split: train path: en-lb/train-* - config_name: en-lt data_files: - split: train path: en-lt/train-* - config_name: en-lv data_files: - split: train path: en-lv/train-* - config_name: en-mg data_files: - split: train path: en-mg/train-* - config_name: en-mk data_files: - split: train path: en-mk/train-* - config_name: en-ml data_files: - split: train path: en-ml/train-* - config_name: en-mr data_files: - split: train path: en-mr/train-* - config_name: en-ms data_files: - split: train path: en-ms/train-* - config_name: en-ne data_files: - split: train path: en-ne/train-* - config_name: en-nl data_files: - split: train path: en-nl/train-* - config_name: en-no data_files: - split: train path: en-no/train-* - config_name: en-oc data_files: - split: train path: en-oc/train-* - config_name: en-or data_files: - split: train path: en-or/train-* - config_name: en-pl data_files: - split: train path: en-pl/train-* - config_name: en-pt data_files: - split: train path: en-pt/train-* - config_name: en-ro data_files: - split: train path: en-ro/train-* - config_name: en-ru data_files: - split: train path: en-ru/train-* - config_name: en-sd data_files: - split: train path: en-sd/train-* - config_name: en-si data_files: - split: train path: en-si/train-* - config_name: en-sk data_files: - split: train path: en-sk/train-* - config_name: en-sl data_files: - split: train path: en-sl/train-* - config_name: en-so data_files: - split: train path: en-so/train-* - config_name: en-sq data_files: - split: train path: en-sq/train-* - config_name: en-sr data_files: - split: train path: en-sr/train-* - config_name: en-su data_files: - split: train path: en-su/train-* - config_name: en-sv data_files: - split: train path: en-sv/train-* - config_name: en-sw data_files: - split: train path: en-sw/train-* - config_name: en-ta data_files: - split: train path: en-ta/train-* - config_name: en-tl data_files: - split: train path: en-tl/train-* - config_name: en-tr data_files: - split: train path: en-tr/train-* - config_name: en-uk data_files: - split: train path: en-uk/train-* - config_name: en-ur data_files: - split: train path: en-ur/train-* - config_name: en-vi data_files: - split: train path: en-vi/train-* - config_name: en-xh data_files: - split: train path: en-xh/train-* - config_name: en-yi data_files: - split: train path: en-yi/train-* - config_name: en-zh data_files: - split: train path: en-zh/train-* language: - af - ar - ast - az - be - bg - bn - br - ca - ceb - cs - da - de - el - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - ha - he - hi - hr - hu - id - ig - ilo - is - it - ja - jv - ko - la - lb - lt - lv - mg - mk - ml - mr - ms - ne - nl - 'no' - oc - or - pl - pt - ro - ru - sd - si - sk - sl - so - sq - sr - su - sv - sw - ta - tl - tr - uk - ur - vi - xh - yi - zh --- # Dataset Card for Parallel Sentences - CCMatrix This dataset contains parallel sentences (i.e. English sentence + the same sentences in another language) for numerous other languages. The texts originate from the [CCMatrix](https://ai.meta.com/blog/ccmatrix-a-billion-scale-bitext-data-set-for-training-translation-models/) dataset. ## Related Datasets The following datasets are also a part of the Parallel Sentences collection: * [parallel-sentences-europarl](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-europarl) * [parallel-sentences-global-voices](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-global-voices) * [parallel-sentences-muse](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-muse) * [parallel-sentences-jw300](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-jw300) * [parallel-sentences-news-commentary](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-news-commentary) * [parallel-sentences-opensubtitles](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-opensubtitles) * [parallel-sentences-talks](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) * [parallel-sentences-tatoeba](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-tatoeba) * [parallel-sentences-wikimatrix](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-wikimatrix) * [parallel-sentences-wikititles](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-wikititles) * [parallel-sentences-ccmatrix](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-ccmatrix) These datasets can be used to train multilingual sentence embedding models. For more information, see [sbert.net - Multilingual Models](https://www.sbert.net/examples/training/multilingual/README.html). ## Dataset Subsets ### `en-...` subsets * Columns: "english", "non_english" * Column types: `str`, `str` * Examples: ```python { "english": "He and his mother will be standing vigil there.”", "non_english": "Él y su madre estarán de vigilia allí”.", } ``` * Collection strategy: Processing the data from [yhavinga/ccmatrix](https://huggingface.co/datasets/yhavinga/ccmatrix) and reformatting it in Parquet and with "english" and "non_english" columns. * Deduplified: No

asahi417/seamless-align-enA-viA.speaker-embedding.xlsr-2b

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13152124231 num_examples: 1853 download_size: 13196111601 dataset_size: 13152124231 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6657621784 num_examples: 1090 download_size: 6681474976 dataset_size: 6657621784 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9681441551 num_examples: 1520 download_size: 9716028942 dataset_size: 9681441551 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9765322177 num_examples: 1545 download_size: 9800069846 dataset_size: 9765322177 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9860909658 num_examples: 1527 download_size: 9895478528 dataset_size: 9860909658 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9709072687 num_examples: 1513 download_size: 9743463146 dataset_size: 9709072687 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9317976193 num_examples: 1465 download_size: 9350906284 dataset_size: 9317976193 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9599344558 num_examples: 1506 download_size: 9633714817 dataset_size: 9599344558 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9611793564 num_examples: 1517 download_size: 9646264815 dataset_size: 9611793564 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9817555828 num_examples: 1518 download_size: 9851984781 dataset_size: 9817555828 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9759896244 num_examples: 1532 download_size: 9794111609 dataset_size: 9759896244 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9920046697 num_examples: 1539 download_size: 9954649265 dataset_size: 9920046697 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7059876136 num_examples: 1146 download_size: 7085729003 dataset_size: 7059876136 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9229841208 num_examples: 1471 download_size: 9262898789 dataset_size: 9229841208 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9385133176 num_examples: 1450 download_size: 9418047633 dataset_size: 9385133176 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9493840990 num_examples: 1478 download_size: 9525582216 dataset_size: 9493840990 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9706904149 num_examples: 1493 download_size: 9741249161 dataset_size: 9706904149 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9563013098 num_examples: 1487 download_size: 9597350611 dataset_size: 9563013098 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9735858312 num_examples: 1504 download_size: 9770239160 dataset_size: 9735858312 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10002930156 num_examples: 1492 download_size: 10038446988 dataset_size: 10002930156 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9623888728 num_examples: 1524 download_size: 9658530642 dataset_size: 9623888728 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9814472575 num_examples: 1494 download_size: 9848825015 dataset_size: 9814472575 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9737465938 num_examples: 1524 download_size: 9770633676 dataset_size: 9737465938 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6654933967 num_examples: 1109 download_size: 6679320781 dataset_size: 6654933967 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9725133610 num_examples: 1530 download_size: 9759744099 dataset_size: 9725133610 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9807752743 num_examples: 1539 download_size: 9842394283 dataset_size: 9807752743 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10160148335 num_examples: 1535 download_size: 10195448487 dataset_size: 10160148335 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9612845669 num_examples: 1510 download_size: 9647308805 dataset_size: 9612845669 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9783575920 num_examples: 1503 download_size: 9817979503 dataset_size: 9783575920 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9937878067 num_examples: 1500 download_size: 9970948531 dataset_size: 9937878067 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10063911799 num_examples: 1509 download_size: 10099441054 dataset_size: 10063911799 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10105113965 num_examples: 1516 download_size: 10140782767 dataset_size: 10105113965 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9885429926 num_examples: 1535 download_size: 9920039716 dataset_size: 9885429926 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10050853493 num_examples: 1565 download_size: 10086889128 dataset_size: 10050853493 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6723416863 num_examples: 1147 download_size: 6748236994 dataset_size: 6723416863 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9902133998 num_examples: 1523 download_size: 9936635144 dataset_size: 9902133998 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10072082067 num_examples: 1536 download_size: 10107859734 dataset_size: 10072082067 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9821819874 num_examples: 1511 download_size: 9856206643 dataset_size: 9821819874 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9999675819 num_examples: 1537 download_size: 10034262905 dataset_size: 9999675819 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9721739176 num_examples: 1459 download_size: 9755772967 dataset_size: 9721739176 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9512855942 num_examples: 1442 download_size: 9546864623 dataset_size: 9512855942 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9919939128 num_examples: 1539 download_size: 9954523425 dataset_size: 9919939128 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10135847217 num_examples: 1576 download_size: 10171980144 dataset_size: 10135847217 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10244250087 num_examples: 1540 download_size: 10280034910 dataset_size: 10244250087 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10163189946 num_examples: 1520 download_size: 10198683267 dataset_size: 10163189946 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6904498909 num_examples: 1158 download_size: 6929277825 dataset_size: 6904498909 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9964789146 num_examples: 1521 download_size: 9999265403 dataset_size: 9964789146 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9863711559 num_examples: 1493 download_size: 9896918120 dataset_size: 9863711559 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10361663085 num_examples: 1558 download_size: 10397631438 dataset_size: 10361663085 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10304210073 num_examples: 1561 download_size: 10340224269 dataset_size: 10304210073 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10546727512 num_examples: 1595 download_size: 10584185986 dataset_size: 10546727512 - config_name: subset_145 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10409793660 num_examples: 1533 download_size: 10443966828 dataset_size: 10409793660 - config_name: subset_146 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10303709963 num_examples: 1553 download_size: 10339570190 dataset_size: 10303709963 - config_name: subset_147 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10567856125 num_examples: 1565 download_size: 10604972751 dataset_size: 10567856125 - config_name: subset_148 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10074810790 num_examples: 1547 download_size: 10110786944 dataset_size: 10074810790 - config_name: subset_149 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 1257786005 num_examples: 185 download_size: 1262597069 dataset_size: 1257786005 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7060472765 num_examples: 1207 download_size: 7086949634 dataset_size: 7060472765 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6958294837 num_examples: 1161 download_size: 6983180953 dataset_size: 6958294837 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7126462079 num_examples: 1197 download_size: 7151925016 dataset_size: 7126462079 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7319727811 num_examples: 1263 download_size: 7346599578 dataset_size: 7319727811 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7077454525 num_examples: 1209 download_size: 7103923783 dataset_size: 7077454525 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 10695197513 num_examples: 1497 download_size: 10730532441 dataset_size: 10695197513 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6868855968 num_examples: 1196 download_size: 6893810483 dataset_size: 6868855968 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7093800554 num_examples: 1235 download_size: 7120534137 dataset_size: 7093800554 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7078975934 num_examples: 1209 download_size: 7104886899 dataset_size: 7078975934 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7325996453 num_examples: 1245 download_size: 7352616605 dataset_size: 7325996453 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7136525609 num_examples: 1260 download_size: 7162458879 dataset_size: 7136525609 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7508441357 num_examples: 1290 download_size: 7536769302 dataset_size: 7508441357 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7661879109 num_examples: 1335 download_size: 7690578111 dataset_size: 7661879109 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7242872802 num_examples: 1267 download_size: 7269843614 dataset_size: 7242872802 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7652932813 num_examples: 1309 download_size: 7681349247 dataset_size: 7652932813 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7614481810 num_examples: 1305 download_size: 7642892649 dataset_size: 7614481810 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9239795404 num_examples: 1325 download_size: 9270733082 dataset_size: 9239795404 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7433036297 num_examples: 1266 download_size: 7459246146 dataset_size: 7433036297 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7628711906 num_examples: 1297 download_size: 7656969364 dataset_size: 7628711906 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7607420351 num_examples: 1307 download_size: 7635852315 dataset_size: 7607420351 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7560370118 num_examples: 1293 download_size: 7588502113 dataset_size: 7560370118 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8139862534 num_examples: 1337 download_size: 8169411382 dataset_size: 8139862534 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7453499255 num_examples: 1272 download_size: 7480374578 dataset_size: 7453499255 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7925438221 num_examples: 1309 download_size: 7952522193 dataset_size: 7925438221 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7739400596 num_examples: 1305 download_size: 7767421974 dataset_size: 7739400596 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7528886677 num_examples: 1268 download_size: 7556740252 dataset_size: 7528886677 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7422223042 num_examples: 1243 download_size: 7448913873 dataset_size: 7422223042 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7875711478 num_examples: 1171 download_size: 7902846811 dataset_size: 7875711478 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7672187490 num_examples: 1291 download_size: 7700422032 dataset_size: 7672187490 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7312597972 num_examples: 1180 download_size: 7338811144 dataset_size: 7312597972 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7860725780 num_examples: 1336 download_size: 7889373692 dataset_size: 7860725780 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7820892373 num_examples: 1341 download_size: 7849558877 dataset_size: 7820892373 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8088726754 num_examples: 1352 download_size: 8118596134 dataset_size: 8088726754 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7810827527 num_examples: 1356 download_size: 7838356933 dataset_size: 7810827527 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7748273881 num_examples: 1284 download_size: 7776538627 dataset_size: 7748273881 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8155822961 num_examples: 1346 download_size: 8185289321 dataset_size: 8155822961 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7719278546 num_examples: 1334 download_size: 7747990038 dataset_size: 7719278546 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8366996802 num_examples: 1373 download_size: 8396943074 dataset_size: 8366996802 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7423996532 num_examples: 1130 download_size: 7449603166 dataset_size: 7423996532 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8052394619 num_examples: 1325 download_size: 8082057526 dataset_size: 8052394619 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8208691898 num_examples: 1383 download_size: 8238827868 dataset_size: 8208691898 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8497030225 num_examples: 1431 download_size: 8527197231 dataset_size: 8497030225 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8325064686 num_examples: 1366 download_size: 8355047764 dataset_size: 8325064686 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8442464622 num_examples: 1412 download_size: 8472259549 dataset_size: 8442464622 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8472138320 num_examples: 1389 download_size: 8502289446 dataset_size: 8472138320 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8320062316 num_examples: 1365 download_size: 8349954826 dataset_size: 8320062316 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8583549410 num_examples: 1398 download_size: 8614870512 dataset_size: 8583549410 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8835066172 num_examples: 1448 download_size: 8866474621 dataset_size: 8835066172 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8258116095 num_examples: 1392 download_size: 8288332282 dataset_size: 8258116095 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 7198816764 num_examples: 1128 download_size: 7221616089 dataset_size: 7198816764 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8648402008 num_examples: 1394 download_size: 8679765409 dataset_size: 8648402008 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8593161997 num_examples: 1397 download_size: 8624047199 dataset_size: 8593161997 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8394114682 num_examples: 1385 download_size: 8424110689 dataset_size: 8394114682 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8140698615 num_examples: 1319 download_size: 8170375758 dataset_size: 8140698615 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8336623372 num_examples: 1390 download_size: 8366759385 dataset_size: 8336623372 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8626196236 num_examples: 1406 download_size: 8657732211 dataset_size: 8626196236 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8723106178 num_examples: 1398 download_size: 8753662184 dataset_size: 8723106178 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8723014783 num_examples: 1408 download_size: 8754409534 dataset_size: 8723014783 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8487354376 num_examples: 1410 download_size: 8516494928 dataset_size: 8487354376 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8594422639 num_examples: 1403 download_size: 8625850894 dataset_size: 8594422639 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6717272768 num_examples: 1091 download_size: 6740538108 dataset_size: 6717272768 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8618674712 num_examples: 1420 download_size: 8649448120 dataset_size: 8618674712 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8660129964 num_examples: 1421 download_size: 8691680929 dataset_size: 8660129964 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8842857082 num_examples: 1440 download_size: 8874581597 dataset_size: 8842857082 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8889486335 num_examples: 1474 download_size: 8921461083 dataset_size: 8889486335 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9107689650 num_examples: 1483 download_size: 9140828036 dataset_size: 9107689650 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9079611515 num_examples: 1473 download_size: 9112756891 dataset_size: 9079611515 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8651416691 num_examples: 1425 download_size: 8683088964 dataset_size: 8651416691 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8805756802 num_examples: 1416 download_size: 8837190154 dataset_size: 8805756802 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8434022491 num_examples: 1350 download_size: 8463835989 dataset_size: 8434022491 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8645068051 num_examples: 1405 download_size: 8676296197 dataset_size: 8645068051 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6505406968 num_examples: 1060 download_size: 6529493775 dataset_size: 6505406968 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8935649178 num_examples: 1442 download_size: 8967341579 dataset_size: 8935649178 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8977856404 num_examples: 1429 download_size: 9009438069 dataset_size: 8977856404 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9250893084 num_examples: 1443 download_size: 9283714245 dataset_size: 9250893084 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8908148488 num_examples: 1446 download_size: 8939861798 dataset_size: 8908148488 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9201901772 num_examples: 1466 download_size: 9234362431 dataset_size: 9201901772 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 8973208285 num_examples: 1438 download_size: 9004836562 dataset_size: 8973208285 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9531262524 num_examples: 1484 download_size: 9565563954 dataset_size: 9531262524 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9237080311 num_examples: 1481 download_size: 9270200551 dataset_size: 9237080311 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9432040586 num_examples: 1503 download_size: 9465196781 dataset_size: 9432040586 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9299174387 num_examples: 1477 download_size: 9332230915 dataset_size: 9299174387 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 6250695911 num_examples: 1037 download_size: 6273368424 dataset_size: 6250695911 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9076719123 num_examples: 1434 download_size: 9107047689 dataset_size: 9076719123 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9042681056 num_examples: 1459 download_size: 9075705064 dataset_size: 9042681056 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9060561447 num_examples: 1456 download_size: 9093521154 dataset_size: 9060561447 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9193480780 num_examples: 1474 download_size: 9226578780 dataset_size: 9193480780 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9642374570 num_examples: 1501 download_size: 9676773522 dataset_size: 9642374570 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9060928875 num_examples: 1439 download_size: 9093805567 dataset_size: 9060928875 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9461107851 num_examples: 1487 download_size: 9494252029 dataset_size: 9461107851 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9380786998 num_examples: 1487 download_size: 9413913597 dataset_size: 9380786998 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9128034376 num_examples: 1453 download_size: 9160750230 dataset_size: 9128034376 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: viA.id dtype: string - name: viA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: viA.audio.speaker_embedding sequence: float32 - name: viA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 9669792454 num_examples: 1518 download_size: 9704382184 dataset_size: 9669792454 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_145 data_files: - split: train path: subset_145/train-* - config_name: subset_146 data_files: - split: train path: subset_146/train-* - config_name: subset_147 data_files: - split: train path: subset_147/train-* - config_name: subset_148 data_files: - split: train path: subset_148/train-* - config_name: subset_149 data_files: - split: train path: subset_149/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

Tuxifan/UbuntuIRC

Tuxifan

--- license: cc0-1.0 task_categories: - text-generation pretty_name: Ubuntu IRC channels --- Completely uncurated collection of IRC logs from the Ubuntu IRC channels

Yossh/danbooru2023-webp-4Mpixel-224

Yossh

--- license: apache-2.0 --- The data set is just resized to 224*224 https://huggingface.co/datasets/KBlueLeaf/danbooru2023-webp-4Mpixel Pseudo code for processing ``` def resize_image(file_path): with Image.open(file_path) as img: resized_img = img.resize((224, 224)) resized_img.save(file_path) ```

hexuan21/weak-to-strong-backup

hexuan21

--- license: apache-2.0 ---

OS-Copilot/OS-Atlas-data

OS-Copilot

--- license: apache-2.0 viewer: false --- # GUI Grounding Pre-training Data for OS-ATLAS This document describes the acquisition of the pre-training data used by OS-ATLAS [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://huggingface.co/papers/2410.23218). <div align="center"> [\[🏠Homepage\]](https://osatlas.github.io) [\[💻Code\]](https://github.com/OS-Copilot/OS-Atlas) [\[🚀Quick Start\]](#quick-start) [\[📝Paper\]](https://arxiv.org/abs/2410.23218) [\[🤗Models\]](https://huggingface.co/collections/OS-Copilot/os-atlas-67246e44003a1dfcc5d0d045) [\[🤗ScreenSpot-v2\]](https://huggingface.co/datasets/OS-Copilot/ScreenSpot-v2) </div>  **Notes:** In GUI grounding data, the position of the target element is recorded in the `bbox` key, represented by `[left, top, right, bottom]`. Each value is a [0, 1] decimal number indicating the ratio of the corresponding position to the width or height of the image. The data stored in this dataset consists of raw data containing **only** element grounding information. When training a model, you need to use the corresponding prompts to wrap these data. The data we released is divided into three domains: mobile, desktop and web. All annotation data is stored in JSON format and each sample contains: * `img_filename`: the interface screenshot file * `instruction`: human instruction or referring expression extracted from ally tree or html * `bbox`: the bounding box of the target element corresponding to instruction Some data also contains a `data_type`, which records the type of an element in its structured information, if it can be obtained. *** ### Mobile data This part of data is stored under the *mobile_domain* directory. Our mobile grounding data consists of four parts. #### AMEX Android Multi-annotation EXpo (AMEX) is a comprehensive, large-scale dataset designed for generalist mobile GUI-control agents [1]. The annotation data is stored in -`amex_raw.json` Due to the single file size limitation of Hugging Face datasets, we stored the Amex images in *zip* format and split them into several sub-files. - `amex_images_part_aa` - `amex_images_part_ab` - `amex_images_part_ac` You need to first merge these split files back into the original file and then extract the contents. ``` cat amex_images_part_* > amex_images.zip 7z x amex_images.zip -aoa -o/path/to/extract/folder ``` #### UIBert UIBert [2] is a dataset extended from Rico dataset [3] for two tasks: similar UI component retrieval and referring expression component retrieval. The annotation data is stored in - `uibert_raw.json` The UIBert images are stored in - `UIBert.zip` #### Widget Captioning and RICOSCA Widget Captioning data are collected by [4]. RICOSCA is a dataset automatically labeled using Android VH in [5] The annotation data is stored in - `widget_captioning.json` - `ricosca.json` The rico images are stored in - `rico_imgs.zip` #### Android_world_data This part of data are sampled from a android environment for building and benchmarking autonomous computer control agents [6]. The annotation data is stored in - `aw_mobile.json` The rico images are stored in - `mobile_images.zip` *** ### Desktop data This part of data is stored under the *desktop_domain* directory. All of the desktop grounding data is collected from the real environments of personal computers running different operating systems. Each image is split into multiple sub-images to enhance data diversity. Our desktop grounding data consists of three parts: Windows, Linux and MacOS. **The image and annotation data for each operating system are stored in corresponding zip and json files.** It is worth noting that, due to the large size of the Windows image data, the split files need to be merged before extraction. ``` cat windows_image_part_* > windows_images.zip 7z x windows_images.zip -aoa -o/path/to/extract/folder ``` *** ### Web data This part of data is stored under the *web_domain* directory. Our desktop grounding data consists of two parts. #### Seeclick web data The web data from SeeClick [7] was crawled from websites provided by Common Crawl, containing more than 270k webpage screenshots and over 3 million webpage elements. The annotation data is stored in - `seeclick_web.json` The images are stored into split files and need to be merged before extraction. ``` cat seeclick_web_image_part_* > seeclick_web_images.zip 7z x seeclick_web_images.zip -aoa -o/path/to/extract/folder ``` #### Fineweb_crawled_data This part of data is crawled from web pages from the latest URLs obtained from FineWeb [8], a cleaned and deduplicated English dataset derived from Common Crawl. Since this portion of the data contains at least 1.6 million images, we have compressed them into 10 zip files, from `fineweb_3m_s11.zip` to `fineweb_3m_s52.zip`. Please extract them into the same directory. As an example, ``` 7z x fineweb_3m_s11.zip -aoa -o/same/path/to/extract/fineweb ``` The annotation data is stored in - `fineweb_3m.json` *** ### Best practice During the training of **OS-Atlas-4B**, we randomly sampled predefined prompts to wrap the grounding data. Additionally, we scaled the relative coordinates of each element (in the range [0, 1]) by multiplying them by 1000 before inputting them into the model for training. Below is an example of a data entry: ``` { "conversations": [ { "from": "human", "value": "<image>\nUsing the provided screenshot, I'll describe webpage elements for you to locate (with bbox).\n<ref>media-maniacs.org</ref>\n<ref>Home</ref>\n<ref>Sitemap</ref>\n<ref>shop you can have what you choose 2012</ref>" }, { "from": "gpt", "value": "<ref>media-maniacs.org</ref><box>[[70,856,141,871]]</box>\n<ref>Home</ref><box>[[21,935,43,951]]</box>\n<ref>Sitemap</ref><box>[[21,919,52,934]]</box>\n<ref>shop you can have what you choose 2012</ref><box>[[368,839,523,855]]</box>" } ] } ``` **OS-Atlas-7B** ``` { "conversations": [ { "from": "human", "value": "<image>\nUsing the provided screenshot, I'll describe webpage elements for you to locate (with bbox).\n<|object_ref_start|>Facebook<|object_ref_end|>\n<|object_ref_start|>Subscribe<|object_ref_end|>\n<|object_ref_start|>Twitter<|object_ref_end|>\n<|object_ref_start|>Read More<|object_ref_end|>\n<|object_ref_start|>Read More<|object_ref_end|>" }, { "from": "gpt", "value": "<|object_ref_start|>Facebook<|object_ref_end|><|box_start|>(4,955),(36,970)<|box_end|>\n<|object_ref_start|>Subscribe<|object_ref_end|><|box_start|>(4,913),(43,932)<|box_end|>\n<|object_ref_start|>Twitter<|object_ref_end|><|box_start|>(39,955),(62,970)<|box_end|>\n<|object_ref_start|>Read More<|object_ref_end|><|box_start|>(30,138),(73,157)<|box_end|>\n<|object_ref_start|>Read More<|object_ref_end|><|box_start|>(30,139),(73,155)<|box_end|>" } ] } ``` The prompts we used are stored in `prompts.json`. *** **The following are the open-source datasets we used as data sources. We welcome everyone to check the details and cite these sources accordingly！** [1] [AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents](https://arxiv.org/abs/2407.17490) [2] [UIBert: Learning Generic Multimodal Representations for UI Understanding](https://arxiv.org/abs/2107.13731) [3] [Rico: A mobile app dataset for building data-driven design applications](https://dl.acm.org/doi/pdf/10.1145/3126594.3126651) [4] [Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements](https://arxiv.org/pdf/2010.04295.pdf) [5] [Mapping Natural Language Instructions to Mobile UI Action Sequences](https://arxiv.org/pdf/2005.03776) [6] [ANDROIDWORLD: A Dynamic Benchmarking Environment for Autonomous Agents](https://arxiv.org/abs/2405.14573) [7] [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://arxiv.org/abs/2401.10935) [8] [The fineweb datasets: Decanting the web for the finest text data at scale](https://arxiv.org/abs/2406.17557)

fsicoli/common_voice_16_0

fsicoli

--- license: cc0-1.0 language: - ab - af - am - ar - as - ast - az - ba - bas - be - bg - bn - br - ca - ckb - cnh - cs - cv - cy - da - de - dv - dyu - el - en - eo - es - et - eu - fa - fi - fr - gl - gn - ha - he - hi - hsb - hu - ia - id - ig - is - it - ja - ka - kab - kk - kmr - ko - ky - lg - lo - lt - lv - mdf - mhr - mk - ml - mn - mr - mrj - mt - myv - nl - oc - or - pl - ps - pt - quy - ro - ru - rw - sah - sat - sc - sk - skr - sl - sq - sr - sw - ta - th - ti - tig - tk - tok - tr - tt - tw - ug - uk - ur - uz - vi - vot - yue - zgh - zh - yo task_categories: - automatic-speech-recognition pretty_name: Common Voice Corpus 16.0 size_categories: - 100B<n<1T tags: - mozilla - foundation --- # Dataset Card for Common Voice Corpus 16.0 <!-- Provide a quick summary of the dataset. --> This dataset is an unofficial version of the Mozilla Common Voice Corpus 16. It was downloaded and converted from the project's website https://commonvoice.mozilla.org/. ## Languages ``` Abkhaz, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Hakha Chin, Hausa, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latvian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Norwegian Nynorsk, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Yoruba ``` ## How to use The datasets library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the load_dataset function. For example, to download the Portuguese config, simply specify the corresponding language config name (i.e., "pt" for Portuguese): ``` from datasets import load_dataset cv_16 = load_dataset("fsicoli/common_voice_16_0", "pt", split="train") ``` Using the datasets library, you can also stream the dataset on-the-fly by adding a streaming=True argument to the load_dataset function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. ``` from datasets import load_dataset cv_16 = load_dataset("fsicoli/common_voice_16_0", "pt", split="train", streaming=True) print(next(iter(cv_16))) ``` Bonus: create a PyTorch dataloader directly with your own datasets (local/streamed). ### Local ``` from datasets import load_dataset from torch.utils.data.sampler import BatchSampler, RandomSampler cv_16 = load_dataset("fsicoli/common_voice_16_0", "pt", split="train") batch_sampler = BatchSampler(RandomSampler(cv_16), batch_size=32, drop_last=False) dataloader = DataLoader(cv_16, batch_sampler=batch_sampler) ``` ### Streaming ``` from datasets import load_dataset from torch.utils.data import DataLoader cv_16 = load_dataset("fsicoli/common_voice_16_0", "pt", split="train") dataloader = DataLoader(cv_16, batch_size=32) ``` To find out more about loading and preparing audio datasets, head over to hf.co/blog/audio-datasets. ### Dataset Structure Data Instances A typical data point comprises the path to the audio file and its sentence. Additional fields include accent, age, client_id, up_votes, down_votes, gender, locale and segment. ### Licensing Information Public Domain, CC-0 ### Citation Information ``` @inproceedings{commonvoice:2020, author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, title = {Common Voice: A Massively-Multilingual Speech Corpus}, booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, pages = {4211--4215}, year = 2020 } ``` ---

2A2I/Arabic_Aya

2A2I

--- language: - ar license: apache-2.0 size_categories: - 1M<n<10M task_categories: - text-classification - translation - summarization pretty_name: 2A dataset_info: - config_name: CohereForAI-aya_collection-aya_dataset features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: string - name: language_code dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 7555482 num_examples: 13960 download_size: 3687445 dataset_size: 7555482 - config_name: CohereForAI-aya_collection-aya_human_annotated features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: test num_bytes: 222650 num_examples: 250 download_size: 120393 dataset_size: 222650 - config_name: CohereForAI-aya_collection-templated_afrisenti features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 5070578 num_examples: 14468 - name: test num_bytes: 2674428 num_examples: 7838 - name: validation num_bytes: 643036 num_examples: 1816 download_size: 2330165 dataset_size: 8388042 - config_name: CohereForAI-aya_collection-templated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 20413129 num_examples: 70000 - name: test num_bytes: 5799667 num_examples: 20000 - name: validation num_bytes: 2976183 num_examples: 10000 download_size: 6746433 dataset_size: 29188979 - config_name: CohereForAI-aya_collection-templated_ntx_llm features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 199809 num_examples: 111 download_size: 34306 dataset_size: 199809 - config_name: CohereForAI-aya_collection-templated_xcsqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: validation num_bytes: 393580 num_examples: 1000 download_size: 137233 dataset_size: 393580 - config_name: CohereForAI-aya_collection-templated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 97691354 num_examples: 90760 - name: test num_bytes: 15499274 num_examples: 14791 - name: validation num_bytes: 10752041 num_examples: 9768 download_size: 57959575 dataset_size: 123942669 - config_name: CohereForAI-aya_collection-translated_adversarial_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 147727007 num_examples: 100000 - name: test num_bytes: 16108000 num_examples: 10000 - name: validation num_bytes: 14862183 num_examples: 10000 download_size: 52642775 dataset_size: 178697190 - config_name: CohereForAI-aya_collection-translated_cnn_dailymail features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 3578924407 num_examples: 1000000 - name: test num_bytes: 415594340 num_examples: 114900 - name: validation num_bytes: 486698663 num_examples: 133680 download_size: 2209523190 dataset_size: 4481217410 - config_name: CohereForAI-aya_collection-translated_dolly features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: gcp_source dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: alphabet dtype: string - name: split dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 213140804 num_examples: 148080 download_size: 96189154 dataset_size: 213140804 - config_name: CohereForAI-aya_collection-translated_flan_coqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 245744048 num_examples: 64090 download_size: 124335769 dataset_size: 245744048 - config_name: CohereForAI-aya_collection-translated_flan_cot features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 634249526 num_examples: 919100 download_size: 273491678 dataset_size: 634249526 - config_name: CohereForAI-aya_collection-translated_flan_gem_wiki features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 961863533.277311 num_examples: 271470 download_size: 485152798 dataset_size: 961863533.277311 - config_name: CohereForAI-aya_collection-translated_flan_lambada features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 16531932 num_examples: 42790 download_size: 7457248 dataset_size: 16531932 - config_name: CohereForAI-aya_collection-translated_flan_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 2989244 num_examples: 5400 download_size: 1292664 dataset_size: 2989244 - config_name: CohereForAI-aya_collection-translated_hotpotqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 1154195031 num_examples: 3554760 - name: validation num_bytes: 69779681 num_examples: 224000 download_size: 420699282 dataset_size: 1223974712 - config_name: CohereForAI-aya_collection-translated_joke_explaination features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 8219049 num_examples: 7540 download_size: 3600136 dataset_size: 8219049 - config_name: CohereForAI-aya_collection-translated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 40908047 num_examples: 140000 - name: test num_bytes: 11646781 num_examples: 40000 - name: validation num_bytes: 5951801 num_examples: 20000 download_size: 12723211 dataset_size: 58506629 - config_name: CohereForAI-aya_collection-translated_mlqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: test num_bytes: 331062576 num_examples: 231800 - name: validation num_bytes: 31900260 num_examples: 22960 download_size: 146571384 dataset_size: 362962836 - config_name: CohereForAI-aya_collection-translated_nqopen features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 397677612 num_examples: 1758500 - name: validation num_bytes: 16780970 num_examples: 72200 download_size: 136208663 dataset_size: 414458582 - config_name: CohereForAI-aya_collection-translated_paws features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 303643575 num_examples: 494010 - name: test num_bytes: 49242541 num_examples: 80000 - name: validation num_bytes: 49475307 num_examples: 80000 download_size: 66436419 dataset_size: 402361423 - config_name: CohereForAI-aya_collection-translated_piqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 113290227 num_examples: 161130 - name: validation num_bytes: 12924744 num_examples: 18380 download_size: 45954644 dataset_size: 126214971 - config_name: CohereForAI-aya_collection-translated_soda features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 6230916321 num_examples: 11915820 - name: test num_bytes: 777982873 num_examples: 1489680 - name: validation num_bytes: 772817056 num_examples: 1463460 download_size: 2804874077 dataset_size: 7781716250 - config_name: CohereForAI-aya_collection-translated_wiki_split features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 6349516377 num_examples: 9899440 - name: test num_bytes: 32058254 num_examples: 50000 - name: validation num_bytes: 32284536 num_examples: 50000 download_size: 2446037624 dataset_size: 6413859167 - config_name: CohereForAI-aya_collection-translated_wikiqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 5014300 num_examples: 10400 - name: test num_bytes: 1378807 num_examples: 2930 - name: validation num_bytes: 685770 num_examples: 1400 download_size: 2872586 dataset_size: 7078877 - config_name: CohereForAI-aya_collection-translated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 5250663186 num_examples: 5231120 - name: test num_bytes: 721821743 num_examples: 729740 - name: validation num_bytes: 635907993 num_examples: 632640 download_size: 3091503409 dataset_size: 6608392922 - config_name: CohereForAI-aya_dataset features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 8314232 num_examples: 13960 - name: test num_bytes: 246400 num_examples: 250 download_size: 3778631 dataset_size: 8560632 - config_name: CohereForAI-aya_evaluation_suite-aya_human_annotated features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: __index_level_0__ dtype: int64 splits: - name: test num_bytes: 222650 num_examples: 250 download_size: 120393 dataset_size: 222650 - config_name: CohereForAI-aya_evaluation_suite-dolly_human_edited features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 - name: __index_level_0__ dtype: int64 splits: - name: test num_bytes: 188495 num_examples: 200 download_size: 100291 dataset_size: 188495 - config_name: CohereForAI-aya_evaluation_suite-dolly_machine_translated features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 - name: __index_level_0__ dtype: int64 splits: - name: test num_bytes: 3491803 num_examples: 2000 download_size: 1762303 dataset_size: 3491803 configs: - config_name: CohereForAI-aya_collection-aya_dataset data_files: - split: train path: CohereForAI-aya_collection-aya_dataset/train-* - config_name: CohereForAI-aya_collection-aya_human_annotated data_files: - split: test path: CohereForAI-aya_collection-aya_human_annotated/test-* - config_name: CohereForAI-aya_collection-templated_afrisenti data_files: - split: train path: CohereForAI-aya_collection-templated_afrisenti/train-* - split: test path: CohereForAI-aya_collection-templated_afrisenti/test-* - split: validation path: CohereForAI-aya_collection-templated_afrisenti/validation-* - config_name: CohereForAI-aya_collection-templated_mintaka data_files: - split: train path: CohereForAI-aya_collection-templated_mintaka/train-* - split: test path: CohereForAI-aya_collection-templated_mintaka/test-* - split: validation path: CohereForAI-aya_collection-templated_mintaka/validation-* - config_name: CohereForAI-aya_collection-templated_ntx_llm data_files: - split: train path: CohereForAI-aya_collection-templated_ntx_llm/train-* - config_name: CohereForAI-aya_collection-templated_xcsqa data_files: - split: validation path: CohereForAI-aya_collection-templated_xcsqa/validation-* - config_name: CohereForAI-aya_collection-templated_xlel_wd data_files: - split: train path: CohereForAI-aya_collection-templated_xlel_wd/train-* - split: test path: CohereForAI-aya_collection-templated_xlel_wd/test-* - split: validation path: CohereForAI-aya_collection-templated_xlel_wd/validation-* - config_name: CohereForAI-aya_collection-translated_adversarial_qa data_files: - split: train path: CohereForAI-aya_collection-translated_adversarial_qa/train-* - split: test path: CohereForAI-aya_collection-translated_adversarial_qa/test-* - split: validation path: CohereForAI-aya_collection-translated_adversarial_qa/validation-* - config_name: CohereForAI-aya_collection-translated_cnn_dailymail data_files: - split: train path: CohereForAI-aya_collection-translated_cnn_dailymail/train-* - split: test path: CohereForAI-aya_collection-translated_cnn_dailymail/test-* - split: validation path: CohereForAI-aya_collection-translated_cnn_dailymail/validation-* - config_name: CohereForAI-aya_collection-translated_dolly data_files: - split: train path: CohereForAI-aya_collection-translated_dolly/train-* - config_name: CohereForAI-aya_collection-translated_flan_coqa data_files: - split: train path: CohereForAI-aya_collection-translated_flan_coqa/train-* - config_name: CohereForAI-aya_collection-translated_flan_cot data_files: - split: train path: CohereForAI-aya_collection-translated_flan_cot/train-* - config_name: CohereForAI-aya_collection-translated_flan_gem_wiki data_files: - split: train path: CohereForAI-aya_collection-translated_flan_gem_wiki/train-* - config_name: CohereForAI-aya_collection-translated_flan_lambada data_files: - split: train path: CohereForAI-aya_collection-translated_flan_lambada/train-* - config_name: CohereForAI-aya_collection-translated_flan_qa data_files: - split: train path: CohereForAI-aya_collection-translated_flan_qa/train-* - config_name: CohereForAI-aya_collection-translated_hotpotqa data_files: - split: train path: CohereForAI-aya_collection-translated_hotpotqa/train-* - split: validation path: CohereForAI-aya_collection-translated_hotpotqa/validation-* - config_name: CohereForAI-aya_collection-translated_joke_explaination data_files: - split: train path: CohereForAI-aya_collection-translated_joke_explaination/train-* - config_name: CohereForAI-aya_collection-translated_mintaka data_files: - split: train path: CohereForAI-aya_collection-translated_mintaka/train-* - split: test path: CohereForAI-aya_collection-translated_mintaka/test-* - split: validation path: CohereForAI-aya_collection-translated_mintaka/validation-* - config_name: CohereForAI-aya_collection-translated_mlqa data_files: - split: test path: CohereForAI-aya_collection-translated_mlqa/test-* - split: validation path: CohereForAI-aya_collection-translated_mlqa/validation-* - config_name: CohereForAI-aya_collection-translated_nqopen data_files: - split: train path: CohereForAI-aya_collection-translated_nqopen/train-* - split: validation path: CohereForAI-aya_collection-translated_nqopen/validation-* - config_name: CohereForAI-aya_collection-translated_paws data_files: - split: train path: CohereForAI-aya_collection-translated_paws/train-* - split: test path: CohereForAI-aya_collection-translated_paws/test-* - split: validation path: CohereForAI-aya_collection-translated_paws/validation-* - config_name: CohereForAI-aya_collection-translated_piqa data_files: - split: train path: CohereForAI-aya_collection-translated_piqa/train-* - split: validation path: CohereForAI-aya_collection-translated_piqa/validation-* - config_name: CohereForAI-aya_collection-translated_soda data_files: - split: train path: CohereForAI-aya_collection-translated_soda/train-* - split: test path: CohereForAI-aya_collection-translated_soda/test-* - split: validation path: CohereForAI-aya_collection-translated_soda/validation-* - config_name: CohereForAI-aya_collection-translated_wiki_split data_files: - split: train path: CohereForAI-aya_collection-translated_wiki_split/train-* - split: test path: CohereForAI-aya_collection-translated_wiki_split/test-* - split: validation path: CohereForAI-aya_collection-translated_wiki_split/validation-* - config_name: CohereForAI-aya_collection-translated_wikiqa data_files: - split: train path: CohereForAI-aya_collection-translated_wikiqa/train-* - split: test path: CohereForAI-aya_collection-translated_wikiqa/test-* - split: validation path: CohereForAI-aya_collection-translated_wikiqa/validation-* - config_name: CohereForAI-aya_collection-translated_xlel_wd data_files: - split: train path: CohereForAI-aya_collection-translated_xlel_wd/train-* - split: test path: CohereForAI-aya_collection-translated_xlel_wd/test-* - split: validation path: CohereForAI-aya_collection-translated_xlel_wd/validation-* - config_name: CohereForAI-aya_dataset data_files: - split: train path: CohereForAI-aya_dataset/train-* - split: test path: CohereForAI-aya_dataset/test-* - config_name: CohereForAI-aya_evaluation_suite-aya_human_annotated data_files: - split: test path: CohereForAI-aya_evaluation_suite-aya_human_annotated/test-* - config_name: CohereForAI-aya_evaluation_suite-dolly_human_edited data_files: - split: test path: CohereForAI-aya_evaluation_suite-dolly_human_edited/test-* - config_name: CohereForAI-aya_evaluation_suite-dolly_machine_translated data_files: - split: test path: CohereForAI-aya_evaluation_suite-dolly_machine_translated/test-* --- # Dataset Card for : Arabic Aya (2A) <!-- Provide a quick summary of the dataset. --> <!-- This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).--> ## **Arabic Aya (2A) : A Curated Subset of the Aya Collection for Arabic Language Processing** ### Dataset Sources & Infos - **Data Origin**: Derived from 69 subsets of the original Aya datasets : [CohereForAI/aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection), [CohereForAI/aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset), and [CohereForAI/aya_evaluation_suite](https://huggingface.co/datasets/CohereForAI/aya_evaluation_suite). - **Languages**: Modern Standard Arabic (MSA) and a variety of Arabic dialects ( 'arb', 'arz', 'ary', 'ars', 'knc', 'acm', 'apc', 'aeb', 'ajp', 'acq' ) - **Applications**: `Language Modeling`, `Text Classification`, `Sentiment Analysis`, `Dialect Identification`, `Translation` - **Paper:** [2402.06619](https://huggingface.co/papers/2402.06619) - **Maintainer:** [Elfilali Ali](https://huggingface.co/Ali-C137) - **License:** Apache-2.0 ### Overview `Arabic Aya` is a meticulously curated dataset derived from the comprehensive Aya collection by [CohereForAI](https://huggingface.co/CohereForAI), specifically focusing on Arabic text data. This dataset aggregates content from the [CohereForAI/aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection), [CohereForAI/aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset), and [CohereForAI/aya_evaluation_suite](https://huggingface.co/datasets/CohereForAI/aya_evaluation_suite), filtering out all but the Arabic content, including both Modern Standard Arabic (MSA) and various regional dialects. ### Purpose The aim of 'Arabic Aya' is to provide researchers, technologists, and linguists with a ready-to-use Arabic text resource, significantly reducing the time and effort required for data preprocessing in NLP and AI projects focused on the Arabic language. - Use the Aya datasets out of the box for your Arabic applications and research 😀 ### Usage This dataset serves as a foundational tool for those embarking on Arabic language projects, from academic research to commercial applications. By providing a pre-filtered source of Arabic text, 'Arabic Aya' enables users to dive straight into model training, analysis, and application development without the preliminary hassle of data cleaning and language filtering. #### Use with HuggingFace's datasets library To load this dataset with Datasets, you'll need to install Datasets as `pip install datasets --upgrade` and then use a similar code to the following: ```python from datasets import load_dataset dataset = load_dataset("2A2I/Arabic_Aya", "CohereForAI-aya_collection-templated_mintaka") ``` In the above code snippet, "CohereForAI-aya_collection-templated_mintaka" refers to the arabic version (100k rows) of the original "templated_mintaka" subset (780k rows) of the aya_collection. You can load other subsets by specifying its name at the time of loading the dataset. ### Access and Contribution Available on the Hugging Face Hub under [2A2I/Arabic_Aya](https://huggingface.co/datasets/2A2I/Arabic_Aya), 'Arabic Aya' invites contributions from the community. Users are encouraged to offer feedback, suggest improvements. ### Support and Collaboration We are committed to fostering an inclusive and supportive environment around Arabic AI and NLP research. For support, collaboration, or queries regarding the dataset, please reach out through the Hugging Face Hub's discussion section or reach out at [2A2I Contact Email]([email protected]). # Original Dataset Card of Aya by CohereForAI  # Dataset Summary The Aya Collection is a massive multilingual collection consisting of 513 million instances of prompts and completions covering a wide range of tasks. This collection incorporates instruction-style templates from fluent speakers and applies them to a curated list of datasets, as well as translations of instruction-style datasets into 101 languages. Aya Dataset, a human-curated multilingual instruction and response dataset, is also part of this collection. See our paper for more details regarding the collection. - **Curated by:** Contributors of [Aya Open Science Intiative](https://cohere.com/research/aya) - **Language(s):** 115 languages - **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) - **Aya Datasets Family:** | Name | Explanation | |------|--------------| | [aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset) | Human-annotated multilingual instruction finetuning dataset, comprising over 204K instances across 65 languages. | | [aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection) | Created by applying instruction-style templates from fluent speakers to 44 datasets, including translations of 19 instruction-style datasets into 101 languages.| | [aya_evaluation_suite](https://huggingface.co/datasets/CohereForAI/aya_evaluation_suite) | A diverse evaluation set for multilingual open-ended generation, featuring 250 culturally grounded prompts in 7 languages, 200 translated prompts in 24 languages, and human-edited versions selected for cross-cultural relevance from English Dolly in 6 languages.| # Dataset The `Aya Collection` is a comprehensive, large corpus of datasets that can be used by researchers around the world to train multilingual models. Our goal is only to include datasets with permissive licensing for manipulation and redistribution. The `Aya Collection` consists of three different sources of data: 1. Templated data: We collaborated with fluent speakers to create templates that allowed for the automatic expansion of existing datasets into various languages. 2. Translated data: We translated a hand-selected subset of 19 datasets into 101 languages (114 dialects) using the NLLB 3.3B parameter machine translation model. 3. Aya Dataset: We release the [Aya Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset) as a subset of the overall collection. This is the only dataset in the collection that is human-annotated in its entirety. ## Load with Datasets To load this dataset with Datasets, you'll need to install Datasets as `pip install datasets --upgrade` and then use the following code: ```python from datasets import load_dataset dataset = load_dataset("CohereForAI/aya_collection", "templated_mintaka") ``` In the above code snippet, "templated_mintaka" refers to a subset of the aya_collection. You can load other subsets by specifying its name at the time of loading the dataset. ## Data Instances An example of a `train` instance looks as follows: ```json {'id': 246001, 'inputs': 'The following query in English is taken from the geography category. What could be the answer to the question?\nWhat is the seventh tallest mountain in North America?', 'targets': 'The answer is Mount Lucania.', 'dataset_name': 'Mintaka-inst', 'sub_dataset_name': '-', 'task_type': 'question-answering', 'template_id': 3, 'language': 'eng', 'split': 'train', 'script': 'Latn' } ``` ## Data Fields The data fields are the same among all splits: - `id:` Unique id of the data point - `inputs:` Prompt or input to the language model. - `targets:` Completion or output of the language model. - `dataset_name:` The name of the source dataset that the data point was taken from - `sub_dataset_name:` If the source is a collection, this field indicates which part of that collection the data point was taken from. If it is not a collection, this field is left blank. - `task_type:` The task type that this conversation belongs to. - `template_id`: The id of the template applied to this data point. - `language:` The ISO code of the dialect of the conversation. - `script:` The script of the language. - `split:` Indicates whether the data point is part of the `train` or the `test` split. ### Statistics The total number of data points, including the Aya Dataset` is 513,758,189. To view the breakdown of dialect codes and the respective templated and translated data point counts in the Aya Collection , refer to the toggled table below. <details> <summary> <b> Breakdown of Aya Collection data point counts grouped by dialects </b> </summary> |dialect code|language|translated data point count|templated data point count|total count | |------------|--------|---------------------------|--------------------------|---------------| |ace |Achinese|8240684 |2000 |8242684 | |acm |Arabic |4120342 |0 |4120342 | |acq |Arabic |4120342 |0 |4120342 | |aeb |Arabic |4120342 |0 |4120342 | |afr |Afrikaans|4120342 |6108 |4126450 | |ajp |Arabic |4120342 |0 |4120342 | |als |Albanian|4120342 |0 |4120342 | |amh |Amharic |4120342 |25327 |4145669 | |apc |Arabic |4120342 |0 |4120342 | |arb |Arabic |6424999 |216430 |6641429 | |ars |Arabic |4120342 |0 |4120342 | |ary |Arabic |4120342 |18076 |4138418 | |arz |Arabic |4120342 |0 |4120342 | |azb |Azerbaijani|4120342 |0 |4120342 | |azj |Azerbaijani|4120342 |0 |4120342 | |bel |Belarusian|4120342 |21273 |4141615 | |ben |Bengali |4120342 |30661 |4151003 | |bjn |Banjar |8240684 |2000 |8242684 | |bul |Bulgarian|4120342 |37722 |4158064 | |cat |Catalan |4120342 |66900 |4187242 | |ceb |Cebuano |4120342 |0 |4120342 | |ces |Czech |4120342 |179604 |4299946 | |ckb |Kurdish |4120342 |0 |4120342 | |cym |Welsh |4120342 |0 |4120342 | |dan |Danish |4120342 |36310 |4156652 | |deu |German |4120342 |1326722 |5447064 | |ell |Greek |4120342 |40291 |4160633 | |eng |English |9771427 |8066678 |17838105 | |epo |Esperanto|4120342 |0 |4120342 | |est |Estonian|4120342 |0 |4120342 | |eus |Basque |4120342 |0 |4120342 | |fin |Finnish |4120342 |457895 |4578237 | |fra |French |4120342 |835520 |4955862 | |gla |Scottish Gaelic|4120342 |0 |4120342 | |gle |Irish |4120342 |0 |4120342 | |glg |Galician|4120342 |0 |4120342 | |guj |Gujarati|4120342 |2157 |4122499 | |hat |Haitian Creole|4120342 |0 |4120342 | |hau |Hausa |4120342 |51396 |4171738 | |heb |Hebrew |4120342 |103466 |4223808 | |hin |Hindi |4120342 |260387 |4380729 | |hun |Hungarian|4120342 |82039 |4202381 | |hye |Armenian|4120342 |7080 |4127422 | |ibo |Igbo |4120342 |36312 |4156654 | |ind |Indonesian|4120342 |45709 |4166051 | |isl |Icelandic|4120342 |0 |4120342 | |ita |Italian |4120342 |405682 |4526024 | |jav |Javanese|4120342 |829 |4121171 | |jpn |Japanese|4120342 |2693177 |6813519 | |kan |Kannada |4120342 |1156 |4121498 | |kas |Kashmiri|4120342 |0 |4120342 | |kat |Georgian|4120342 |0 |4120342 | |kaz |Kazakh |4120342 |0 |4120342 | |khk |Mongolian|4120342 |0 |4120342 | |khm |Khmer |4120342 |0 |4120342 | |kir |Kyrgyz |4120342 |0 |4120342 | |kmr |Kurdish |4120342 |0 |4120342 | |knc |Kanuri |8240684 |0 |8240684 | |kor |Korean |4120342 |41011 |4161353 | |lao |Lao |4120342 |0 |4120342 | |lit |Lithuanian|4120342 |0 |4120342 | |ltz |Luxembourgish|4120342 |0 |4120342 | |lvs |Latvian |4120342 |0 |4120342 | |mal |Malayalam|4120342 |4347 |4124689 | |mar |Marathi |4120342 |3678 |4124020 | |min |Minangkabau|6753788 |2000 |6755788 | |mkd |Macedonian|4120342 |0 |4120342 | |mlt |Maltese |4120342 |0 |4120342 | |mni |Manipuri|4120342 |0 |4120342 | |mri |Maori |4120342 |0 |4120342 | |mya |Burmese |4120342 |0 |4120342 | |nld |Dutch |4120342 |220181 |4340523 | |nno |Norwegian|4120342 |0 |4120342 | |nob |Norwegian|4120342 |0 |4120342 | |npi |Nepali |4120342 |0 |4120342 | |nso |Northern Sotho|4120342 |0 |4120342 | |pbt |Pashto |4120342 |0 |4120342 | |pes |Persian |4120342 |245520 |4365862 | |plt |Malagasy|4120342 |0 |4120342 | |pol |Polish |4120342 |332503 |4452845 | |por |Portuguese|4120342 |287432 |4407774 | |ron |Romanian|4120342 |36359 |4156701 | |rus |Russian |4120342 |545920 |4666262 | |sin |Sinhala |4120342 |195 |4120537 | |slk |Slovak |4120342 |27845 |4148187 | |slv |Slovenian|4120342 |25731 |4146073 | |smo |Samoan |4120342 |0 |4120342 | |sna |Shona |4120342 |3684 |4124026 | |snd |Sindhi |4120342 |0 |4120342 | |som |Somali |4120342 |2926 |4123268 | |sot |Southern Sotho|4120342 |0 |4120342 | |spa |Spanish |4120342 |379194 |4499536 | |srp |Serbian |4120342 |77124 |4197466 | |sun |Sundanese|4120342 |2208 |4122550 | |swe |Swedish |4120342 |76486 |4196828 | |swh |Swahili |4120342 |12726 |4133068 | |tam |Tamil |4120342 |11462 |4131804 | |taq |Tamasheq|4120342 |0 |4120342 | |tel |Telugu |4120342 |477821 |4598163 | |tgk |Tajik |4120342 |0 |4120342 | |tha |Thai |4120342 |2125180 |6245522 | |tur |Turkish |4120342 |59932 |4180274 | |ukr |Ukrainian|4120342 |189384 |4309726 | |urd |Urdu |4120342 |337739 |4458081 | |uzn |Uzbek |4120342 |0 |4120342 | |vie |Vietnamese|4120342 |42232 |4162574 | |xho |Xhosa |4120342 |2952 |4123294 | |ydd |Yiddish |4120342 |0 |4120342 | |yor |Yoruba |4120342 |4907 |4125249 | |yue |Chinese |4120342 |0 |4120342 | |zho-Hans |Chinese |4120342 |54528 |4174870 | |zho-Hant |Chinese |4120342 |0 |4120342 | |zsm |Malay |4120342 |13950 |4134292 | |zul |Zulu |4120342 |786 |4121128 | |arq |Arabic |0 |6046 |6046 | |ban |Balinese|0 |2000 |2000 | |bbc |Toba Batak|0 |2000 |2000 | |bem |Bemba |0 |776 |776 | |fil |Filipino|0 |220 |220 | |fon |Fon |0 |845 |845 | |hrv |Croatian|0 |9007 |9007 | |kin |Kinyarwanda|0 |11165 |11165 | |lij |Ligurian|0 |6409 |6409 | |mad |Madurese|0 |2000 |2000 | |nij |Ngaju |0 |2000 |2000 | |nor |Norwegian|0 |72352 |72352 | |pan |Punjabi |0 |2156 |2156 | |twi |Twi |0 |10840 |10840 | |wol |Wolof |0 |785 |785 | |zho |Chinese |0 |74972 |74972 | PS: Templated data also includes Mozambican Portuguese, which doesn't have its own ISO language code. </details> <br> # Motivations & Intentions - **Curation Rationale:** Automatic augmentation of existing datasets serves to enhance the available linguistic resources for multiple languages. The list of languages was initially established from mT5 and aligned with the annotators’ language list and NLLB translation model. The datasets were translated directly from English for all languages. # Additional Information ## Provenance - **Methods Used:** A combination of crowd-sourced templating and automatic translation was employed to source this dataset. - **Methodology Details:** - *Source:* Existing NLP datasets - *Dates of Collection:* May 2023 - Dec 2023 ## Dataset Version and Maintenance - **Maintenance Status:** Actively Maintained - **Version Details:** - *Current version:* 1.0 - *Last Update:* 02/2024 - *First Release:* 02/2024 ## Authorship - **Publishing Organization:** [Cohere For AI](https://cohere.com/research) - **Industry Type:** Not-for-profit - Tech - **Contact Details:** https://cohere.com/research/aya ## Licensing Information This dataset can be used for any purpose, whether academic or commercial, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Citation Information ```bibtex @misc{singh2024aya, title={Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning}, author={Shivalika Singh and Freddie Vargus and Daniel Dsouza and Börje F. Karlsson and Abinaya Mahendiran and Wei-Yin Ko and Herumb Shandilya and Jay Patel and Deividas Mataciunas and Laura OMahony and Mike Zhang and Ramith Hettiarachchi and Joseph Wilson and Marina Machado and Luisa Souza Moura and Dominik Krzemiński and Hakimeh Fadaei and Irem Ergün and Ifeoma Okoh and Aisha Alaagib and Oshan Mudannayake and Zaid Alyafeai and Vu Minh Chien and Sebastian Ruder and Surya Guthikonda and Emad A. Alghamdi and Sebastian Gehrmann and Niklas Muennighoff and Max Bartolo and Julia Kreutzer and Ahmet Üstün and Marzieh Fadaee and Sara Hooker}, year={2024}, eprint={2402.06619}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

anon8231489123/ShareGPT_Vicuna_unfiltered

anon8231489123

--- license: apache-2.0 language: - en --- **Further cleaning done. Please look through the dataset and ensure that I didn't miss anything.** **Update: Confirmed working method for training the model: https://huggingface.co/AlekseyKorshuk/vicuna-7b/discussions/4#64346c08ef6d5abefe42c12c** Two choices: - Removes instances of "I'm sorry, but": https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json - Has instances of "I'm sorry, but": https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split.json The choice is yours. The first dataset may go to far and remove valuable data. The second is better for when the AI asks for clarification, but it also may refuse to do stuff like browse the internet, which it actually may be able to do with certain langchain implementations. These are important things to think about before training. ~100k ShareGPT conversations narrowed down to 53k by: * Removing non-english conversations * Removing excessive unicode (indicative of Chinese or Korean text, usually) * Removing excessive repeated characters * Removing various instances "AI Moralizing". Conversations with these phrases were removed (and a few others that can't be mentioned here): "text-based AI language model", "domestic violence", "please refrain", "derogatory", "inappropriate", "offensive", "racism", "racist", "racial", "discriminate", "discriminatory", "discrimination", "sexist", "sexism", "unacceptable", "inclusive workplace", "lgbt", "morals", "ethics", "ethical", "legality", "illegal", "illegality", "hateful", "harmful", "it is never okay", "It is important to", "It's important to", "real-world consequences", "hate speech", "glorify", "not be appropriate", "supremacist", "extremist", "responsible AI", "AI principles", "AI assistant", "an AI language", "ableist", "hurtful", "gender stereotype", "gender inequality", "underrepresentation", "safe spaces", "gender-based", "inclusivity", "feminist", "feminism", "transgender", "empowerment", "communist", "capitalism", "stereotypes", "biases", "bias", "Microaggression", "prioritize human safety", "as a language model", "as an AI language model", "As a large language model", "As an AI", "ethical principles", "consensual", "it is not appropriate", "it's not appropriate", "I cannot fulfill your request", "harmful to human beings", "ethical guidelines", "my guidelines", "prioritize user safety", "adhere to ethical guidelines", "harmful consequences", "potentially harmful", "dangerous activities", "promote safety", "well-being of all users", "responsible information sharing", "jeopardize the safety", "illegal actions or intentions", "undermine the stability", "promote the well-being", "illegal activities or actions", "adherence to the law", "potentially be harmful", "illegal substances or activities", "committed to promoting", "safe information", "lawful information", "cannot provide guidance", "cannot provide information", "unable to offer assistance", "cannot engage in discussions", "programming prohibits", "follow ethical guidelines", "ensure the safety", "involves an illegal subject", "prioritize safety", "illegal subject", "prioritize user well-being", "cannot support or promote", "activities that could harm", "pose a risk to others", "against my programming", "activities that could undermine", "potentially dangerous", "not within the scope", "designed to prioritize safety", "not able to provide", "maintain user safety", "adhere to safety guidelines", "dangerous or harmful", "cannot provide any information", "focus on promoting safety" * Conversations split into 2048 token chunks as described here: https://github.com/lm-sys/FastChat/blob/main/docs/commands/data_cleaning.md This should be fully ready to train an unfiltered english Vicuna model based on the procedure here: https://github.com/lm-sys/FastChat/

inductiva/windtunnel-20k

inductiva

--- pretty_name: Wind Tunnel 20K Dataset size_categories: - 10K<n<100K task_categories: - feature-extraction - graph-ml - image-to-3d language: - en tags: - simulation - openfoam - physics - windtunnel - inductiva - machine learning - synthetic --- <p align="center"> <img src="https://huggingface.co/datasets/inductiva/windtunnel/resolve/main/pressure_field_mesh.png", width="500px"> </p> # Wind Tunnel Dataset The **Wind Tunnel Dataset** contains **19,812 OpenFOAM simulations** of **1,000 unique automobile-like objects** placed in a virtual wind tunnel measuring **20 meters long, 10 meters wide, and 8 meters high.** Each object was tested under **20 different conditions**: 4 random wind speeds ranging from **10 to 50 m/s**, and 5 rotation angles (**0°**, **180°** and **3 random angles**). The object meshes were generated using [Instant Mesh](https://github.com/TencentARC/InstantMesh) based on images sourced from the [Stanford Cars Dataset](https://www.kaggle.com/datasets/jessicali9530/stanford-cars-dataset). To make sure the results are stable and reliable, each simulation runs for **300 iterations**. The entire dataset is organized into three subsets: **70% for training, 20% for validation, and 10% for testing.** The data generation process itself was orchestrated using the [Inductiva API](https://inductiva.ai/), which allowed us to run hundreds of OpenFOAM simulations in parallel on the cloud. ## Motivation: Addressing the Data Gap in CFD Recently, there’s been a lot of interest in using **machine learning (ML)** to speed up **CFD simulations**. Research has shown that for well-defined scenarios—like a virtual wind tunnel—you can train an ML model to “predict” the results of a simulation **much faster** than traditional methods, while still keeping the accuracy close to what you’d expect from classical simulations. That said, the **ML/CFD communities** are still lacking enough **training data** for their research. We’ve identified two main reasons for this. First, there’s a shortage of datasets with **high-quality 3D meshes** needed for running CFD simulations. Existing 3D object datasets have a lot of limitations: they’re either too small, closed-source, or have low-quality meshes. Without this input data, it’s been really hard to generate large-scale training datasets for realistic CFD scenarios, which almost always involve 3D meshes. Second, even if you had all the 3D meshes you needed, setting up and running thousands of **CFD simulations** to generate a large, diverse dataset isn’t easy. To create a dataset like this, you’d need to define an initial simulation scenario (like the wind tunnel setup) and then run enough variations—different meshes, wind speeds, and so on—to cover a wide range of data points for training a robust **ML model**. The problem is, running a single CFD simulation can be tricky enough with most software. Orchestrating **thousands of simulations** and handling all the resulting data? That’s a whole new level of challenge. While both of these problems are difficult to solve in general, we decided to focus on one common CFD scenario: a **virtual wind tunnel** for **static automobiles**. Using the popular **OpenFOAM** simulation package, we produced a large dataset of CFD simulations. Next, we’ll explain how we tackled the challenges of generating the data and orchestrating the simulations. ## Generating a Large Quantity of Automobile-like 3D Meshes Since there aren’t many publicly available 3D meshes of automobiles, we decided to use recent image-to-mesh models to generate meshes from freely available car images. We specifically used the open-source [InstantMesh](https://github.com/TencentARC/InstantMesh) model (Apache-2.0), which is currently state-of-the-art in **image-to-mesh generation**. We generated the automobile-like meshes by running Instant Mesh on **1,000 images** from the publicly available [Stanford Cars Dataset](https://www.kaggle.com/datasets/jessicali9530/stanford-cars-dataset) (Apache-2.0), which contains 16,185 images of automobiles. Running the image-to-mesh model naturally results in some defects, like irregular surfaces, asymmetry, holes, and disconnected components. To address these issues, we implemented a custom post-processing step to improve mesh quality. We used **PCA** to align the meshes with the main axes and removed any disconnected components. The resulting set of meshes still contains minor defects, like “spikes” or “cavities” in flat areas, unexpected holes, and asymmetry issues. However, we see these imperfections as valuable features of the dataset. From a machine learning perspective, they bring challenges that can help prevent overfitting and contribute to building more robust and generalizable models. ## Orchestrating 20k Cloud Simulations—Using Just Python To tackle the challenge of orchestrating **20,000 OpenFOAM simulations**, we resorted to the **Inductiva API**. The Inductiva platform offers a simple Python API for running simulation workflows in the cloud and supports several popular open-source packages, including **OpenFOAM**. Here’s an [example](https://docs.inductiva.ai/en/latest/simulators/OpenFOAM.html) of how to run an OpenFOAM simulation using Inductiva. With the Inductiva API, it’s easy to parameterize specific simulation scenarios and run variations of a base case by programmatically adjusting the input parameters and starting conditions of the simulation. More details [here](#OpenFoam-Parameters). Additionally, users can create custom Python classes that wrap these parameterized simulations, providing a simple Python interface for running simulations—no need to interact directly with the underlying simulation packages. We used the [Inductiva API to create a Python class for the Wind Tunnel scenario](https://github.com/inductiva/wind-tunnel), which allowed us to run **20,000 simulations** across a range of input parameters. For more on how to transform your complex simulation workflows into easy-to-use Python classes, we wrote a [blog post](https://inductiva.ai/blog/article/transform-complex-simulations) all about it. ## How Did We Generate the Dataset? 1. **Generate Input Meshes**: We first generated input meshes using the **InstantMesh model** with images from the **Stanford Cars Dataset**, followed by post-processing to improve mesh quality. 2. **Run OpenFOAM Simulations**: Using the Inductiva API, we ran OpenFOAM simulations on the input meshes under different wind speeds and angles. The result is an output mesh `openfoam_mesh.obj`that contains all the relevant simulation data. 3. **Post-process OpenFOAM Output**: We post-processed the OpenFOAM output to generate streamlines and pressure map meshes. The code we used to generate and post-process the meshes is available on [GitHub](https://github.com/inductiva/datasets-generation/tree/main/windtunnel_dataset). ## Dataset Structure ``` data ├── train │ ├── <SIMULATION_ID> │ │ ├── input_mesh.obj │ │ ├── openfoam_mesh.obj │ │ ├── pressure_field_mesh.vtk │ │ ├── simulation_metadata.json │ │ └── streamlines_mesh.ply │ └── ... ├── validation │ └── ... └── test └── ... ``` ## Dataset Files Each simulation in the Wind Tunnel Dataset is accompanied by several key files that provide both the input and the output data of the simulations. Here’s a breakdown of the files included in each simulation: - **[input_mesh.obj](#input_meshobj)**: OBJ file with the input mesh. - **[openfoam_mesh.obj](#openfoam_meshobj)**: OBJ file with the OpenFOAM mesh. - **[pressure_field_mesh.vtk](#pressure_field_meshvtk)**: VTK file with the pressure field data. - **[streamlines_mesh.ply](#streamlines_meshply)**: PLY file with the streamlines. - **[metadata.json](#metadatajson)**: JSON with metadata about the input parameters and about some output results such as the force coefficients (obtained via simulation) and the path of the output files. ### input_mesh.obj The input mesh we generated using the Instant Mesh model from images in the Stanford Cars Dataset, serves as the starting point for the OpenFOAM simulation. Details on the mesh generation process can be found [here](#Generating-a-large-quantity-of-Automobile-like-3D-Meshes). | **Input Mesh** | **# points of input meshes** | |-------------------------------|------------------------------| |  |  | ```python import pyvista as pv # Load the mesh mesh_path = "input_mesh.obj" mesh = pv.read(mesh_path) # Get the vertices (points) vertices = mesh.points # Get the faces (connections) # The faces array contains the number of vertices per face followed by the vertex indices. # For example: [3, v1, v2, v3, 3, v4, v5, v6, ...] where 3 means a triangle. faces = mesh.faces ``` ### openfoam_mesh.obj This mesh is the result of the OpenFOAM simulation. The number of points is reduced compared to the `input_mesh.obj` due to mesh refinement and processing steps applied by OpenFOAM during the simulation. | **OpenFoam Mesh** | **# points of OpenFoam meshes** | |-------------------------------|------------------------------| |  |  | ```python import pyvista as pv # Load the mesh mesh_path = "openfoam_mesh.obj" mesh = pv.read(mesh_path) # Get the vertices (points) vertices = mesh.points # Get the faces (connections) # The faces array contains the number of vertices per face followed by the vertex indices. # For example: [3, v1, v2, v3, 3, v4, v5, v6, ...] where 3 means a triangle. faces = mesh.faces ``` ### pressure_field_mesh.vtk Pressure values were extracted from the `openfoam_mesh.obj` and interpolated onto the `input_mesh.obj` using the closest point strategy. This approach allowed us to project the pressure values onto a higher-resolution mesh. As shown in the histogram, the the point distribution matches that of the `input_mesh.obj`. More details can be found here [here](https://github.com/inductiva/wind-tunnel/blob/deab68a018531ff05d0d8ef9d63d8c108800f78f/windtunnel/windtunnel_outputs.py#L111). | **Pressure Field Mesh** | **# points of Pressure Field meshes** | |-------------------------------|------------------------------| |  | ) | ```python import pyvista as pv mesh_path = "pressure_field_mesh.vtk" mesh = pv.read(mesh_path) # The vertices array contains the coordinates of each point in the mesh. vertices = mesh.points # The faces array contains the number of vertices per face followed by the vertex indices. # For example: [3, v1, v2, v3, 3, v4, v5, v6, ...] where 3 means a triangle. faces = mesh.faces # Get the pressure data (scalar named "p") # This retrieves the pressure values associated with each vertex in the mesh. pressure_data = mesh.point_data["p"] ``` ### streamlines_mesh.ply Streamlines visually represent the flow characteristics within the simulation, illustrating how air flows around the object More information can be found [here](https://github.com/inductiva/wind-tunnel/blob/deab68a018531ff05d0d8ef9d63d8c108800f78f/windtunnel/windtunnel_outputs.py#L70). | **Streamlines Mesh** | **# points of streamlines meshes** | |-------------------------------|------------------------------| |  |  | ### metadata.json This file contains metadata related to the simulation, including input parameters such as `wind_speed`, `rotate_angle`, `num_iterations`, and `resolution`. Additionally, it includes output parameters like `drag_coefficient`, `moment_coefficient`, `lift_coefficient`, `front_lift_coefficient`, and `rear_lift_coefficient`. The file also specifies the locations of the generated output meshes. ```json { "id": "1w63au1gpxgyn9kun5q9r7eqa", "object_file": "object_24.obj", "wind_speed": 35, "rotate_angle": 332, "num_iterations": 300, "resolution": 5, "drag_coefficient": 0.8322182, "moment_coefficient": 0.3425206, "lift_coefficient": 0.1824983, "front_lift_coefficient": 0.4337698, "rear_lift_coefficient": -0.2512715, "input_mesh_path": "data/train/1w63au1gpxgyn9kun5q9r7eqa/input_mesh.obj", "openfoam_mesh_path": "data/train/1w63au1gpxgyn9kun5q9r7eqa/openfoam_mesh.obj", "pressure_field_mesh_path": "data/train/1w63au1gpxgyn9kun5q9r7eqa/pressure_field_mesh.vtk", "streamlines_mesh_path": "data/train/1w63au1gpxgyn9kun5q9r7eqa/streamlines_mesh.ply" } ``` ### Dataset Statistics The dataset includes **19,812 valid samples** out of **20,000 simulations**, with [188 submissions failing](https://huggingface.co/datasets/inductiva/windtunnel/resolve/main/failed_tasks.txt) due to numerical errors in OpenFOAM. The full dataset requires about **300 GB** of storage, but you can also download smaller portions if needed. ## Downloading the Dataset: To download the dataset, you’ll need to install the [Datasets package](https://huggingface.co/docs/datasets/en/index) from Hugging Face: ```python pip install datasets ``` ### 1. Using snapshot_download() ```python import huggingface_hub dataset_name = "inductiva/windtunnel-20k" # Download the entire dataset huggingface_hub.snapshot_download(repo_id=dataset_name, repo_type="dataset") # Download to a specific local directory huggingface_hub.snapshot_download( repo_id=dataset_name, repo_type="dataset", local_dir="local_folder" ) # Download only the simulation metadata across all simulations huggingface_hub.snapshot_download( repo_id=dataset_name, repo_type="dataset", local_dir="local_folder", allow_patterns=["*/*/*/simulation_metadata.json"] ) ``` ### 2. Using load_dataset() ```python import datasets # Load the dataset (streaming is supported) dataset = datasets.load_dataset("inductiva/windtunnel-20k", streaming=False) # Display dataset information print(dataset) # Access a sample from the training set sample = dataset["train"][0] print("Sample from training set:", sample) ``` ## OpenFoam Parameters We used the [Inductiva Template Manager](https://tutorials.inductiva.ai/intro_to_api/templating.html) to **parameterize** the OpenFoam configuration files. Below are some snippets from the templates used in the wind tunnel simulations. initialConditions.jinja ```jinja flowVelocity ({{ wind_speed }} 0 0); ``` controlDict.jinja ```jinja endTime {{ num_iterations }}; ``` forceCoeffs.jinja ```jinja magUInf {{ wind_speed }}; lRef {{ length }}; // Wheelbase length Aref {{ area }}; // Estimated ``` snappyHexMeshDict.jinja ```jinja geometry { object { type triSurfaceMesh; file "object.obj"; } refinementBox { type searchableBox; min ({{ x_min }} {{ y_min }} {{ z_min }}); max ({{ x_max }} {{ y_max }} {{ z_max }}); } }; features ( { file "object.eMesh"; level {{ resolution + 1 }}; } ); refinementSurfaces { object { // Surface-wise min and max refinement level level ({{ resolution }} {{ resolution + 1 }}); } } refinementRegions { refinementBox { mode inside; levels ((1E15 {{ resolution - 1 }})); } } locationInMesh ({{ x_min }} {{ y_min }} {{ z_min }}); ``` You can find the full OpenFoam configuration on github: [https://github.com/inductiva/wind-tunnel/tree/main/windtunnel/templates](https://github.com/inductiva/wind-tunnel/tree/main/windtunnel/templates) ## What's Next? If you encounter any issues with this dataset, feel free to reach out at [[email protected]]([email protected]). If you spot any problematic meshes, let us know so we can fix them in the next version of the **Windtunnel-20k dataset**. To learn more about how we created this dataset—or how you can generate synthetic datasets for Physics-AI models—check out our well-tested [4-step recipe for generating synthetic data](https://inductiva.ai/blog/article/supercharge-your-physics-ml-with-inductivas-cloud-based-simulation-api) or discover how to [transform your own complex simulation workflows into easy-to-use Python classes](https://inductiva.ai/blog/article/transform-complex-simulations). You may also be interested in reading our blog post, [The 3D Mesh Resolution Threshold - 5k Points is All You Need!](https://inductiva.ai/blog/article/5k-points-is-all-you-need), where we explore just how much you can reduce the level of detail in a 3D object while still maintaining accurate aerodynamic results in a virtual wind tunnel built with OpenFOAM.

wecover/OPUS_TED2020

wecover

--- configs: - config_name: default data_files: - split: train path: '*/*/train.parquet' - split: valid path: '*/*/valid.parquet' - split: test path: '*/*/test.parquet' - config_name: af data_files: - split: train path: '*/*af*/train.parquet' - split: test path: '*/*af*/test.parquet' - split: valid path: '*/*af*/valid.parquet' - config_name: am data_files: - split: train path: '*/*am*/train.parquet' - split: test path: '*/*am*/test.parquet' - split: valid path: '*/*am*/valid.parquet' - config_name: ar data_files: - split: train path: '*/*ar*/train.parquet' - split: test path: '*/*ar*/test.parquet' - split: valid path: '*/*ar*/valid.parquet' - config_name: az data_files: - split: train path: '*/*az*/train.parquet' - split: test path: '*/*az*/test.parquet' - split: valid path: '*/*az*/valid.parquet' - config_name: be data_files: - split: train path: '*/*be*/train.parquet' - split: test path: '*/*be*/test.parquet' - split: valid path: '*/*be*/valid.parquet' - config_name: bg data_files: - split: train path: '*/*bg*/train.parquet' - split: test path: '*/*bg*/test.parquet' - split: valid path: '*/*bg*/valid.parquet' - config_name: bn data_files: - split: train path: '*/*bn*/train.parquet' - split: test path: '*/*bn*/test.parquet' - split: valid path: '*/*bn*/valid.parquet' - config_name: bs data_files: - split: train path: '*/*bs*/train.parquet' - split: test path: '*/*bs*/test.parquet' - split: valid path: '*/*bs*/valid.parquet' - config_name: ca data_files: - split: train path: '*/*ca*/train.parquet' - split: test path: '*/*ca*/test.parquet' - split: valid path: '*/*ca*/valid.parquet' - config_name: cs data_files: - split: train path: '*/*cs*/train.parquet' - split: test path: '*/*cs*/test.parquet' - split: valid path: '*/*cs*/valid.parquet' - config_name: da data_files: - split: train path: '*/*da*/train.parquet' - split: test path: '*/*da*/test.parquet' - split: valid path: '*/*da*/valid.parquet' - config_name: de data_files: - split: train path: '*/*de*/train.parquet' - split: test path: '*/*de*/test.parquet' - split: valid path: '*/*de*/valid.parquet' - config_name: el data_files: - split: train path: '*/*el*/train.parquet' - split: test path: '*/*el*/test.parquet' - split: valid path: '*/*el*/valid.parquet' - config_name: en data_files: - split: train path: '*/*en*/train.parquet' - split: test path: '*/*en*/test.parquet' - split: valid path: '*/*en*/valid.parquet' - config_name: eo data_files: - split: train path: '*/*eo*/train.parquet' - split: test path: '*/*eo*/test.parquet' - split: valid path: '*/*eo*/valid.parquet' - config_name: es data_files: - split: train path: '*/*es*/train.parquet' - split: test path: '*/*es*/test.parquet' - split: valid path: '*/*es*/valid.parquet' - config_name: et data_files: - split: train path: '*/*et*/train.parquet' - split: test path: '*/*et*/test.parquet' - split: valid path: '*/*et*/valid.parquet' - config_name: eu data_files: - split: train path: '*/*eu*/train.parquet' - split: test path: '*/*eu*/test.parquet' - split: valid path: '*/*eu*/valid.parquet' - config_name: fa data_files: - split: train path: '*/*fa*/train.parquet' - split: test path: '*/*fa*/test.parquet' - split: valid path: '*/*fa*/valid.parquet' - config_name: fi data_files: - split: train path: '*/*fi*/train.parquet' - split: test path: '*/*fi*/test.parquet' - split: valid path: '*/*fi*/valid.parquet' - config_name: fr data_files: - split: train path: '*/*fr*/train.parquet' - split: test path: '*/*fr*/test.parquet' - split: valid path: '*/*fr*/valid.parquet' - config_name: ga data_files: - split: train path: '*/*ga*/train.parquet' - split: test path: '*/*ga*/test.parquet' - split: valid path: '*/*ga*/valid.parquet' - config_name: gl data_files: - split: train path: '*/*gl*/train.parquet' - split: test path: '*/*gl*/test.parquet' - split: valid path: '*/*gl*/valid.parquet' - config_name: he data_files: - split: train path: '*/*he*/train.parquet' - split: test path: '*/*he*/test.parquet' - split: valid path: '*/*he*/valid.parquet' - config_name: hi data_files: - split: train path: '*/*hi*/train.parquet' - split: test path: '*/*hi*/test.parquet' - split: valid path: '*/*hi*/valid.parquet' - config_name: hr data_files: - split: train path: '*/*hr*/train.parquet' - split: test path: '*/*hr*/test.parquet' - split: valid path: '*/*hr*/valid.parquet' - config_name: hu data_files: - split: train path: '*/*hu*/train.parquet' - split: test path: '*/*hu*/test.parquet' - split: valid path: '*/*hu*/valid.parquet' - config_name: hy data_files: - split: train path: '*/*hy*/train.parquet' - split: test path: '*/*hy*/test.parquet' - split: valid path: '*/*hy*/valid.parquet' - config_name: id data_files: - split: train path: '*/*id*/train.parquet' - split: test path: '*/*id*/test.parquet' - split: valid path: '*/*id*/valid.parquet' - config_name: is data_files: - split: train path: '*/*is*/train.parquet' - split: test path: '*/*is*/test.parquet' - split: valid path: '*/*is*/valid.parquet' - config_name: it data_files: - split: train path: '*/*it*/train.parquet' - split: test path: '*/*it*/test.parquet' - split: valid path: '*/*it*/valid.parquet' - config_name: ja data_files: - split: train path: '*/*ja*/train.parquet' - split: test path: '*/*ja*/test.parquet' - split: valid path: '*/*ja*/valid.parquet' - config_name: ka data_files: - split: train path: '*/*ka*/train.parquet' - split: test path: '*/*ka*/test.parquet' - split: valid path: '*/*ka*/valid.parquet' - config_name: kk data_files: - split: train path: '*/*kk*/train.parquet' - split: test path: '*/*kk*/test.parquet' - split: valid path: '*/*kk*/valid.parquet' - config_name: km data_files: - split: train path: '*/*km*/train.parquet' - split: test path: '*/*km*/test.parquet' - split: valid path: '*/*km*/valid.parquet' - config_name: kn data_files: - split: train path: '*/*kn*/train.parquet' - split: test path: '*/*kn*/test.parquet' - split: valid path: '*/*kn*/valid.parquet' - config_name: ko data_files: - split: train path: '*/*ko*/train.parquet' - split: test path: '*/*ko*/test.parquet' - split: valid path: '*/*ko*/valid.parquet' - config_name: ku data_files: - split: train path: '*/*ku*/train.parquet' - split: test path: '*/*ku*/test.parquet' - split: valid path: '*/*ku*/valid.parquet' - config_name: lo data_files: - split: train path: '*/*lo*/train.parquet' - split: test path: '*/*lo*/test.parquet' - split: valid path: '*/*lo*/valid.parquet' - config_name: lt data_files: - split: train path: '*/*lt*/train.parquet' - split: test path: '*/*lt*/test.parquet' - split: valid path: '*/*lt*/valid.parquet' - config_name: mg data_files: - split: train path: '*/*mg*/train.parquet' - split: test path: '*/*mg*/test.parquet' - split: valid path: '*/*mg*/valid.parquet' - config_name: mk data_files: - split: train path: '*/*mk*/train.parquet' - split: test path: '*/*mk*/test.parquet' - split: valid path: '*/*mk*/valid.parquet' - config_name: ml data_files: - split: train path: '*/*ml*/train.parquet' - split: test path: '*/*ml*/test.parquet' - split: valid path: '*/*ml*/valid.parquet' - config_name: mn data_files: - split: train path: '*/*mn*/train.parquet' - split: test path: '*/*mn*/test.parquet' - split: valid path: '*/*mn*/valid.parquet' - config_name: mr data_files: - split: train path: '*/*mr*/train.parquet' - split: test path: '*/*mr*/test.parquet' - split: valid path: '*/*mr*/valid.parquet' - config_name: ms data_files: - split: train path: '*/*ms*/train.parquet' - split: test path: '*/*ms*/test.parquet' - split: valid path: '*/*ms*/valid.parquet' - config_name: my data_files: - split: train path: '*/*my*/train.parquet' - split: test path: '*/*my*/test.parquet' - split: valid path: '*/*my*/valid.parquet' - config_name: ne data_files: - split: train path: '*/*ne*/train.parquet' - split: test path: '*/*ne*/test.parquet' - split: valid path: '*/*ne*/valid.parquet' - config_name: nl data_files: - split: train path: '*/*nl*/train.parquet' - split: test path: '*/*nl*/test.parquet' - split: valid path: '*/*nl*/valid.parquet' - config_name: pl data_files: - split: train path: '*/*pl*/train.parquet' - split: test path: '*/*pl*/test.parquet' - split: valid path: '*/*pl*/valid.parquet' - config_name: pt data_files: - split: train path: '*/*pt*/train.parquet' - split: test path: '*/*pt*/test.parquet' - split: valid path: '*/*pt*/valid.parquet' - config_name: ro data_files: - split: train path: '*/*ro*/train.parquet' - split: test path: '*/*ro*/test.parquet' - split: valid path: '*/*ro*/valid.parquet' - config_name: ru data_files: - split: train path: '*/*ru*/train.parquet' - split: test path: '*/*ru*/test.parquet' - split: valid path: '*/*ru*/valid.parquet' - config_name: sk data_files: - split: train path: '*/*sk*/train.parquet' - split: test path: '*/*sk*/test.parquet' - split: valid path: '*/*sk*/valid.parquet' - config_name: sl data_files: - split: train path: '*/*sl*/train.parquet' - split: test path: '*/*sl*/test.parquet' - split: valid path: '*/*sl*/valid.parquet' - config_name: so data_files: - split: train path: '*/*so*/train.parquet' - split: test path: '*/*so*/test.parquet' - split: valid path: '*/*so*/valid.parquet' - config_name: sq data_files: - split: train path: '*/*sq*/train.parquet' - split: test path: '*/*sq*/test.parquet' - split: valid path: '*/*sq*/valid.parquet' - config_name: sr data_files: - split: train path: '*/*sr*/train.parquet' - split: test path: '*/*sr*/test.parquet' - split: valid path: '*/*sr*/valid.parquet' - config_name: sv data_files: - split: train path: '*/*sv*/train.parquet' - split: test path: '*/*sv*/test.parquet' - split: valid path: '*/*sv*/valid.parquet' - config_name: sw data_files: - split: train path: '*/*sw*/train.parquet' - split: test path: '*/*sw*/test.parquet' - split: valid path: '*/*sw*/valid.parquet' - config_name: ta data_files: - split: train path: '*/*ta*/train.parquet' - split: test path: '*/*ta*/test.parquet' - split: valid path: '*/*ta*/valid.parquet' - config_name: te data_files: - split: train path: '*/*te*/train.parquet' - split: test path: '*/*te*/test.parquet' - split: valid path: '*/*te*/valid.parquet' - config_name: th data_files: - split: train path: '*/*th*/train.parquet' - split: test path: '*/*th*/test.parquet' - split: valid path: '*/*th*/valid.parquet' - config_name: tl data_files: - split: train path: '*/*tl*/train.parquet' - split: test path: '*/*tl*/test.parquet' - split: valid path: '*/*tl*/valid.parquet' - config_name: tr data_files: - split: train path: '*/*tr*/train.parquet' - split: test path: '*/*tr*/test.parquet' - split: valid path: '*/*tr*/valid.parquet' - config_name: ug data_files: - split: train path: '*/*ug*/train.parquet' - split: test path: '*/*ug*/test.parquet' - split: valid path: '*/*ug*/valid.parquet' - config_name: uk data_files: - split: train path: '*/*uk*/train.parquet' - split: test path: '*/*uk*/test.parquet' - split: valid path: '*/*uk*/valid.parquet' - config_name: ur data_files: - split: train path: '*/*ur*/train.parquet' - split: test path: '*/*ur*/test.parquet' - split: valid path: '*/*ur*/valid.parquet' - config_name: uz data_files: - split: train path: '*/*uz*/train.parquet' - split: test path: '*/*uz*/test.parquet' - split: valid path: '*/*uz*/valid.parquet' - config_name: vi data_files: - split: train path: '*/*vi*/train.parquet' - split: test path: '*/*vi*/test.parquet' - split: valid path: '*/*vi*/valid.parquet' - config_name: ky data_files: - split: train path: '*/*ky*/train.parquet' - split: test path: '*/*ky*/test.parquet' - split: valid path: '*/*ky*/valid.parquet' - config_name: si data_files: - split: train path: '*/*si*/train.parquet' - split: test path: '*/*si*/test.parquet' - split: valid path: '*/*si*/valid.parquet' - config_name: as data_files: - split: train path: '*/*as*/train.parquet' - split: test path: '*/*as*/test.parquet' - split: valid path: '*/*as*/valid.parquet' - config_name: ha data_files: - split: train path: '*/*ha*/train.parquet' - split: test path: '*/*ha*/test.parquet' - split: valid path: '*/*ha*/valid.parquet' - config_name: la data_files: - split: train path: '*/*la*/train.parquet' - split: test path: '*/*la*/test.parquet' - split: valid path: '*/*la*/valid.parquet' - config_name: pa data_files: - split: train path: '*/*pa*/train.parquet' - split: test path: '*/*pa*/test.parquet' - split: valid path: '*/*pa*/valid.parquet' - config_name: ps data_files: - split: train path: '*/*ps*/train.parquet' - split: test path: '*/*ps*/test.parquet' - split: valid path: '*/*ps*/valid.parquet' ---

huggingface/release-assets

huggingface

--- license: mit ---

poloclub/diffusiondb

poloclub

--- layout: default title: Home nav_order: 1 has_children: false annotations_creators: - no-annotation language: - en language_creators: - found license: - cc0-1.0 multilinguality: - multilingual pretty_name: DiffusionDB size_categories: - n>1T source_datasets: - original tags: - stable diffusion - prompt engineering - prompts - research paper task_categories: - text-to-image - image-to-text task_ids: - image-captioning --- # DiffusionDB <img width="100%" src="https://user-images.githubusercontent.com/15007159/201762588-f24db2b8-dbb2-4a94-947b-7de393fc3d33.gif"> ## Table of Contents - [DiffusionDB](#diffusiondb) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Two Subsets](#two-subsets) - [Key Differences](#key-differences) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Dataset Metadata](#dataset-metadata) - [Metadata Schema](#metadata-schema) - [Data Splits](#data-splits) - [Loading Data Subsets](#loading-data-subsets) - [Method 1: Using Hugging Face Datasets Loader](#method-1-using-hugging-face-datasets-loader) - [Method 2. Use the PoloClub Downloader](#method-2-use-the-poloclub-downloader) - [Usage/Examples](#usageexamples) - [Downloading a single file](#downloading-a-single-file) - [Downloading a range of files](#downloading-a-range-of-files) - [Downloading to a specific directory](#downloading-to-a-specific-directory) - [Setting the files to unzip once they've been downloaded](#setting-the-files-to-unzip-once-theyve-been-downloaded) - [Method 3. Use `metadata.parquet` (Text Only)](#method-3-use-metadataparquet-text-only) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) - [Who are the source language producers?](#who-are-the-source-language-producers) - [Annotations](#annotations) - [Annotation process](#annotation-process) - [Who are the annotators?](#who-are-the-annotators) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [DiffusionDB homepage](https://poloclub.github.io/diffusiondb) - **Repository:** [DiffusionDB repository](https://github.com/poloclub/diffusiondb) - **Distribution:** [DiffusionDB Hugging Face Dataset](https://huggingface.co/datasets/poloclub/diffusiondb) - **Paper:** [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://arxiv.org/abs/2210.14896) - **Point of Contact:** [Jay Wang](mailto:[email protected]) ### Dataset Summary DiffusionDB is the first large-scale text-to-image prompt dataset. It contains **14 million** images generated by Stable Diffusion using prompts and hyperparameters specified by real users. DiffusionDB is publicly available at [🤗 Hugging Face Dataset](https://huggingface.co/datasets/poloclub/diffusiondb). ### Supported Tasks and Leaderboards The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. ### Languages The text in the dataset is mostly English. It also contains other languages such as Spanish, Chinese, and Russian. ### Two Subsets DiffusionDB provides two subsets (DiffusionDB 2M and DiffusionDB Large) to support different needs. |Subset|Num of Images|Num of Unique Prompts|Size|Image Directory|Metadata Table| |:--|--:|--:|--:|--:|--:| |DiffusionDB 2M|2M|1.5M|1.6TB|`images/`|`metadata.parquet`| |DiffusionDB Large|14M|1.8M|6.5TB|`diffusiondb-large-part-1/` `diffusiondb-large-part-2/`|`metadata-large.parquet`| ##### Key Differences 1. Two subsets have a similar number of unique prompts, but DiffusionDB Large has much more images. DiffusionDB Large is a superset of DiffusionDB 2M. 2. Images in DiffusionDB 2M are stored in `png` format; images in DiffusionDB Large use a lossless `webp` format. ## Dataset Structure We use a modularized file structure to distribute DiffusionDB. The 2 million images in DiffusionDB 2M are split into 2,000 folders, where each folder contains 1,000 images and a JSON file that links these 1,000 images to their prompts and hyperparameters. Similarly, the 14 million images in DiffusionDB Large are split into 14,000 folders. ```bash # DiffusionDB 2M ./ ├── images │   ├── part-000001 │   │   ├── 3bfcd9cf-26ea-4303-bbe1-b095853f5360.png │   │   ├── 5f47c66c-51d4-4f2c-a872-a68518f44adb.png │   │   ├── 66b428b9-55dc-4907-b116-55aaa887de30.png │   │   ├── [...] │   │   └── part-000001.json │   ├── part-000002 │   ├── part-000003 │   ├── [...] │   └── part-002000 └── metadata.parquet ``` ```bash # DiffusionDB Large ./ ├── diffusiondb-large-part-1 │   ├── part-000001 │   │   ├── 0a8dc864-1616-4961-ac18-3fcdf76d3b08.webp │   │   ├── 0a25cacb-5d91-4f27-b18a-bd423762f811.webp │   │   ├── 0a52d584-4211-43a0-99ef-f5640ee2fc8c.webp │   │   ├── [...] │   │   └── part-000001.json │   ├── part-000002 │   ├── part-000003 │   ├── [...] │   └── part-010000 ├── diffusiondb-large-part-2 │   ├── part-010001 │   │   ├── 0a68f671-3776-424c-91b6-c09a0dd6fc2d.webp │   │   ├── 0a0756e9-1249-4fe2-a21a-12c43656c7a3.webp │   │   ├── 0aa48f3d-f2d9-40a8-a800-c2c651ebba06.webp │   │   ├── [...] │   │   └── part-000001.json │   ├── part-010002 │   ├── part-010003 │   ├── [...] │   └── part-014000 └── metadata-large.parquet ``` These sub-folders have names `part-0xxxxx`, and each image has a unique name generated by [UUID Version 4](https://en.wikipedia.org/wiki/Universally_unique_identifier). The JSON file in a sub-folder has the same name as the sub-folder. Each image is a `PNG` file (DiffusionDB 2M) or a lossless `WebP` file (DiffusionDB Large). The JSON file contains key-value pairs mapping image filenames to their prompts and hyperparameters. ### Data Instances For example, below is the image of `f3501e05-aef7-4225-a9e9-f516527408ac.png` and its key-value pair in `part-000001.json`. <img width="300" src="https://i.imgur.com/gqWcRs2.png"> ```json { "f3501e05-aef7-4225-a9e9-f516527408ac.png": { "p": "geodesic landscape, john chamberlain, christopher balaskas, tadao ando, 4 k, ", "se": 38753269, "c": 12.0, "st": 50, "sa": "k_lms" }, } ``` ### Data Fields - key: Unique image name - `p`: Prompt - `se`: Random seed - `c`: CFG Scale (guidance scale) - `st`: Steps - `sa`: Sampler ### Dataset Metadata To help you easily access prompts and other attributes of images without downloading all the Zip files, we include two metadata tables `metadata.parquet` and `metadata-large.parquet` for DiffusionDB 2M and DiffusionDB Large, respectively. The shape of `metadata.parquet` is (2000000, 13) and the shape of `metatable-large.parquet` is (14000000, 13). Two tables share the same schema, and each row represents an image. We store these tables in the Parquet format because Parquet is column-based: you can efficiently query individual columns (e.g., prompts) without reading the entire table. Below are three random rows from `metadata.parquet`. | image_name | prompt | part_id | seed | step | cfg | sampler | width | height | user_name | timestamp | image_nsfw | prompt_nsfw | |:-----------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------:|-----------:|-------:|------:|----------:|--------:|---------:|:-----------------------------------------------------------------|:--------------------------|-------------:|--------------:| | 0c46f719-1679-4c64-9ba9-f181e0eae811.png | a small liquid sculpture, corvette, viscous, reflective, digital art | 1050 | 2026845913 | 50 | 7 | 8 | 512 | 512 | c2f288a2ba9df65c38386ffaaf7749106fed29311835b63d578405db9dbcafdb | 2022-08-11 09:05:00+00:00 | 0.0845108 | 0.00383462 | | a00bdeaa-14eb-4f6c-a303-97732177eae9.png | human sculpture of lanky tall alien on a romantic date at italian restaurant with smiling woman, nice restaurant, photography, bokeh | 905 | 1183522603 | 50 | 10 | 8 | 512 | 768 | df778e253e6d32168eb22279a9776b3cde107cc82da05517dd6d114724918651 | 2022-08-19 17:55:00+00:00 | 0.692934 | 0.109437 | | 6e5024ce-65ed-47f3-b296-edb2813e3c5b.png | portrait of barbaric spanish conquistador, symmetrical, by yoichi hatakenaka, studio ghibli and dan mumford | 286 | 1713292358 | 50 | 7 | 8 | 512 | 640 | 1c2e93cfb1430adbd956be9c690705fe295cbee7d9ac12de1953ce5e76d89906 | 2022-08-12 03:26:00+00:00 | 0.0773138 | 0.0249675 | #### Metadata Schema `metadata.parquet` and `metatable-large.parquet` share the same schema. |Column|Type|Description| |:---|:---|:---| |`image_name`|`string`|Image UUID filename.| |`prompt`|`string`|The text prompt used to generate this image.| |`part_id`|`uint16`|Folder ID of this image.| |`seed`|`uint32`| Random seed used to generate this image.| |`step`|`uint16`| Step count (hyperparameter).| |`cfg`|`float32`| Guidance scale (hyperparameter).| |`sampler`|`uint8`| Sampler method (hyperparameter). Mapping: `{1: "ddim", 2: "plms", 3: "k_euler", 4: "k_euler_ancestral", 5: "k_heun", 6: "k_dpm_2", 7: "k_dpm_2_ancestral", 8: "k_lms", 9: "others"}`. |`width`|`uint16`|Image width.| |`height`|`uint16`|Image height.| |`user_name`|`string`|The unique discord ID's SHA256 hash of the user who generated this image. For example, the hash for `xiaohk#3146` is `e285b7ef63be99e9107cecd79b280bde602f17e0ca8363cb7a0889b67f0b5ed0`. "deleted_account" refer to users who have deleted their accounts. None means the image has been deleted before we scrape it for the second time.| |`timestamp`|`timestamp`|UTC Timestamp when this image was generated. None means the image has been deleted before we scrape it for the second time. Note that timestamp is not accurate for duplicate images that have the same prompt, hypareparameters, width, height.| |`image_nsfw`|`float32`|Likelihood of an image being NSFW. Scores are predicted by [LAION's state-of-art NSFW detector](https://github.com/LAION-AI/LAION-SAFETY) (range from 0 to 1). A score of 2.0 means the image has already been flagged as NSFW and blurred by Stable Diffusion.| |`prompt_nsfw`|`float32`|Likelihood of a prompt being NSFW. Scores are predicted by the library [Detoxicy](https://github.com/unitaryai/detoxify). Each score represents the maximum of `toxicity` and `sexual_explicit` (range from 0 to 1).| > **Warning** > Although the Stable Diffusion model has an NSFW filter that automatically blurs user-generated NSFW images, this NSFW filter is not perfect—DiffusionDB still contains some NSFW images. Therefore, we compute and provide the NSFW scores for images and prompts using the state-of-the-art models. The distribution of these scores is shown below. Please decide an appropriate NSFW score threshold to filter out NSFW images before using DiffusionDB in your projects. <img src="https://i.imgur.com/1RiGAXL.png" width="100%"> ### Data Splits For DiffusionDB 2M, we split 2 million images into 2,000 folders where each folder contains 1,000 images and a JSON file. For DiffusionDB Large, we split 14 million images into 14,000 folders where each folder contains 1,000 images and a JSON file. ### Loading Data Subsets DiffusionDB is large (1.6TB or 6.5 TB)! However, with our modularized file structure, you can easily load a desirable number of images and their prompts and hyperparameters. In the [`example-loading.ipynb`](https://github.com/poloclub/diffusiondb/blob/main/notebooks/example-loading.ipynb) notebook, we demonstrate three methods to load a subset of DiffusionDB. Below is a short summary. #### Method 1: Using Hugging Face Datasets Loader You can use the Hugging Face [`Datasets`](https://huggingface.co/docs/datasets/quickstart) library to easily load prompts and images from DiffusionDB. We pre-defined 16 DiffusionDB subsets (configurations) based on the number of instances. You can see all subsets in the [Dataset Preview](https://huggingface.co/datasets/poloclub/diffusiondb/viewer/all/train). ```python import numpy as np from datasets import load_dataset # Load the dataset with the `large_random_1k` subset dataset = load_dataset('poloclub/diffusiondb', 'large_random_1k') ``` #### Method 2. Use the PoloClub Downloader This repo includes a Python downloader [`download.py`](https://github.com/poloclub/diffusiondb/blob/main/scripts/download.py) that allows you to download and load DiffusionDB. You can use it from your command line. Below is an example of loading a subset of DiffusionDB. ##### Usage/Examples The script is run using command-line arguments as follows: - `-i` `--index` - File to download or lower bound of a range of files if `-r` is also set. - `-r` `--range` - Upper bound of range of files to download if `-i` is set. - `-o` `--output` - Name of custom output directory. Defaults to the current directory if not set. - `-z` `--unzip` - Unzip the file/files after downloading - `-l` `--large` - Download from Diffusion DB Large. Defaults to Diffusion DB 2M. ###### Downloading a single file The specific file to download is supplied as the number at the end of the file on HuggingFace. The script will automatically pad the number out and generate the URL. ```bash python download.py -i 23 ``` ###### Downloading a range of files The upper and lower bounds of the set of files to download are set by the `-i` and `-r` flags respectively. ```bash python download.py -i 1 -r 2000 ``` Note that this range will download the entire dataset. The script will ask you to confirm that you have 1.7Tb free at the download destination. ###### Downloading to a specific directory The script will default to the location of the dataset's `part` .zip files at `images/`. If you wish to move the download location, you should move these files as well or use a symbolic link. ```bash python download.py -i 1 -r 2000 -o /home/$USER/datahoarding/etc ``` Again, the script will automatically add the `/` between the directory and the file when it downloads. ###### Setting the files to unzip once they've been downloaded The script is set to unzip the files _after_ all files have downloaded as both can be lengthy processes in certain circumstances. ```bash python download.py -i 1 -r 2000 -z ``` #### Method 3. Use `metadata.parquet` (Text Only) If your task does not require images, then you can easily access all 2 million prompts and hyperparameters in the `metadata.parquet` table. ```python from urllib.request import urlretrieve import pandas as pd # Download the parquet table table_url = f'https://huggingface.co/datasets/poloclub/diffusiondb/resolve/main/metadata.parquet' urlretrieve(table_url, 'metadata.parquet') # Read the table using Pandas metadata_df = pd.read_parquet('metadata.parquet') ``` ## Dataset Creation ### Curation Rationale Recent diffusion models have gained immense popularity by enabling high-quality and controllable image generation based on text prompts written in natural language. Since the release of these models, people from different domains have quickly applied them to create award-winning artworks, synthetic radiology images, and even hyper-realistic videos. However, generating images with desired details is difficult, as it requires users to write proper prompts specifying the exact expected results. Developing such prompts requires trial and error, and can often feel random and unprincipled. Simon Willison analogizes writing prompts to wizards learning “magical spells”: users do not understand why some prompts work, but they will add these prompts to their “spell book.” For example, to generate highly-detailed images, it has become a common practice to add special keywords such as “trending on artstation” and “unreal engine” in the prompt. Prompt engineering has become a field of study in the context of text-to-text generation, where researchers systematically investigate how to construct prompts to effectively solve different down-stream tasks. As large text-to-image models are relatively new, there is a pressing need to understand how these models react to prompts, how to write effective prompts, and how to design tools to help users generate images. To help researchers tackle these critical challenges, we create DiffusionDB, the first large-scale prompt dataset with 14 million real prompt-image pairs. ### Source Data #### Initial Data Collection and Normalization We construct DiffusionDB by scraping user-generated images on the official Stable Diffusion Discord server. We choose Stable Diffusion because it is currently the only open-source large text-to-image generative model, and all generated images have a CC0 1.0 Universal Public Domain Dedication license that waives all copyright and allows uses for any purpose. We choose the official [Stable Diffusion Discord server](https://discord.gg/stablediffusion) because it is public, and it has strict rules against generating and sharing illegal, hateful, or NSFW (not suitable for work, such as sexual and violent content) images. The server also disallows users to write or share prompts with personal information. #### Who are the source language producers? The language producers are users of the official [Stable Diffusion Discord server](https://discord.gg/stablediffusion). ### Annotations The dataset does not contain any additional annotations. #### Annotation process [N/A] #### Who are the annotators? [N/A] ### Personal and Sensitive Information The authors removed the discord usernames from the dataset. We decide to anonymize the dataset because some prompts might include sensitive information: explicitly linking them to their creators can cause harm to creators. ## Considerations for Using the Data ### Social Impact of Dataset The purpose of this dataset is to help develop better understanding of large text-to-image generative models. The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. It should note that we collect images and their prompts from the Stable Diffusion Discord server. The Discord server has rules against users generating or sharing harmful or NSFW (not suitable for work, such as sexual and violent content) images. The Stable Diffusion model used in the server also has an NSFW filter that blurs the generated images if it detects NSFW content. However, it is still possible that some users had generated harmful images that were not detected by the NSFW filter or removed by the server moderators. Therefore, DiffusionDB can potentially contain these images. To mitigate the potential harm, we provide a [Google Form](https://forms.gle/GbYaSpRNYqxCafMZ9) on the [DiffusionDB website](https://poloclub.github.io/diffusiondb/) where users can report harmful or inappropriate images and prompts. We will closely monitor this form and remove reported images and prompts from DiffusionDB. ### Discussion of Biases The 14 million images in DiffusionDB have diverse styles and categories. However, Discord can be a biased data source. Our images come from channels where early users could use a bot to use Stable Diffusion before release. As these users had started using Stable Diffusion before the model was public, we hypothesize that they are AI art enthusiasts and are likely to have experience with other text-to-image generative models. Therefore, the prompting style in DiffusionDB might not represent novice users. Similarly, the prompts in DiffusionDB might not generalize to domains that require specific knowledge, such as medical images. ### Other Known Limitations **Generalizability.** Previous research has shown a prompt that works well on one generative model might not give the optimal result when used in other models. Therefore, different models can need users to write different prompts. For example, many Stable Diffusion prompts use commas to separate keywords, while this pattern is less seen in prompts for DALL-E 2 or Midjourney. Thus, we caution researchers that some research findings from DiffusionDB might not be generalizable to other text-to-image generative models. ## Additional Information ### Dataset Curators DiffusionDB is created by [Jay Wang](https://zijie.wang), [Evan Montoya](https://www.linkedin.com/in/evan-montoya-b252391b4/), [David Munechika](https://www.linkedin.com/in/dmunechika/), [Alex Yang](https://alexanderyang.me), [Ben Hoover](https://www.bhoov.com), [Polo Chau](https://faculty.cc.gatech.edu/~dchau/). ### Licensing Information The DiffusionDB dataset is available under the [CC0 1.0 License](https://creativecommons.org/publicdomain/zero/1.0/). The Python code in this repository is available under the [MIT License](https://github.com/poloclub/diffusiondb/blob/main/LICENSE). ### Citation Information ```bibtex @article{wangDiffusionDBLargescalePrompt2022, title = {{{DiffusionDB}}: {{A}} Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models}, author = {Wang, Zijie J. and Montoya, Evan and Munechika, David and Yang, Haoyang and Hoover, Benjamin and Chau, Duen Horng}, year = {2022}, journal = {arXiv:2210.14896 [cs]}, url = {https://arxiv.org/abs/2210.14896} } ``` ### Contributions If you have any questions, feel free to [open an issue](https://github.com/poloclub/diffusiondb/issues/new) or contact [Jay Wang](https://zijie.wang).

SwayStar123/preprocessed_commoncatalog-cc-by_DCAE

SwayStar123

--- license: cc task_categories: - text-to-image language: - en pretty_name: 'Preprocessed Common catalogue (CC-BY) DCAE ' size_categories: - 10M<n<100M --- The images are resized and then encoded with the DC-AE f32 autoencoder. The resizing is done with a bucketmanager with base resolution 512x512, minimum side length 256, maximum side length 1024, all sides are divisible by 32 ofcourse as they needed to be encoded by the DCAEf32 encoder. The captions are generated with moondream2, encoded with siglip and bert. (Bert embeddings variance is very high, so use a norm layer). The text embeddings are padded to 64 tokens, but i have provided the unpadded length aswell so you can prune it to the maximum in the batch and save compute.

Salesforce/lotsa_data

Salesforce

--- license: apache-2.0 configs: - config_name: default data_files: - split: train path: "*/*.arrow" - config_name: "BEIJING_SUBWAY_30MIN" data_files: - split: train path: "BEIJING_SUBWAY_30MIN/*.arrow" - config_name: "HZMETRO" data_files: - split: train path: "HZMETRO/*.arrow" - config_name: "LOOP_SEATTLE" data_files: - split: train path: "LOOP_SEATTLE/*.arrow" - config_name: "LOS_LOOP" data_files: - split: train path: "LOS_LOOP/*.arrow" - config_name: "M_DENSE" data_files: - split: train path: "M_DENSE/*.arrow" - config_name: "PEMS03" data_files: - split: train path: "PEMS03/*.arrow" - config_name: "PEMS04" data_files: - split: train path: "PEMS04/*.arrow" - config_name: "PEMS07" data_files: - split: train path: "PEMS07/*.arrow" - config_name: "PEMS08" data_files: - split: train path: "PEMS08/*.arrow" - config_name: "PEMS_BAY" data_files: - split: train path: "PEMS_BAY/*.arrow" - config_name: "Q-TRAFFIC" data_files: - split: train path: "Q-TRAFFIC/*.arrow" - config_name: "SHMETRO" data_files: - split: train path: "SHMETRO/*.arrow" - config_name: "SZ_TAXI" data_files: - split: train path: "SZ_TAXI/*.arrow" - config_name: "alibaba_cluster_trace_2018" data_files: - split: train path: "alibaba_cluster_trace_2018/*.arrow" - config_name: "australian_electricity_demand" data_files: - split: train path: "australian_electricity_demand/*.arrow" - config_name: "azure_vm_traces_2017" data_files: - split: train path: "azure_vm_traces_2017/*.arrow" - config_name: "bdg-2_bear" data_files: - split: train path: "bdg-2_bear/*.arrow" - config_name: "bdg-2_fox" data_files: - split: train path: "bdg-2_fox/*.arrow" - config_name: "bdg-2_panther" data_files: - split: train path: "bdg-2_panther/*.arrow" - config_name: "bdg-2_rat" data_files: - split: train path: "bdg-2_rat/*.arrow" - config_name: "beijing_air_quality" data_files: - split: train path: "beijing_air_quality/*.arrow" - config_name: "bitcoin_with_missing" data_files: - split: train path: "bitcoin_with_missing/*.arrow" - config_name: "borealis" data_files: - split: train path: "borealis/*.arrow" - config_name: "borg_cluster_data_2011" data_files: - split: train path: "borg_cluster_data_2011/*.arrow" - config_name: "buildings_900k" data_files: - split: train path: "buildings_900k/*.arrow" - config_name: "bull" data_files: - split: train path: "bull/*.arrow" - config_name: "car_parts_with_missing" data_files: - split: train path: "car_parts_with_missing/*.arrow" - config_name: "cdc_fluview_ilinet" data_files: - split: train path: "cdc_fluview_ilinet/*.arrow" - config_name: "cdc_fluview_who_nrevss" data_files: - split: train path: "cdc_fluview_who_nrevss/*.arrow" - config_name: "china_air_quality" data_files: - split: train path: "china_air_quality/*.arrow" - config_name: "cif_2016_12" data_files: - split: train path: "cif_2016_12/*.arrow" - config_name: "cif_2016_6" data_files: - split: train path: "cif_2016_6/*.arrow" - config_name: "cmip6" data_files: - split: train path: "cmip6_*/*.arrow" - config_name: "cmip6_1850" data_files: - split: train path: "cmip6_1850/*.arrow" - config_name: "cmip6_1855" data_files: - split: train path: "cmip6_1855/*.arrow" - config_name: "cmip6_1860" data_files: - split: train path: "cmip6_1860/*.arrow" - config_name: "cmip6_1865" data_files: - split: train path: "cmip6_1865/*.arrow" - config_name: "cmip6_1870" data_files: - split: train path: "cmip6_1870/*.arrow" - config_name: "cmip6_1875" data_files: - split: train path: "cmip6_1875/*.arrow" - config_name: "cmip6_1880" data_files: - split: train path: "cmip6_1880/*.arrow" - config_name: "cmip6_1885" data_files: - split: train path: "cmip6_1885/*.arrow" - config_name: "cmip6_1890" data_files: - split: train path: "cmip6_1890/*.arrow" - config_name: "cmip6_1895" data_files: - split: train path: "cmip6_1895/*.arrow" - config_name: "cmip6_1900" data_files: - split: train path: "cmip6_1900/*.arrow" - config_name: "cmip6_1905" data_files: - split: train path: "cmip6_1905/*.arrow" - config_name: "cmip6_1910" data_files: - split: train path: "cmip6_1910/*.arrow" - config_name: "cmip6_1915" data_files: - split: train path: "cmip6_1915/*.arrow" - config_name: "cmip6_1920" data_files: - split: train path: "cmip6_1920/*.arrow" - config_name: "cmip6_1925" data_files: - split: train path: "cmip6_1925/*.arrow" - config_name: "cmip6_1930" data_files: - split: train path: "cmip6_1930/*.arrow" - config_name: "cmip6_1935" data_files: - split: train path: "cmip6_1935/*.arrow" - config_name: "cmip6_1940" data_files: - split: train path: "cmip6_1940/*.arrow" - config_name: "cmip6_1945" data_files: - split: train path: "cmip6_1945/*.arrow" - config_name: "cmip6_1950" data_files: - split: train path: "cmip6_1950/*.arrow" - config_name: "cmip6_1955" data_files: - split: train path: "cmip6_1955/*.arrow" - config_name: "cmip6_1960" data_files: - split: train path: "cmip6_1960/*.arrow" - config_name: "cmip6_1965" data_files: - split: train path: "cmip6_1965/*.arrow" - config_name: "cmip6_1970" data_files: - split: train path: "cmip6_1970/*.arrow" - config_name: "cmip6_1975" data_files: - split: train path: "cmip6_1975/*.arrow" - config_name: "cmip6_1980" data_files: - split: train path: "cmip6_1980/*.arrow" - config_name: "cmip6_1985" data_files: - split: train path: "cmip6_1985/*.arrow" - config_name: "cmip6_1990" data_files: - split: train path: "cmip6_1990/*.arrow" - config_name: "cmip6_1995" data_files: - split: train path: "cmip6_1995/*.arrow" - config_name: "cmip6_2000" data_files: - split: train path: "cmip6_2000/*.arrow" - config_name: "cmip6_2005" data_files: - split: train path: "cmip6_2005/*.arrow" - config_name: "cmip6_2010" data_files: - split: train path: "cmip6_2010/*.arrow" - config_name: "cockatoo" data_files: - split: train path: "cockatoo/*.arrow" - config_name: "covid19_energy" data_files: - split: train path: "covid19_energy/*.arrow" - config_name: "covid_deaths" data_files: - split: train path: "covid_deaths/*.arrow" - config_name: "covid_mobility" data_files: - split: train path: "covid_mobility/*.arrow" - config_name: "elecdemand" data_files: - split: train path: "elecdemand/*.arrow" - config_name: "elf" data_files: - split: train path: "elf/*.arrow" - config_name: "era5" data_files: - split: train path: "era5_*/*.arrow" - config_name: "era5_1989" data_files: - split: train path: "era5_1989/*.arrow" - config_name: "era5_1990" data_files: - split: train path: "era5_1990/*.arrow" - config_name: "era5_1991" data_files: - split: train path: "era5_1991/*.arrow" - config_name: "era5_1992" data_files: - split: train path: "era5_1992/*.arrow" - config_name: "era5_1993" data_files: - split: train path: "era5_1993/*.arrow" - config_name: "era5_1994" data_files: - split: train path: "era5_1994/*.arrow" - config_name: "era5_1995" data_files: - split: train path: "era5_1995/*.arrow" - config_name: "era5_1996" data_files: - split: train path: "era5_1996/*.arrow" - config_name: "era5_1997" data_files: - split: train path: "era5_1997/*.arrow" - config_name: "era5_1998" data_files: - split: train path: "era5_1998/*.arrow" - config_name: "era5_1999" data_files: - split: train path: "era5_1999/*.arrow" - config_name: "era5_2000" data_files: - split: train path: "era5_2000/*.arrow" - config_name: "era5_2001" data_files: - split: train path: "era5_2001/*.arrow" - config_name: "era5_2002" data_files: - split: train path: "era5_2002/*.arrow" - config_name: "era5_2003" data_files: - split: train path: "era5_2003/*.arrow" - config_name: "era5_2004" data_files: - split: train path: "era5_2004/*.arrow" - config_name: "era5_2005" data_files: - split: train path: "era5_2005/*.arrow" - config_name: "era5_2006" data_files: - split: train path: "era5_2006/*.arrow" - config_name: "era5_2007" data_files: - split: train path: "era5_2007/*.arrow" - config_name: "era5_2008" data_files: - split: train path: "era5_2008/*.arrow" - config_name: "era5_2009" data_files: - split: train path: "era5_2009/*.arrow" - config_name: "era5_2010" data_files: - split: train path: "era5_2010/*.arrow" - config_name: "era5_2011" data_files: - split: train path: "era5_2011/*.arrow" - config_name: "era5_2012" data_files: - split: train path: "era5_2012/*.arrow" - config_name: "era5_2013" data_files: - split: train path: "era5_2013/*.arrow" - config_name: "era5_2014" data_files: - split: train path: "era5_2014/*.arrow" - config_name: "era5_2015" data_files: - split: train path: "era5_2015/*.arrow" - config_name: "era5_2016" data_files: - split: train path: "era5_2016/*.arrow" - config_name: "era5_2017" data_files: - split: train path: "era5_2017/*.arrow" - config_name: "era5_2018" data_files: - split: train path: "era5_2018/*.arrow" - config_name: "extended_web_traffic_with_missing" data_files: - split: train path: "extended_web_traffic_with_missing/*.arrow" - config_name: "favorita_sales" data_files: - split: train path: "favorita_sales/*.arrow" - config_name: "favorita_transactions" data_files: - split: train path: "favorita_transactions/*.arrow" - config_name: "fred_md" data_files: - split: train path: "fred_md/*.arrow" - config_name: "gfc12_load" data_files: - split: train path: "gfc12_load/*.arrow" - config_name: "gfc14_load" data_files: - split: train path: "gfc14_load/*.arrow" - config_name: "gfc17_load" data_files: - split: train path: "gfc17_load/*.arrow" - config_name: "godaddy" data_files: - split: train path: "godaddy/*.arrow" - config_name: "hierarchical_sales" data_files: - split: train path: "hierarchical_sales/*.arrow" - config_name: "hog" data_files: - split: train path: "hog/*.arrow" - config_name: "hospital" data_files: - split: train path: "hospital/*.arrow" - config_name: "ideal" data_files: - split: train path: "ideal/*.arrow" - config_name: "kaggle_web_traffic_weekly" data_files: - split: train path: "kaggle_web_traffic_weekly/*.arrow" - config_name: "kdd2022" data_files: - split: train path: "kdd2022/*.arrow" - config_name: "kdd_cup_2018_with_missing" data_files: - split: train path: "kdd_cup_2018_with_missing/*.arrow" - config_name: "largest" data_files: - split: train path: "largest_*/*.arrow" - config_name: "largest_2017" data_files: - split: train path: "largest_2017/*.arrow" - config_name: "largest_2018" data_files: - split: train path: "largest_2018/*.arrow" - config_name: "largest_2019" data_files: - split: train path: "largest_2019/*.arrow" - config_name: "largest_2020" data_files: - split: train path: "largest_2020/*.arrow" - config_name: "largest_2021" data_files: - split: train path: "largest_2021/*.arrow" - config_name: "lcl" data_files: - split: train path: "lcl/*.arrow" - config_name: "london_smart_meters_with_missing" data_files: - split: train path: "london_smart_meters_with_missing/*.arrow" - config_name: "m1_monthly" data_files: - split: train path: "m1_monthly/*.arrow" - config_name: "m1_quarterly" data_files: - split: train path: "m1_quarterly/*.arrow" - config_name: "m1_yearly" data_files: - split: train path: "m1_yearly/*.arrow" - config_name: "m4_daily" data_files: - split: train path: "m4_daily/*.arrow" - config_name: "m4_hourly" data_files: - split: train path: "m4_hourly/*.arrow" - config_name: "m4_monthly" data_files: - split: train path: "m4_monthly/*.arrow" - config_name: "m4_quarterly" data_files: - split: train path: "m4_quarterly/*.arrow" - config_name: "m4_weekly" data_files: - split: train path: "m4_weekly/*.arrow" - config_name: "m4_yearly" data_files: - split: train path: "m4_yearly/*.arrow" - config_name: "m5" data_files: - split: train path: "m5/*.arrow" - config_name: "monash_m3_monthly" data_files: - split: train path: "monash_m3_monthly/*.arrow" - config_name: "monash_m3_other" data_files: - split: train path: "monash_m3_other/*.arrow" - config_name: "monash_m3_quarterly" data_files: - split: train path: "monash_m3_quarterly/*.arrow" - config_name: "monash_m3_yearly" data_files: - split: train path: "monash_m3_yearly/*.arrow" - config_name: "nn5_daily_with_missing" data_files: - split: train path: "nn5_daily_with_missing/*.arrow" - config_name: "nn5_weekly" data_files: - split: train path: "nn5_weekly/*.arrow" - config_name: "oikolab_weather" data_files: - split: train path: "oikolab_weather/*.arrow" - config_name: "pdb" data_files: - split: train path: "pdb/*.arrow" - config_name: "pedestrian_counts" data_files: - split: train path: "pedestrian_counts/*.arrow" - config_name: "project_tycho" data_files: - split: train path: "project_tycho/*.arrow" - config_name: "residential_load_power" data_files: - split: train path: "residential_load_power/*.arrow" - config_name: "residential_pv_power" data_files: - split: train path: "residential_pv_power/*.arrow" - config_name: "restaurant" data_files: - split: train path: "restaurant/*.arrow" - config_name: "rideshare_with_missing" data_files: - split: train path: "rideshare_with_missing/*.arrow" - config_name: "saugeenday" data_files: - split: train path: "saugeenday/*.arrow" - config_name: "sceaux" data_files: - split: train path: "sceaux/*.arrow" - config_name: "smart" data_files: - split: train path: "smart/*.arrow" - config_name: "solar_power" data_files: - split: train path: "solar_power/*.arrow" - config_name: "spain" data_files: - split: train path: "spain/*.arrow" - config_name: "subseasonal" data_files: - split: train path: "subseasonal/*.arrow" - config_name: "subseasonal_precip" data_files: - split: train path: "subseasonal_precip/*.arrow" - config_name: "sunspot_with_missing" data_files: - split: train path: "sunspot_with_missing/*.arrow" - config_name: "taxi_30min" data_files: - split: train path: "taxi_30min/*.arrow" - config_name: "temperature_rain_with_missing" data_files: - split: train path: "temperature_rain_with_missing/*.arrow" - config_name: "tourism_monthly" data_files: - split: train path: "tourism_monthly/*.arrow" - config_name: "tourism_quarterly" data_files: - split: train path: "tourism_quarterly/*.arrow" - config_name: "tourism_yearly" data_files: - split: train path: "tourism_yearly/*.arrow" - config_name: "traffic_hourly" data_files: - split: train path: "traffic_hourly/*.arrow" - config_name: "traffic_weekly" data_files: - split: train path: "traffic_weekly/*.arrow" - config_name: "uber_tlc_daily" data_files: - split: train path: "uber_tlc_daily/*.arrow" - config_name: "uber_tlc_hourly" data_files: - split: train path: "uber_tlc_hourly/*.arrow" - config_name: "us_births" data_files: - split: train path: "us_births/*.arrow" - config_name: "vehicle_trips_with_missing" data_files: - split: train path: "vehicle_trips_with_missing/*.arrow" - config_name: "weather" data_files: - split: train path: "weather/*.arrow" - config_name: "wiki-rolling_nips" data_files: - split: train path: "wiki-rolling_nips/*.arrow" - config_name: "wind_farms_with_missing" data_files: - split: train path: "wind_farms_with_missing/*.arrow" - config_name: "wind_power" data_files: - split: train path: "wind_power/*.arrow" --- # LOTSA Data The Large-scale Open Time Series Archive (LOTSA) is a collection of open time series datasets for time series forecasting. It was collected for the purpose of pre-training Large Time Series Models. See the [paper](https://arxiv.org/abs/2402.02592) and [codebase](https://github.com/SalesforceAIResearch/uni2ts) for more information. ## Citation <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> If you're using LOTSA data in your research or applications, please cite it using this BibTeX: **BibTeX:** ```markdown @article{woo2024unified, title={Unified Training of Universal Time Series Forecasting Transformers}, author={Woo, Gerald and Liu, Chenghao and Kumar, Akshat and Xiong, Caiming and Savarese, Silvio and Sahoo, Doyen}, journal={arXiv preprint arXiv:2402.02592}, year={2024} } ``` ## Ethical Considerations This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.

orionweller/reddit_mds_incremental

orionweller

--- dataset_info: features: [] splits: - name: creation num_bytes: 0 num_examples: 0 download_size: 324 dataset_size: 0 configs: - config_name: default data_files: - split: creation path: data/creation-* ---

livecodebench/code_generation_lite

livecodebench

--- license: cc tags: - code - code generation pretty_name: LiveCodeBench size_categories: - n<1K --- ## LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code <p align="center"> <a href="https://livecodebench.github.io/">🏠 Home Page</a> • <a href="https://github.com/LiveCodeBench/LiveCodeBench">💻 GitHub Repository </a> • <a href="https://livecodebench.github.io/leaderboard.html">🏆 Leaderboard</a> • <a href="https://arxiv.org/abs/2403.07974">📄 Paper </a> </p>  ## Change Log Since LiveCodeBench is a continuously updated benchmark, we provide different versions of the dataset. Particularly, we provide the following versions of the dataset: - `release_v1`: The initial release of the dataset with problems released between May 2023 and Mar 2024 containing 400 problems. - `release_v2`: The updated release of the dataset with problems released between May 2023 and May 2024 containing 511 problems. - `release_v3`: The updated release of the dataset with problems released between May 2023 and Jul 2024 containing 612 problems. - `release_v4`: The updated release of the dataset with problems released between May 2023 and Sep 2024 containing 713 problems. - `release_v5`: The updated release of the dataset with problems released between May 2023 and Jan 2025 containing 880 problems. You can use the `version_tag` argument to load the desired version of the dataset. Additionally, you can use version tags like `v1`, `v2`, `v1_v3`, `v4_v5` to get the problems released in a specific version. ## Dataset Description LiveCodeBench is a "live" updating benchmark for holistically evaluating code related capabilities of LLMs. Particularly, it evaluates LLMs across a range of capabilties including code generation, self-repair, test output prediction, and code execution. This is the code generation scenario of LiveCodeBench. It is also used for evaluating self-repair using test case feedback. LiveCodeBench problems are collected from competition programming websites with particular focus on maintaining problem quality, test case quality, and problem difficulty diversity. This scenario currently hosts over 500 problems from LeetCode, AtCoder, and Codeforces. Each problem instance is consists of problem description, input/output examples, and hidden test cases. Additionally, every problem is tagged with its difficulty level and release date which allows measuring model performance across different time windows. The goal is to generate a correct and efficient solution for each problem instance. The initial code_generation dataset included larger number of test cases which leads to substantially large dataset size. This (lite) version has pruned and sampled tests while trying to ensure similar performances with the original dataset. Going forward, livecodebench will be using this lite version for code generation evaluations. ## Usage You can use the dataset by loading it from the Hugging Face datasets library. Additionally, the version tag "release_v1" is used to specify the (temporal) version of the dataset. "v1" corresponds to the initial release of the dataset and "release_v2" is the second version. ```python from datasets import load_dataset lcb_codegen = load_dataset("livecodebench/code_generation_lite", version_tag="release_v2") ```

openai/MMMLU

openai

--- task_categories: - question-answering configs: - config_name: default data_files: - split: test path: test/*.csv - config_name: AR_XY data_files: - split: test path: test/mmlu_AR-XY.csv - config_name: BN_BD data_files: - split: test path: test/mmlu_BN-BD.csv - config_name: DE_DE data_files: - split: test path: test/mmlu_DE-DE.csv - config_name: ES_LA data_files: - split: test path: test/mmlu_ES-LA.csv - config_name: FR_FR data_files: - split: test path: test/mmlu_FR-FR.csv - config_name: HI_IN data_files: - split: test path: test/mmlu_HI-IN.csv - config_name: ID_ID data_files: - split: test path: test/mmlu_ID-ID.csv - config_name: IT_IT data_files: - split: test path: test/mmlu_IT-IT.csv - config_name: JA_JP data_files: - split: test path: test/mmlu_JA-JP.csv - config_name: KO_KR data_files: - split: test path: test/mmlu_KO-KR.csv - config_name: PT_BR data_files: - split: test path: test/mmlu_PT-BR.csv - config_name: SW_KE data_files: - split: test path: test/mmlu_SW-KE.csv - config_name: YO_NG data_files: - split: test path: test/mmlu_YO-NG.csv - config_name: ZH_CN data_files: - split: test path: test/mmlu_ZH-CN.csv language: - ar - bn - de - es - fr - hi - id - it - ja - ko - pt - sw - yo - zh license: mit --- # Multilingual Massive Multitask Language Understanding (MMMLU) The MMLU is a widely recognized benchmark of general knowledge attained by AI models. It covers a broad range of topics from 57 different categories, covering elementary-level knowledge up to advanced professional subjects like law, physics, history, and computer science. We translated the MMLU’s test set into 14 languages using professional human translators. Relying on human translators for this evaluation increases confidence in the accuracy of the translations, especially for low-resource languages like Yoruba. We are publishing the professional human translations and the code we use to run the evaluations. This effort reflects our commitment to improving the multilingual capabilities of AI models, ensuring they perform accurately across languages, particularly for underrepresented communities. By prioritizing high-quality translations, we aim to make AI technology more inclusive and effective for users worldwide. ## Locales MMMLU contains the MMLU test set translated into the following locales: * AR_XY (Arabic) * BN_BD (Bengali) * DE_DE (German) * ES_LA (Spanish) * FR_FR (French) * HI_IN (Hindi) * ID_ID (Indonesian) * IT_IT (Italian) * JA_JP (Japanese) * KO_KR (Korean) * PT_BR (Brazilian Portuguese) * SW_KE (Swahili) * YO_NG (Yoruba) * ZH_CN (Simplified Chinese) ## Sources Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., & Steinhardt, J. (2021). [*Measuring Massive Multitask Language Understanding*](https://arxiv.org/abs/2009.03300). [OpenAI Simple Evals GitHub Repository](https://github.com/openai/simple-evals)

lmms-lab/LLaVA-Video-178K

lmms-lab

--- configs: - config_name: 0_30_s_academic_v0_1 data_files: - split: caption path: 0_30_s_academic_v0_1/*cap*.json - split: open_ended path: 0_30_s_academic_v0_1/*oe*.json - split: multi_choice path: 0_30_s_academic_v0_1/*mc*.json - config_name: 0_30_s_youtube_v0_1 data_files: - split: caption path: 0_30_s_youtube_v0_1/*cap*.json - split: open_ended path: 0_30_s_youtube_v0_1/*oe*.json - split: multi_choice path: 0_30_s_youtube_v0_1/*mc*.json - config_name: 0_30_s_activitynet data_files: - split: open_ended path: 0_30_s_activitynet/*oe*.json - config_name: 0_30_s_perceptiontest data_files: - split: multi_choice path: 0_30_s_perceptiontest/*mc*.json - config_name: 0_30_s_nextqa data_files: - split: open_ended path: 0_30_s_nextqa/*oe*.json - split: multi_choice path: 0_30_s_nextqa/*mc*.json - config_name: 30_60_s_academic_v0_1 data_files: - split: caption path: 30_60_s_academic_v0_1/*cap*.json - split: open_ended path: 30_60_s_academic_v0_1/*oe*.json - split: multi_choice path: 30_60_s_academic_v0_1/*mc*.json - config_name: 30_60_s_youtube_v0_1 data_files: - split: caption path: 30_60_s_youtube_v0_1/*cap*.json - split: open_ended path: 30_60_s_youtube_v0_1/*oe*.json - split: multi_choice path: 30_60_s_youtube_v0_1/*mc*.json - config_name: 30_60_s_activitynet data_files: - split: open_ended path: 30_60_s_activitynet/*oe*.json - config_name: 30_60_s_perceptiontest data_files: - split: multi_choice path: 30_60_s_perceptiontest/*mc*.json - config_name: 30_60_s_nextqa data_files: - split: open_ended path: 30_60_s_nextqa/*oe*.json - split: multi_choice path: 30_60_s_nextqa/*mc*.json - config_name: 1_2_m_youtube_v0_1 data_files: - split: caption path: 1_2_m_youtube_v0_1/*cap*.json - split: open_ended path: 1_2_m_youtube_v0_1/*oe*.json - split: multi_choice path: 1_2_m_youtube_v0_1/*mc*.json - config_name: 1_2_m_academic_v0_1 data_files: - split: caption path: 1_2_m_academic_v0_1/*cap*.json - split: open_ended path: 1_2_m_academic_v0_1/*oe*.json - split: multi_choice path: 1_2_m_academic_v0_1/*mc*.json - config_name: 1_2_m_activitynet data_files: - split: open_ended path: 1_2_m_activitynet/*oe*.json - config_name: 1_2_m_nextqa data_files: - split: open_ended path: 1_2_m_nextqa/*oe*.json - split: multi_choice path: 1_2_m_nextqa/*mc*.json - config_name: 2_3_m_youtube_v0_1 data_files: - split: caption path: 2_3_m_youtube_v0_1/*cap*.json - split: open_ended path: 2_3_m_youtube_v0_1/*oe*.json - split: multi_choice path: 2_3_m_youtube_v0_1/*mc*.json - config_name: 2_3_m_academic_v0_1 data_files: - split: caption path: 2_3_m_academic_v0_1/*cap*.json - split: open_ended path: 2_3_m_academic_v0_1/*oe*.json - split: multi_choice path: 2_3_m_academic_v0_1/*mc*.json - config_name: 2_3_m_activitynet data_files: - split: open_ended path: 2_3_m_activitynet/*oe*.json - config_name: 2_3_m_nextqa data_files: - split: open_ended path: 2_3_m_nextqa/*oe*.json - split: multi_choice path: 2_3_m_nextqa/*mc*.json - config_name: llava_hound data_files: - split: open_ended path: llava_hound/sharegptvideo_qa_255k_processed.json language: - en task_categories: - visual-question-answering - video-text-to-text tags: - video --- # Dataset Card for LLaVA-Video-178K ## Dataset Description - **Curated by:** Yuanhan Zhang, Jinming Wu, Wei Li - **Language(s) (NLP):** English, Chinese - **License:** Apache License 2.0 ## Uses This dataset is used for the training of the LLaVA-Video model. We only allow the use of this dataset for academic research and education purpose. For OpenAI GPT-4 generated data, we recommend the users to check the [OpenAI Usage Policy](https://openai.com/policies/usage-policies/). ### Data Sources For the training of LLaVA-Video, we utilized video-language data from five primary sources: - **LLaVA-Video-178K**: This dataset includes **178,510** caption entries, 960,792 open-ended QA (question and answer) items, and 196,198 multiple-choice QA items. These data were newly annotated for this project. - We include this dataset in this repository: LLaVA-Video-178K/XXX_academic_v0_1 and LLaVA-Video-178K/XXX_youtube_v0_1. - **NeXT-QA**: Comprises 17,090 open-ended QA items and 17,024 multiple-choice QA items. - We include this dataset in this repository: LLaVA-Video-178K/XXX_nextqa. - **ActivityNetQA**: Includes 23,530 open-ended QA items, - We include this dataset in this repository: LLaVA-Video-178K/XXX_activitynetqa. - **PerceptionTest**: Includes 1,803 open-ended QA items. - We include this dataset in this repository: LLaVA-Video-178K/XXX_perceptiontest. - **LLaVA-Hound**: Contains 240,000 open-ended QA items and 15,000 caption entries. - The video data and annotations are available at the following URLs: - Video data: [train_300k](https://huggingface.co/datasets/ShareGPTVideo/train_video_and_instruction/tree/main/train_300k) - Annotation data: LLaVA-Video-178K/llava_hound - loading function is specified here: [function](https://github.com/LLaVA-VL/LLaVA-NeXT/blob/7125e3654d88063cb467ed242db76f1e2b184d4c/llava/train/train.py#L1162) The **LLaVA-Video-178K** dataset is the only contribution from this repository; we provide additional datasets for reproducing LLaVA-Video. - **Project Page:** [Project Page](https://llava-vl.github.io/blog/2024-09-30-llava-video/). - **Paper**: For more details, please check our [paper](https://arxiv.org/abs/2410.02713) ### Annotation Pipeline The following directories are provided for generating captions and QA data: - **Captions**: `LLaVA-Video-178K/gpt4o_caption_prompt` - **QA**: `LLaVA-Video-178K/gpt4o_qa_prompt` ### The subset used in the LLaVA-OneVision We have included captions and open-ended questions in the [0_30_s_academic_v0_1 split](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K/tree/main/0_30_s_academic_v0_1), along with 240,000 open-ended QA items and 15,000 caption entries, as part of the video data in LLaVA-Hound for LLaVA-OneVision. - [**0_30_s_academic_v0_1 caption**](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K/blob/main/0_30_s_academic_v0_1/0_30_s_academic_v0_1_cap_processed.json) - [**0_30_s_academic_v0_1 open-ended QA**](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K/blob/main/0_30_s_academic_v0_1/0_30_s_academic_v0_1_cap_processed.json) - **LLaVA-Hound**: Same as above. ## Citation ```bibtex @misc{zhang2024videoinstructiontuningsynthetic, title={Video Instruction Tuning With Synthetic Data}, author={Yuanhan Zhang and Jinming Wu and Wei Li and Bo Li and Zejun Ma and Ziwei Liu and Chunyuan Li}, year={2024}, eprint={2410.02713}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2410.02713}, } ``` ## Dataset Card Contact [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/) [Jinming Wu](https://scholar.google.com/citations?user=eh-XJIoAAAAJ&hl=zh-CN) [Wei Li](https://scholar.google.com/citations?user=q8ZrKVIAAAAJ&hl=zh-CN)

philschmid/llama2-german-corpus-tokenized-llama-chunk-4096

philschmid

--- dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: labels sequence: int64 splits: - name: train num_bytes: 1190392538880 num_examples: 20753008 download_size: 307400657843 dataset_size: 1190392538880 --- # Dataset Card for "llama2-german-corpus-tokenized-llama-chunk-4096" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

bigbio/pubmed_qa

bigbio

--- language: - en bigbio_language: - English license: mit multilinguality: monolingual bigbio_license_shortname: MIT pretty_name: PubMedQA homepage: https://github.com/pubmedqa/pubmedqa bigbio_pubmed: True bigbio_public: True bigbio_tasks: - QUESTION_ANSWERING --- # Dataset Card for PubMedQA ## Dataset Description - **Homepage:** https://github.com/pubmedqa/pubmedqa - **Pubmed:** True - **Public:** True - **Tasks:** QA PubMedQA is a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research biomedical questions with yes/no/maybe using the corresponding abstracts. PubMedQA has 1k expert-annotated (PQA-L), 61.2k unlabeled (PQA-U) and 211.3k artificially generated QA instances (PQA-A). Each PubMedQA instance is composed of: (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding PubMed abstract without its conclusion, (3) a long answer, which is the conclusion of the abstract and, presumably, answers the research question, and (4) a yes/no/maybe answer which summarizes the conclusion. PubMedQA is the first QA dataset where reasoning over biomedical research texts, especially their quantitative contents, is required to answer the questions. PubMedQA datasets comprise of 3 different subsets: (1) PubMedQA Labeled (PQA-L): A labeled PubMedQA subset comprises of 1k manually annotated yes/no/maybe QA data collected from PubMed articles. (2) PubMedQA Artificial (PQA-A): An artificially labelled PubMedQA subset comprises of 211.3k PubMed articles with automatically generated questions from the statement titles and yes/no answer labels generated using a simple heuristic. (3) PubMedQA Unlabeled (PQA-U): An unlabeled PubMedQA subset comprises of 61.2k context-question pairs data collected from PubMed articles. ## Citation Information ``` @inproceedings{jin2019pubmedqa, title={PubMedQA: A Dataset for Biomedical Research Question Answering}, author={Jin, Qiao and Dhingra, Bhuwan and Liu, Zhengping and Cohen, William and Lu, Xinghua}, booktitle={Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, pages={2567--2577}, year={2019} } ```

AmazonScience/MultilingualMultiModalClassification

AmazonScience

--- license: cc-by-4.0 dataset_info: - config_name: multieurlex-doc-bg features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 407278322 num_examples: 15979 - name: validation num_bytes: 121021498 num_examples: 4997 - name: test num_bytes: 126194699 num_examples: 4988 download_size: 94161088 dataset_size: 654494519 - config_name: multieurlex-doc-cs features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 465064539 num_examples: 23056 - name: validation num_bytes: 98206202 num_examples: 4997 - name: test num_bytes: 101905013 num_examples: 4988 download_size: 103341160 dataset_size: 665175754 - config_name: multieurlex-doc-da features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1137431321 num_examples: 54806 - name: validation num_bytes: 100630592 num_examples: 4997 - name: test num_bytes: 103660755 num_examples: 4988 download_size: 211774968 dataset_size: 1341722668 - config_name: multieurlex-doc-de features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1156790099 num_examples: 54804 - name: test num_bytes: 108731388 num_examples: 4988 - name: validation num_bytes: 105635067 num_examples: 4997 download_size: 214358454 dataset_size: 1371156554 - config_name: multieurlex-doc-el features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1412326683 num_examples: 54828 - name: validation num_bytes: 127450631 num_examples: 4997 - name: test num_bytes: 132083962 num_examples: 4988 download_size: 249838066 dataset_size: 1671861276 - config_name: multieurlex-doc-en features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1208998381 num_examples: 54808 - name: test num_bytes: 110325080 num_examples: 4988 - name: validation num_bytes: 106866095 num_examples: 4997 download_size: 223853363 dataset_size: 1426189556 - config_name: multieurlex-doc-es features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1354212928 num_examples: 52621 - name: test num_bytes: 128661948 num_examples: 4988 - name: validation num_bytes: 124535827 num_examples: 4997 download_size: 254828898 dataset_size: 1607410703 - config_name: multieurlex-doc-et features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 385076032 num_examples: 22986 - name: validation num_bytes: 82795960 num_examples: 4997 - name: test num_bytes: 85548380 num_examples: 4988 download_size: 87523878 dataset_size: 553420372 - config_name: multieurlex-doc-fi features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 746551995 num_examples: 42362 - name: validation num_bytes: 88644474 num_examples: 4997 - name: test num_bytes: 90495504 num_examples: 4988 download_size: 144867468 dataset_size: 925691973 - config_name: multieurlex-doc-fr features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1308833036 num_examples: 54804 - name: validation num_bytes: 117528920 num_examples: 4997 - name: test num_bytes: 122076609 num_examples: 4988 download_size: 244074331 dataset_size: 1548438565 - config_name: multieurlex-doc-hr features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 166426724 num_examples: 7944 - name: validation num_bytes: 52267708 num_examples: 2499 - name: test num_bytes: 99712738 num_examples: 4988 download_size: 49985102 dataset_size: 318407170 - config_name: multieurlex-doc-hu features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 430043841 num_examples: 22542 - name: validation num_bytes: 94622333 num_examples: 4997 - name: test num_bytes: 97747785 num_examples: 4988 download_size: 97614905 dataset_size: 622413959 - config_name: multieurlex-doc-it features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1249061937 num_examples: 54805 - name: validation num_bytes: 110908837 num_examples: 4997 - name: test num_bytes: 114867681 num_examples: 4987 download_size: 231926930 dataset_size: 1474838455 - config_name: multieurlex-doc-nl features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1286183580 num_examples: 54803 - name: validation num_bytes: 112858254 num_examples: 4997 - name: test num_bytes: 116992911 num_examples: 4988 download_size: 237826260 dataset_size: 1516034745 - config_name: multieurlex-doc-pl features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 471614388 num_examples: 23063 - name: validation num_bytes: 101196012 num_examples: 4997 - name: test num_bytes: 104384366 num_examples: 4988 download_size: 104236091 dataset_size: 677194766 - config_name: multieurlex-doc-pt features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 1269347766 num_examples: 52205 - name: validation num_bytes: 117194055 num_examples: 4997 - name: test num_bytes: 120747746 num_examples: 4988 download_size: 238776517 dataset_size: 1507289567 - config_name: multieurlex-doc-ro features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 359230898 num_examples: 15914 - name: validation num_bytes: 107876284 num_examples: 4997 - name: test num_bytes: 112291364 num_examples: 4988 download_size: 89545760 dataset_size: 579398546 - config_name: multieurlex-doc-sv features: - name: filename dtype: string - name: words sequence: sequence: string - name: boxes sequence: sequence: sequence: int64 splits: - name: train num_bytes: 867755140 num_examples: 42356 - name: validation num_bytes: 101193984 num_examples: 4997 - name: test num_bytes: 103453976 num_examples: 4988 download_size: 166948914 dataset_size: 1072403100 - config_name: wiki-doc-ar-img features: - name: image dtype: image - name: label dtype: class_label: names: '0': Earthquake '1': SolarEclipse '2': MusicFestival '3': MilitaryConflict '4': FilmFestival '5': Convention '6': FootballMatch '7': OlympicEvent '8': GrandPrix '9': GolfTournament '10': WomensTennisAssociationTournament '11': TennisTournament '12': SoccerTournament '13': WrestlingEvent '14': HorseRace '15': CyclingRace '16': MixedMartialArtsEvent '17': Election '18': SoccerClubSeason '19': NationalFootballLeagueSeason '20': NCAATeamSeason '21': BaseballSeason '22': VideoGame '23': BiologicalDatabase '24': EurovisionSongContestEntry '25': Album '26': Musical '27': ClassicalMusicComposition '28': ArtistDiscography '29': Single '30': Poem '31': Magazine '32': Newspaper '33': AcademicJournal '34': Play '35': Manga '36': ComicStrip '37': Anime '38': HollywoodCartoon '39': MusicGenre '40': Grape '41': Conifer '42': Fern '43': Moss '44': GreenAlga '45': CultivatedVariety '46': Cycad '47': Arachnid '48': Fish '49': Insect '50': Reptile '51': Mollusca '52': Bird '53': Amphibian '54': RaceHorse '55': Crustacean '56': Fungus '57': Lighthouse '58': Theatre '59': RollerCoaster '60': Airport '61': RailwayStation '62': Road '63': RailwayLine '64': Bridge '65': RoadTunnel '66': Dam '67': CricketGround '68': Stadium '69': Racecourse '70': GolfCourse '71': Prison '72': Hospital '73': Museum '74': Hotel '75': Library '76': Restaurant '77': ShoppingMall '78': HistoricBuilding '79': Castle '80': Volcano '81': MountainPass '82': Glacier '83': Canal '84': River '85': Lake '86': Mountain '87': Cave '88': MountainRange '89': Galaxy '90': ArtificialSatellite '91': Planet '92': Town '93': Village '94': Diocese '95': AutomobileEngine '96': SupremeCourtOfTheUnitedStatesCase '97': MilitaryPerson '98': Religious '99': Engineer '100': BusinessPerson '101': SportsTeamMember '102': SoccerManager '103': Chef '104': Philosopher '105': CollegeCoach '106': ScreenWriter '107': Historian '108': Poet '109': President '110': PrimeMinister '111': Congressman '112': Senator '113': Mayor '114': MemberOfParliament '115': Governor '116': Monarch '117': PlayboyPlaymate '118': Cardinal '119': Saint '120': Pope '121': ChristianBishop '122': BeautyQueen '123': RadioHost '124': HandballPlayer '125': Cricketer '126': Jockey '127': SumoWrestler '128': AmericanFootballPlayer '129': LacrossePlayer '130': TennisPlayer '131': AmateurBoxer '132': SoccerPlayer '133': Rower '134': TableTennisPlayer '135': BeachVolleyballPlayer '136': SpeedwayRider '137': FormulaOneRacer '138': NascarDriver '139': Swimmer '140': IceHockeyPlayer '141': FigureSkater '142': Skater '143': Curler '144': Skier '145': GolfPlayer '146': SquashPlayer '147': PokerPlayer '148': BadmintonPlayer '149': ChessPlayer '150': RugbyPlayer '151': DartsPlayer '152': NetballPlayer '153': MartialArtist '154': Gymnast '155': Canoeist '156': GaelicGamesPlayer '157': HorseRider '158': BaseballPlayer '159': Cyclist '160': Bodybuilder '161': AustralianRulesFootballPlayer '162': BasketballPlayer '163': Ambassador '164': Baronet '165': Model '166': Architect '167': Judge '168': Economist '169': Journalist '170': Painter '171': Comedian '172': ComicsCreator '173': ClassicalMusicArtist '174': FashionDesigner '175': AdultActor '176': VoiceActor '177': Photographer '178': HorseTrainer '179': Entomologist '180': Medician '181': SoapCharacter '182': AnimangaCharacter '183': MythologicalFigure '184': Noble '185': Astronaut '186': OfficeHolder '187': PublicTransitSystem '188': BusCompany '189': LawFirm '190': Winery '191': RecordLabel '192': Brewery '193': Airline '194': Publisher '195': Bank '196': PoliticalParty '197': Legislature '198': Band '199': BasketballLeague '200': SoccerLeague '201': IceHockeyLeague '202': BaseballLeague '203': RugbyLeague '204': MilitaryUnit '205': University '206': School '207': CyclingTeam '208': CanadianFootballTeam '209': BasketballTeam '210': AustralianFootballTeam '211': HockeyTeam '212': HandballTeam '213': CricketTeam '214': RugbyClub '215': TradeUnion '216': RadioStation '217': BroadcastNetwork '218': TelevisionStation splits: - name: train num_bytes: 7919491304.875 num_examples: 8129 - name: test num_bytes: 1691686089.125 num_examples: 1743 - name: validation num_bytes: 1701166069.25 num_examples: 1742 download_size: 11184835705 dataset_size: 11312343463.25 - config_name: wiki-doc-ar-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 8062791605.746 num_examples: 8129 - name: test num_bytes: 1722071386.382 num_examples: 1743 - name: validation num_bytes: 1731948280.766 num_examples: 1742 download_size: 11226133595 dataset_size: 11516811272.894001 - config_name: wiki-doc-de-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 59980253508.125 num_examples: 41047 - name: validation num_bytes: 12842370238.5 num_examples: 8796 - name: test num_bytes: 12835845039.5 num_examples: 8796 download_size: 84274708249 dataset_size: 85658468786.125 - config_name: wiki-doc-en-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 201861788293.75 num_examples: 152506 - name: validation num_bytes: 43199951001.0 num_examples: 32680 - name: test num_bytes: 43177176523.0 num_examples: 32680 download_size: 282546982586 dataset_size: 288238915817.75 - config_name: wiki-doc-es-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 58485685843.875 num_examples: 42713 - name: validation num_bytes: 12550991282.569 num_examples: 9153 - name: test num_bytes: 12546829230.442 num_examples: 9154 download_size: 82063829353 dataset_size: 83583506356.886 - config_name: wiki-doc-fr-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 40498485460.875 num_examples: 33329 - name: validation num_bytes: 8641683528.108 num_examples: 7142 - name: test num_bytes: 8649896334.108 num_examples: 7142 download_size: 56468886228 dataset_size: 57790065323.091 - config_name: wiki-doc-it-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 25293800981.25 num_examples: 20166 - name: validation num_bytes: 5433600428.554 num_examples: 4321 - name: test num_bytes: 5411100552.106 num_examples: 4322 download_size: 35441755215 dataset_size: 36138501961.91 - config_name: wiki-doc-ja-img features: - name: image dtype: image - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 30506965411.75 num_examples: 23250 - name: test num_bytes: 6540291049.322 num_examples: 4982 - name: validation num_bytes: 6513584731.193 num_examples: 4983 download_size: 43248429810 dataset_size: 43560841192.265 - config_name: wiki-doc-ja-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 30650799906.25 num_examples: 23254 - name: validation num_bytes: 6543258936.193 num_examples: 4983 - name: test num_bytes: 6570176552.322 num_examples: 4982 download_size: 43344042661 dataset_size: 43764235394.765 - config_name: wiki-doc-pt-img features: - name: image dtype: image - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 21744787468.0 num_examples: 20168 - name: test num_bytes: 4702448837.106 num_examples: 4322 - name: validation num_bytes: 4646765273.106 num_examples: 4322 download_size: 30769070664 dataset_size: 31094001578.211998 - config_name: wiki-doc-pt-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 22164275072.0 num_examples: 20168 - name: validation num_bytes: 4735717368.106 num_examples: 4322 - name: test num_bytes: 4792666148.106 num_examples: 4322 download_size: 30891429558 dataset_size: 31692658588.211998 - config_name: wiki-doc-pt-merged-v2 features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 22164275065.16 num_examples: 20168 - name: validation num_bytes: 4735717370.818 num_examples: 4322 - name: test num_bytes: 4792666150.818 num_examples: 4322 download_size: 30891429558 dataset_size: 31692658586.796 - config_name: wiki-doc-zh-img features: - name: image dtype: image - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 30248140475.625 num_examples: 23099 - name: test num_bytes: 6471322916.25 num_examples: 4950 - name: validation num_bytes: 6507120137.25 num_examples: 4950 download_size: 42958276266 dataset_size: 43226583529.125 - config_name: wiki-doc-zh-merged features: - name: image dtype: image - name: filename dtype: string - name: words sequence: string - name: ocr_bboxes sequence: sequence: int64 - name: label dtype: class_label: names: '0': AcademicJournal '1': AdultActor '2': Album '3': AmateurBoxer '4': Ambassador '5': AmericanFootballPlayer '6': Amphibian '7': AnimangaCharacter '8': Anime '9': Arachnid '10': Baronet '11': BasketballTeam '12': BeautyQueen '13': BroadcastNetwork '14': BusCompany '15': BusinessPerson '16': CanadianFootballTeam '17': Canal '18': Cardinal '19': Cave '20': ChristianBishop '21': ClassicalMusicArtist '22': ClassicalMusicComposition '23': CollegeCoach '24': Comedian '25': ComicsCreator '26': Congressman '27': Conifer '28': Convention '29': Cricketer '30': Crustacean '31': CultivatedVariety '32': Cycad '33': Dam '34': Economist '35': Engineer '36': Entomologist '37': EurovisionSongContestEntry '38': Fern '39': FilmFestival '40': Fish '41': FootballMatch '42': Glacier '43': GolfTournament '44': Governor '45': Gymnast '46': Historian '47': IceHockeyLeague '48': Insect '49': Journalist '50': Judge '51': Lighthouse '52': Magazine '53': Mayor '54': Medician '55': MemberOfParliament '56': MilitaryPerson '57': Model '58': Mollusca '59': Monarch '60': Moss '61': Mountain '62': MountainPass '63': MountainRange '64': MusicFestival '65': Musical '66': MythologicalFigure '67': Newspaper '68': Noble '69': OfficeHolder '70': Other '71': Philosopher '72': Photographer '73': PlayboyPlaymate '74': Poem '75': Poet '76': Pope '77': President '78': PrimeMinister '79': PublicTransitSystem '80': Racecourse '81': RadioHost '82': RadioStation '83': Religious '84': Reptile '85': Restaurant '86': Road '87': RoadTunnel '88': RollerCoaster '89': RugbyClub '90': RugbyLeague '91': Saint '92': School '93': ScreenWriter '94': Senator '95': ShoppingMall '96': Skater '97': SoccerLeague '98': SoccerManager '99': SoccerPlayer '100': SoccerTournament '101': SportsTeamMember '102': SumoWrestler '103': TelevisionStation '104': TennisTournament '105': TradeUnion '106': University '107': Village '108': VoiceActor '109': Volcano '110': WrestlingEvent splits: - name: train num_bytes: 30382212749.625 num_examples: 23099 - name: test num_bytes: 6499933446.25 num_examples: 4950 - name: validation num_bytes: 6536010774.25 num_examples: 4950 download_size: 43027961181 dataset_size: 43418156970.125 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* - config_name: multieurlex-doc-bg data_files: - split: train path: multieurlex-doc-bg/train-* - split: validation path: multieurlex-doc-bg/validation-* - split: test path: multieurlex-doc-bg/test-* - config_name: multieurlex-doc-cs data_files: - split: train path: multieurlex-doc-cs/train-* - split: validation path: multieurlex-doc-cs/validation-* - split: test path: multieurlex-doc-cs/test-* - config_name: multieurlex-doc-da data_files: - split: train path: multieurlex-doc-da/train-* - split: validation path: multieurlex-doc-da/validation-* - split: test path: multieurlex-doc-da/test-* - config_name: multieurlex-doc-de data_files: - split: train path: multieurlex-doc-de/train-* - split: test path: multieurlex-doc-de/test-* - split: validation path: multieurlex-doc-de/validation-* - config_name: multieurlex-doc-el data_files: - split: train path: multieurlex-doc-el/train-* - split: validation path: multieurlex-doc-el/validation-* - split: test path: multieurlex-doc-el/test-* - config_name: multieurlex-doc-en data_files: - split: train path: multieurlex-doc-en/train-* - split: test path: multieurlex-doc-en/test-* - split: validation path: multieurlex-doc-en/validation-* - config_name: multieurlex-doc-es data_files: - split: train path: multieurlex-doc-es/train-* - split: test path: multieurlex-doc-es/test-* - split: validation path: multieurlex-doc-es/validation-* - config_name: multieurlex-doc-et data_files: - split: train path: multieurlex-doc-et/train-* - split: validation path: multieurlex-doc-et/validation-* - split: test path: multieurlex-doc-et/test-* - config_name: multieurlex-doc-fi data_files: - split: train path: multieurlex-doc-fi/train-* - split: validation path: multieurlex-doc-fi/validation-* - split: test path: multieurlex-doc-fi/test-* - config_name: multieurlex-doc-fr data_files: - split: train path: multieurlex-doc-fr/train-* - split: validation path: multieurlex-doc-fr/validation-* - split: test path: multieurlex-doc-fr/test-* - config_name: multieurlex-doc-hr data_files: - split: train path: multieurlex-doc-hr/train-* - split: validation path: multieurlex-doc-hr/validation-* - split: test path: multieurlex-doc-hr/test-* - config_name: multieurlex-doc-hu data_files: - split: train path: multieurlex-doc-hu/train-* - split: validation path: multieurlex-doc-hu/validation-* - split: test path: multieurlex-doc-hu/test-* - config_name: multieurlex-doc-it data_files: - split: train path: multieurlex-doc-it/train-* - split: validation path: multieurlex-doc-it/validation-* - split: test path: multieurlex-doc-it/test-* - config_name: multieurlex-doc-nl data_files: - split: train path: multieurlex-doc-nl/train-* - split: validation path: multieurlex-doc-nl/validation-* - split: test path: multieurlex-doc-nl/test-* - config_name: multieurlex-doc-pl data_files: - split: train path: multieurlex-doc-pl/train-* - split: validation path: multieurlex-doc-pl/validation-* - split: test path: multieurlex-doc-pl/test-* - config_name: multieurlex-doc-pt data_files: - split: train path: multieurlex-doc-pt/train-* - split: validation path: multieurlex-doc-pt/validation-* - split: test path: multieurlex-doc-pt/test-* - config_name: multieurlex-doc-ro data_files: - split: train path: multieurlex-doc-ro/train-* - split: validation path: multieurlex-doc-ro/validation-* - split: test path: multieurlex-doc-ro/test-* - config_name: multieurlex-doc-sv data_files: - split: train path: multieurlex-doc-sv/train-* - split: validation path: multieurlex-doc-sv/validation-* - split: test path: multieurlex-doc-sv/test-* - config_name: wiki-doc-ar-img data_files: - split: train path: wiki-doc-ar-img/train-* - split: test path: wiki-doc-ar-img/test-* - split: validation path: wiki-doc-ar-img/validation-* - config_name: wiki-doc-ar-merged data_files: - split: train path: wiki-doc-ar-merged/train-* - split: test path: wiki-doc-ar-merged/test-* - split: validation path: wiki-doc-ar-merged/validation-* - config_name: wiki-doc-de-merged data_files: - split: train path: wiki-doc-de-merged/train-* - split: validation path: wiki-doc-de-merged/validation-* - split: test path: wiki-doc-de-merged/test-* - config_name: wiki-doc-en-merged data_files: - split: train path: wiki-doc-en-merged/train-* - split: validation path: wiki-doc-en-merged/validation-* - split: test path: wiki-doc-en-merged/test-* - config_name: wiki-doc-es-merged data_files: - split: train path: wiki-doc-es-merged/train-* - split: validation path: wiki-doc-es-merged/validation-* - split: test path: wiki-doc-es-merged/test-* - config_name: wiki-doc-fr-merged data_files: - split: train path: wiki-doc-fr-merged/train-* - split: validation path: wiki-doc-fr-merged/validation-* - split: test path: wiki-doc-fr-merged/test-* - config_name: wiki-doc-it-merged data_files: - split: train path: wiki-doc-it-merged/train-* - split: validation path: wiki-doc-it-merged/validation-* - split: test path: wiki-doc-it-merged/test-* - config_name: wiki-doc-ja-img data_files: - split: train path: wiki-doc-ja-img/train-* - split: test path: wiki-doc-ja-img/test-* - split: validation path: wiki-doc-ja-img/validation-* - config_name: wiki-doc-ja-merged data_files: - split: train path: wiki-doc-ja-merged/train-* - split: validation path: wiki-doc-ja-merged/validation-* - split: test path: wiki-doc-ja-merged/test-* - config_name: wiki-doc-pt-img data_files: - split: train path: wiki-doc-pt-img/train-* - split: test path: wiki-doc-pt-img/test-* - split: validation path: wiki-doc-pt-img/validation-* - config_name: wiki-doc-pt-merged data_files: - split: train path: wiki-doc-pt-merged/train-* - split: validation path: wiki-doc-pt-merged/validation-* - split: test path: wiki-doc-pt-merged/test-* - config_name: wiki-doc-pt-merged-v2 data_files: - split: train path: wiki-doc-pt-merged-v2/train-* - split: validation path: wiki-doc-pt-merged-v2/validation-* - split: test path: wiki-doc-pt-merged-v2/test-* - config_name: wiki-doc-zh-img data_files: - split: train path: wiki-doc-zh-img/train-* - split: test path: wiki-doc-zh-img/test-* - split: validation path: wiki-doc-zh-img/validation-* - config_name: wiki-doc-zh-merged data_files: - split: train path: wiki-doc-zh-merged/train-* - split: test path: wiki-doc-zh-merged/test-* - split: validation path: wiki-doc-zh-merged/validation-* --- ## Additional Information To load the dataset, ``` import datasets ds = datasets.load_dataset("AmazonScience/MultilingualMultiModalClassification", data_dir="wiki-doc-ar-merged") print(ds) DatasetDict({ train: Dataset({ features: ['image', 'filename', 'words', 'ocr_bboxes', 'label'], num_rows: 8129 }) validation: Dataset({ features: ['image', 'filename', 'words', 'ocr_bboxes', 'label'], num_rows: 1742 }) test: Dataset({ features: ['image', 'filename', 'words', 'ocr_bboxes', 'label'], num_rows: 1743 }) }) # In case you encountered `NonMatchingSplitsSizesError`, try out the following: # from datasets import Image, Value, Sequence, ClassLabel, Features # features = Features({'image': Image(mode=None, decode=True, id=None), 'filename': Value(dtype='string', id=None), 'words': Sequence(feature=Value(dtype='string', id=None), length=-1, id=None), 'ocr_bboxes': Sequence(feature=Sequence(feature=Value(dtype='int64', id=None), length=-1, id=None), length=-1, id=None), 'label': ClassLabel(names=['AcademicJournal', 'AdultActor', 'Album', 'AmateurBoxer', 'Ambassador', 'AmericanFootballPlayer', 'Amphibian', 'AnimangaCharacter', 'Anime', 'Arachnid', 'Baronet', 'BasketballTeam', 'BeautyQueen', 'BroadcastNetwork', 'BusCompany', 'BusinessPerson', 'CanadianFootballTeam', 'Canal', 'Cardinal', 'Cave', 'ChristianBishop', 'ClassicalMusicArtist', 'ClassicalMusicComposition', 'CollegeCoach', 'Comedian', 'ComicsCreator', 'Congressman', 'Conifer', 'Convention', 'Cricketer', 'Crustacean', 'CultivatedVariety', 'Cycad', 'Dam', 'Economist', 'Engineer', 'Entomologist', 'EurovisionSongContestEntry', 'Fern', 'FilmFestival', 'Fish', 'FootballMatch', 'Glacier', 'GolfTournament', 'Governor', 'Gymnast', 'Historian', 'IceHockeyLeague', 'Insect', 'Journalist', 'Judge', 'Lighthouse', 'Magazine', 'Mayor', 'Medician', 'MemberOfParliament', 'MilitaryPerson', 'Model', 'Mollusca', 'Monarch', 'Moss', 'Mountain', 'MountainPass', 'MountainRange', 'MusicFestival', 'Musical', 'MythologicalFigure', 'Newspaper', 'Noble', 'OfficeHolder', 'Other', 'Philosopher', 'Photographer', 'PlayboyPlaymate', 'Poem', 'Poet', 'Pope', 'President', 'PrimeMinister', 'PublicTransitSystem', 'Racecourse', 'RadioHost', 'RadioStation', 'Religious', 'Reptile', 'Restaurant', 'Road', 'RoadTunnel', 'RollerCoaster', 'RugbyClub', 'RugbyLeague', 'Saint', 'School', 'ScreenWriter', 'Senator', 'ShoppingMall', 'Skater', 'SoccerLeague', 'SoccerManager', 'SoccerPlayer', 'SoccerTournament', 'SportsTeamMember', 'SumoWrestler', 'TelevisionStation', 'TennisTournament', 'TradeUnion', 'University', 'Village', 'VoiceActor', 'Volcano', 'WrestlingEvent'], id=None)}) # ds = datasets.load_dataset("AmazonScience/MultilingualMultiModalClassification", data_dir="wiki-doc-ar-merged", features=features, verification_mode="no_checks") ``` ### Licensing Information #### Wiki Each image is licensed under original provider. Any additional work provided by current work is provided under CC-BY-SA-4.0 following the Wikipedia license. #### MultiEURLEX We provide MultiEURLEX with the same licensing as the original EU data (CC-BY-4.0): © European Union, 1998-2021 The Commission’s document reuse policy is based on Decision 2011/833/EU. Unless otherwise specified, you can re-use the legal documents published in EUR-Lex for commercial or non-commercial purposes. The copyright for the editorial content of this website, the summaries of EU legislation and the consolidated texts, which is owned by the EU, is licensed under the Creative Commons Attribution 4.0 International licence. This means that you can re-use the content provided you acknowledge the source and indicate any changes you have made. Source: https://eur-lex.europa.eu/content/legal-notice/legal-notice.html \ Read more: https://eur-lex.europa.eu/content/help/faq/reuse-contents-eurlex.html ### Citation Information ``` @inproceedings{fujinuma-etal-2023-multi, title = "A Multi-Modal Multilingual Benchmark for Document Image Classification", author = "Fujinuma, Yoshinari and Varia, Siddharth and Sankaran, Nishant and Appalaraju, Srikar and Min, Bonan and Vyas, Yogarshi", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.findings-emnlp.958", doi = "10.18653/v1/2023.findings-emnlp.958", pages = "14361--14376", abstract = "Document image classification is different from plain-text document classification and consists of classifying a document by understanding the content and structure of documents such as forms, emails, and other such documents. We show that the only existing dataset for this task (Lewis et al., 2006) has several limitations and we introduce two newly curated multilingual datasets WIKI-DOC and MULTIEURLEX-DOC that overcome these limitations. We further undertake a comprehensive study of popular visually-rich document understanding or Document AI models in previously untested setting in document image classification such as 1) multi-label classification, and 2) zero-shot cross-lingual transfer setup. Experimental results show limitations of multilingual Document AI models on cross-lingual transfer across typologically distant languages. Our datasets and findings open the door for future research into improving Document AI models.", } ```

legacy-datasets/c4

legacy-datasets

--- pretty_name: C4 annotations_creators: - no-annotation language_creators: - found language: - en license: - odc-by multilinguality: - multilingual size_categories: - 100M<n<1B source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling paperswithcode_id: c4 viewer: false dataset_info: - config_name: en features: - name: text dtype: string - name: timestamp dtype: string - name: url dtype: string splits: - name: train num_bytes: 828589180707 num_examples: 364868892 - name: validation num_bytes: 825767266 num_examples: 364608 download_size: 326778635540 dataset_size: 1657178361414 - config_name: en.noblocklist features: - name: text dtype: string - name: timestamp dtype: string - name: url dtype: string splits: - name: train num_bytes: 1029628201361 num_examples: 393391519 - name: validation num_bytes: 1025606012 num_examples: 393226 download_size: 406611392434 dataset_size: 2059256402722 - config_name: realnewslike features: - name: text dtype: string - name: timestamp dtype: string - name: url dtype: string splits: - name: train num_bytes: 38165657946 num_examples: 13799838 - name: validation num_bytes: 37875873 num_examples: 13863 download_size: 15419740744 dataset_size: 76331315892 - config_name: en.noclean features: - name: text dtype: string - name: timestamp dtype: string - name: url dtype: string splits: - name: train num_bytes: 6715509699938 num_examples: 1063805381 - name: validation num_bytes: 6706356913 num_examples: 1065029 download_size: 2430376268625 dataset_size: 6722216056851 --- <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"> <p><b>Deprecated:</b> Dataset "c4" is deprecated and will be deleted. Use "<a href="https://huggingface.co/datasets/allenai/c4">allenai/c4</a>" instead.</p> </div> # Dataset Card for C4 ## Table of Contents - [Dataset Card for C4](#dataset-card-for-c4) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) - [Who are the source language producers?](#who-are-the-source-language-producers) - [Annotations](#annotations) - [Annotation process](#annotation-process) - [Who are the annotators?](#who-are-the-annotators) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://huggingface.co/datasets/allenai/c4 - **Paper:** https://arxiv.org/abs/1910.10683 ### Dataset Summary A colossal, cleaned version of Common Crawl's web crawl corpus. Based on Common Crawl dataset: "https://commoncrawl.org". This is the version prepared by AllenAI, hosted at this address: https://huggingface.co/datasets/allenai/c4 It comes in four variants: - `en`: 305GB in JSON format - `en.noblocklist`: 380GB in JSON format - `en.noclean`: 2.3TB in JSON format - `realnewslike`: 15GB in JSON format The `en.noblocklist` variant is exactly the same as the `en` variant, except we turned off the so-called "badwords filter", which removes all documents that contain words from the lists at https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words. ### Supported Tasks and Leaderboards C4 is mainly intended to pretrain language models and word representations. ### Languages The dataset is in English. ## Dataset Structure ### Data Instances An example form the `en` config is: ``` { 'url': 'https://klyq.com/beginners-bbq-class-taking-place-in-missoula/', 'text': 'Beginners BBQ Class Taking Place in Missoula!\nDo you want to get better at making delicious BBQ? You will have the opportunity, put this on your calendar now. Thursday, September 22nd join World Class BBQ Champion, Tony Balay from Lonestar Smoke Rangers. He will be teaching a beginner level class for everyone who wants to get better with their culinary skills.\nHe will teach you everything you need to know to compete in a KCBS BBQ competition, including techniques, recipes, timelines, meat selection and trimming, plus smoker and fire information.\nThe cost to be in the class is $35 per person, and for spectators it is free. Included in the cost will be either a t-shirt or apron and you will be tasting samples of each meat that is prepared.', 'timestamp': '2019-04-25T12:57:54Z' } ``` ### Data Fields The data have several fields: - `url`: url of the source as a string - `text`: text content as a string - `timestamp`: timestamp as a string ### Data Splits | name | train |validation| |----------------|--------:|---------:| | en |364868892| 364608| | en.noblocklist |393391519| 393226| | en.noclean | ?| ?| | realnewslike | 13799838| 13863| ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization C4 dataset is a collection of about 750GB of English-language text sourced from the public Common Crawl web scrape. It includes heuristics to extract only natural language (as opposed to boilerplate and other gibberish) in addition to extensive deduplication. You can find the code that has been used to build this dataset in [c4.py](https://github.com/tensorflow/datasets/blob/5952d3d60d60e1727786fa7a9a23d24bb463d4d6/tensorflow_datasets/text/c4.py) by Tensorflow Datasets. The dataset was explicitly designed to be English only: any page that was not given a probability of at least 99% of being English by [langdetect](https://github.com/Mimino666/langdetect) was discarded. #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information AllenAI are releasing this dataset under the terms of ODC-BY. By using this, you are also bound by the Common Crawl terms of use in respect of the content contained in the dataset. ### Citation Information ``` @article{2019t5, author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu}, title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer}, journal = {arXiv e-prints}, year = {2019}, archivePrefix = {arXiv}, eprint = {1910.10683}, } ``` ### Contributions Thanks to [@dirkgr](https://github.com/dirkgr) and [@lhoestq](https://github.com/lhoestq) for adding this dataset.

Qi28/SD_QZ

Qi28

--- license: apache-2.0 ---

mteb/sts12-sts

mteb

--- language: - en ---

open-r1/OpenR1-Math-220k

open-r1

--- license: apache-2.0 language: - en configs: - config_name: all data_files: - split: train path: all/train-* - config_name: default data_files: - split: train path: data/train-* - config_name: extended data_files: - split: train path: extended/train-* dataset_info: - config_name: all features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: problem_type dtype: string - name: question_type dtype: string - name: source dtype: string - name: uuid dtype: string - name: is_reasoning_complete sequence: bool - name: generations sequence: string - name: correctness_math_verify sequence: bool - name: correctness_llama sequence: bool - name: finish_reasons sequence: string - name: correctness_count dtype: int64 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 9734110026.0 num_examples: 225129 download_size: 4221672067 dataset_size: 9734110026.0 - config_name: default features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: problem_type dtype: string - name: question_type dtype: string - name: source dtype: string - name: uuid dtype: string - name: is_reasoning_complete sequence: bool - name: generations sequence: string - name: correctness_math_verify sequence: bool - name: correctness_llama sequence: bool - name: finish_reasons sequence: string - name: correctness_count dtype: int64 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 4964543659 num_examples: 93733 download_size: 2149897914 dataset_size: 4964543659 - config_name: extended features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: problem_type dtype: string - name: question_type dtype: string - name: source dtype: string - name: uuid dtype: string - name: is_reasoning_complete sequence: bool - name: generations sequence: string - name: correctness_math_verify sequence: bool - name: correctness_llama sequence: bool - name: finish_reasons sequence: string - name: correctness_count dtype: int64 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 4769566550 num_examples: 131396 download_size: 2063936457 dataset_size: 4769566550 --- # OpenR1-Math-220k ## Dataset description OpenR1-Math-220k is a large-scale dataset for mathematical reasoning. It consists of 220k math problems with two to four reasoning traces generated by [DeepSeek R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) for problems from NuminaMath 1.5. The traces were verified using [Math Verify](https://github.com/huggingface/Math-Verify) for most samples and [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) as a judge for 12% of the samples, and each problem contains at least one reasoning trace with a correct answer. The dataset consists of two splits: - `default` with 94k problems and that achieves the best performance after SFT. - `extended` with 131k samples where we add data sources like `cn_k12`. This provides more reasoning traces, but we found that the performance after SFT to be lower than the `default` subset, likely because the questions from `cn_k12` are less difficult than other sources. You can load the dataset as follows: ```python from datasets import load_dataset ds = load_dataset("open-r1/OpenR1-Math-220k", "default") ``` ## Dataset curation To build OpenR1-Math-220k, we prompt [DeepSeek R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) model to generate solutions for 400k problems from [NuminaMath 1.5](https://huggingface.co/datasets/AI-MO/NuminaMath-1.5) using [SGLang](https://github.com/sgl-project/sglang), the generation code is available [here](https://github.com/huggingface/open-r1/tree/main/slurm). We follow the model card’s recommended generation parameters and prepend the following instruction to the user prompt: `"Please reason step by step, and put your final answer within \boxed{}."` We set a 16k token limit per generation, as our analysis showed that only 75% of problems could be solved in under 8k tokens, and most of the remaining problems required the full 16k tokens. We were able to generate 25 solutions per hour per H100, enabling us to generate 300k problem solutions per day on 512 H100s. We generate two solutions per problem—and in some cases, four—to provide flexibility in filtering and training. This approach allows for rejection sampling, similar to DeepSeek R1’s methodology, and also makes the dataset suitable for preference optimisation methods like DPO. ## License The dataset is licensed under Apache 2.0

rayliuca/WikidataLabels

rayliuca

--- license: cc0-1.0 dataset_info: - config_name: aa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13986211 num_examples: 436895 download_size: 9821312 dataset_size: 13986211 - config_name: ab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5012532 num_examples: 159908 download_size: 3013706 dataset_size: 5012532 - config_name: abs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252728 num_examples: 143986 download_size: 2567450 dataset_size: 4252728 - config_name: ace features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19105673 num_examples: 574712 download_size: 13573374 dataset_size: 19105673 - config_name: ady features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4444259 num_examples: 148627 download_size: 2705754 dataset_size: 4444259 - config_name: ady-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4412556 num_examples: 147884 download_size: 2682170 dataset_size: 4412556 - config_name: aeb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4305734 num_examples: 145198 download_size: 2606368 dataset_size: 4305734 - config_name: aeb-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4467930 num_examples: 148796 download_size: 2722169 dataset_size: 4467930 - config_name: aeb-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12770359 num_examples: 404946 download_size: 8886489 dataset_size: 12770359 - config_name: af features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58561042 num_examples: 1643153 download_size: 42539052 dataset_size: 58561042 - config_name: agq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1317 num_examples: 33 download_size: 2906 dataset_size: 1317 - config_name: ak features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14198715 num_examples: 443037 download_size: 9991525 dataset_size: 14198715 - config_name: aln features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13811116 num_examples: 432089 download_size: 9673418 dataset_size: 13811116 - config_name: als features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20691 num_examples: 543 download_size: 17540 dataset_size: 20691 - config_name: alt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 108390 num_examples: 1814 download_size: 59046 dataset_size: 108390 - config_name: am features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5231176 num_examples: 163038 download_size: 3187164 dataset_size: 5231176 - config_name: ami features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21519 num_examples: 686 download_size: 16640 dataset_size: 21519 - config_name: an features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 240345072 num_examples: 5921087 download_size: 164895205 dataset_size: 240345072 - config_name: ang features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14275715 num_examples: 443461 download_size: 10063758 dataset_size: 14275715 - config_name: anp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8558258 num_examples: 241612 download_size: 4381360 dataset_size: 8558258 - config_name: ar features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 291173732 num_examples: 5724064 download_size: 159369497 dataset_size: 291173732 - config_name: arc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4473283 num_examples: 150006 download_size: 2722619 dataset_size: 4473283 - config_name: arn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13879729 num_examples: 433912 download_size: 9715431 dataset_size: 13879729 - config_name: arq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4346991 num_examples: 146004 download_size: 2636972 dataset_size: 4346991 - config_name: ary features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5358568 num_examples: 171568 download_size: 3313402 dataset_size: 5358568 - config_name: arz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 81806333 num_examples: 1669699 download_size: 49423508 dataset_size: 81806333 - config_name: as features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21658610 num_examples: 450074 download_size: 9641626 dataset_size: 21658610 - config_name: ase features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252943 num_examples: 143986 download_size: 2568106 dataset_size: 4252943 - config_name: ast features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1385628786 num_examples: 20696237 download_size: 955908362 dataset_size: 1385628786 - config_name: atj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12996229 num_examples: 411639 download_size: 9057557 dataset_size: 12996229 - config_name: av features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4722934 num_examples: 153781 download_size: 2880103 dataset_size: 4722934 - config_name: avk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13194485 num_examples: 414598 download_size: 9200917 dataset_size: 13194485 - config_name: awa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8599312 num_examples: 242320 download_size: 4411751 dataset_size: 8599312 - config_name: ay features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14269432 num_examples: 443521 download_size: 10029939 dataset_size: 14269432 - config_name: az features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21049248 num_examples: 516732 download_size: 14117527 dataset_size: 21049248 - config_name: azb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30781587 num_examples: 607562 download_size: 16028687 dataset_size: 30781587 - config_name: ba features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11525351 num_examples: 261509 download_size: 6733777 dataset_size: 11525351 - config_name: ban features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13674052 num_examples: 426706 download_size: 9513747 dataset_size: 13674052 - config_name: ban-bali features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 50961 num_examples: 748 download_size: 25817 dataset_size: 50961 - config_name: bar features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 54783034 num_examples: 1566120 download_size: 40389830 dataset_size: 54783034 - config_name: bbc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12820895 num_examples: 406960 download_size: 8917054 dataset_size: 12820895 - config_name: bcc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8017228 num_examples: 241977 download_size: 4344579 dataset_size: 8017228 - config_name: be features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30978832 num_examples: 564184 download_size: 17461174 dataset_size: 30978832 - config_name: be-tarask features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18931909 num_examples: 374396 download_size: 10871239 dataset_size: 18931909 - config_name: bg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 200628708 num_examples: 4383953 download_size: 137745533 dataset_size: 200628708 - config_name: bgn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7999280 num_examples: 241566 download_size: 4331249 dataset_size: 7999280 - config_name: bi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14040026 num_examples: 438382 download_size: 9867032 dataset_size: 14040026 - config_name: bjn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8375348 num_examples: 254558 download_size: 5722334 dataset_size: 8375348 - config_name: bm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18145787 num_examples: 549694 download_size: 13129193 dataset_size: 18145787 - config_name: bn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 815803977 num_examples: 9767284 download_size: 261147329 dataset_size: 815803977 - config_name: bo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11671330 num_examples: 278307 download_size: 5669602 dataset_size: 11671330 - config_name: bpy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15497749 num_examples: 347458 download_size: 6991190 dataset_size: 15497749 - config_name: bqi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8017455 num_examples: 241984 download_size: 4345123 dataset_size: 8017455 - config_name: br features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58304963 num_examples: 1653800 download_size: 42722031 dataset_size: 58304963 - config_name: brh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5328437 num_examples: 171504 download_size: 3376189 dataset_size: 5328437 - config_name: bs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30441466 num_examples: 858190 download_size: 21606575 dataset_size: 30441466 - config_name: btm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252525 num_examples: 143980 download_size: 2567218 dataset_size: 4252525 - config_name: bto features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12841721 num_examples: 407470 download_size: 8934218 dataset_size: 12841721 - config_name: bug features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7595464 num_examples: 235268 download_size: 5129941 dataset_size: 7595464 - config_name: bxr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4713699 num_examples: 153707 download_size: 2869313 dataset_size: 4713699 - config_name: ca features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 408509932 num_examples: 9936886 download_size: 288474980 dataset_size: 408509932 - config_name: cbk-zam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14108232 num_examples: 440345 download_size: 9920793 dataset_size: 14108232 - config_name: cdo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6503254 num_examples: 201362 download_size: 4137841 dataset_size: 6503254 - config_name: ce features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 28093148 num_examples: 607767 download_size: 16367596 dataset_size: 28093148 - config_name: ceb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 332947091 num_examples: 7769402 download_size: 219525737 dataset_size: 332947091 - config_name: ch features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13983906 num_examples: 436785 download_size: 9817385 dataset_size: 13983906 - config_name: cho features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13950786 num_examples: 435869 download_size: 9791296 dataset_size: 13950786 - config_name: chr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5386793 num_examples: 172855 download_size: 3419676 dataset_size: 5386793 - config_name: chy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13994916 num_examples: 437007 download_size: 9830465 dataset_size: 13994916 - config_name: ckb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23343034 num_examples: 511183 download_size: 11459344 dataset_size: 23343034 - config_name: co features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47080480 num_examples: 1346929 download_size: 34551346 dataset_size: 47080480 - config_name: cps features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12849864 num_examples: 407695 download_size: 8941921 dataset_size: 12849864 - config_name: cr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5516556 num_examples: 176667 download_size: 3532952 dataset_size: 5516556 - config_name: crh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10864382 num_examples: 336709 download_size: 7542853 dataset_size: 10864382 - config_name: crh-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4419064 num_examples: 148046 download_size: 2688683 dataset_size: 4419064 - config_name: crh-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14201429 num_examples: 442905 download_size: 9986290 dataset_size: 14201429 - config_name: cs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 140189244 num_examples: 3384048 download_size: 97516751 dataset_size: 140189244 - config_name: csb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20177120 num_examples: 619275 download_size: 14528772 dataset_size: 20177120 - config_name: cv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8047221 num_examples: 215611 download_size: 4857718 dataset_size: 8047221 - config_name: cy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 89241808 num_examples: 2244550 download_size: 62686006 dataset_size: 89241808 - config_name: da features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 130931077 num_examples: 3448894 download_size: 98202417 dataset_size: 130931077 - config_name: dag features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2664957 num_examples: 78534 download_size: 2052615 dataset_size: 2664957 - config_name: de features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 765398522 num_examples: 17531361 download_size: 527642124 dataset_size: 765398522 - config_name: de-at features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53043722 num_examples: 1515373 download_size: 38761571 dataset_size: 53043722 - config_name: de-ch features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53480908 num_examples: 1528137 download_size: 39349412 dataset_size: 53480908 - config_name: de-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4256391 num_examples: 144061 download_size: 2571862 dataset_size: 4256391 - config_name: din features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12819746 num_examples: 406591 download_size: 8922303 dataset_size: 12819746 - config_name: diq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7570161 num_examples: 232674 download_size: 5057742 dataset_size: 7570161 - config_name: dsb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16135830 num_examples: 491423 download_size: 11412316 dataset_size: 16135830 - config_name: dtp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13867373 num_examples: 433733 download_size: 9720699 dataset_size: 13867373 - config_name: dty features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8839082 num_examples: 246026 download_size: 4551845 dataset_size: 8839082 - config_name: dua features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2631 num_examples: 87 download_size: 3877 dataset_size: 2631 - config_name: dv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 81396462 num_examples: 2103276 download_size: 45332104 dataset_size: 81396462 - config_name: dz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8590239 num_examples: 242196 download_size: 4406353 dataset_size: 8590239 - config_name: ee features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14377017 num_examples: 447208 download_size: 10136064 dataset_size: 14377017 - config_name: egl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13068224 num_examples: 413551 download_size: 9121776 dataset_size: 13068224 - config_name: el features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32978562 num_examples: 592016 download_size: 19577876 dataset_size: 32978562 - config_name: eml features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14768563 num_examples: 458847 download_size: 10453636 dataset_size: 14768563 - config_name: en features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6327454281 num_examples: 81801560 download_size: 4224231068 dataset_size: 6327454281 - config_name: en-ca features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 73305274 num_examples: 1909970 download_size: 53060194 dataset_size: 73305274 - config_name: en-gb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 115978412 num_examples: 2520405 download_size: 78924421 dataset_size: 115978412 - config_name: en-us features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14815 num_examples: 332 download_size: 9953 dataset_size: 14815 - config_name: eo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 256196064 num_examples: 6285304 download_size: 177219679 dataset_size: 256196064 - config_name: es features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 730214298 num_examples: 17233968 download_size: 514588069 dataset_size: 730214298 - config_name: es-419 features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4355180 num_examples: 146476 download_size: 2659218 dataset_size: 4355180 - config_name: es-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4280933 num_examples: 144717 download_size: 2592085 dataset_size: 4280933 - config_name: et features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 65123623 num_examples: 1820762 download_size: 48197302 dataset_size: 65123623 - config_name: eu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 290282374 num_examples: 7109758 download_size: 197889378 dataset_size: 290282374 - config_name: ext features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 223257222 num_examples: 5359047 download_size: 147078789 dataset_size: 223257222 - config_name: fa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 123727757 num_examples: 2142642 download_size: 65952114 dataset_size: 123727757 - config_name: ff features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14116652 num_examples: 440614 download_size: 9920388 dataset_size: 14116652 - config_name: fi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 286539944 num_examples: 6905698 download_size: 209916638 dataset_size: 286539944 - config_name: fit features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20217258 num_examples: 620391 download_size: 14566702 dataset_size: 20217258 - config_name: fj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14159041 num_examples: 441745 download_size: 9956108 dataset_size: 14159041 - config_name: fkv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4328482 num_examples: 145988 download_size: 2619845 dataset_size: 4328482 - config_name: fo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24474476 num_examples: 731732 download_size: 17876981 dataset_size: 24474476 - config_name: fr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 774128723 num_examples: 17908351 download_size: 534489308 dataset_size: 774128723 - config_name: frc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17896106 num_examples: 547258 download_size: 12953740 dataset_size: 17896106 - config_name: frp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40902510 num_examples: 1191134 download_size: 29778105 dataset_size: 40902510 - config_name: frr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16979214 num_examples: 515350 download_size: 12069637 dataset_size: 16979214 - config_name: fur features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42077410 num_examples: 1221071 download_size: 30714082 dataset_size: 42077410 - config_name: ga features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 471527543 num_examples: 11524282 download_size: 320967189 dataset_size: 471527543 - config_name: gag features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14149375 num_examples: 440732 download_size: 9940551 dataset_size: 14149375 - config_name: gan features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31572161 num_examples: 905186 download_size: 18909564 dataset_size: 31572161 - config_name: gan-hans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31004794 num_examples: 889875 download_size: 18566811 dataset_size: 31004794 - config_name: gan-hant features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4374444 num_examples: 147098 download_size: 2657182 dataset_size: 4374444 - config_name: gcr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4311409 num_examples: 145829 download_size: 2618211 dataset_size: 4311409 - config_name: gd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 49316935 num_examples: 1429457 download_size: 36220978 dataset_size: 49316935 - config_name: gl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 289484839 num_examples: 7052226 download_size: 197315151 dataset_size: 289484839 - config_name: glk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8327018 num_examples: 249115 download_size: 4538325 dataset_size: 8327018 - config_name: gn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14212974 num_examples: 442765 download_size: 10004863 dataset_size: 14212974 - config_name: gom features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4584575 num_examples: 150273 download_size: 2780570 dataset_size: 4584575 - config_name: gom-deva features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8585678 num_examples: 242131 download_size: 4400578 dataset_size: 8585678 - config_name: gom-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12783006 num_examples: 405302 download_size: 8897342 dataset_size: 12783006 - config_name: gor features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14667616 num_examples: 454512 download_size: 10319196 dataset_size: 14667616 - config_name: got features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5432139 num_examples: 172951 download_size: 3435531 dataset_size: 5432139 - config_name: grc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4494817 num_examples: 149631 download_size: 2746170 dataset_size: 4494817 - config_name: gu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23788894 num_examples: 486140 download_size: 10779200 dataset_size: 23788894 - config_name: guc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1419 num_examples: 38 download_size: 3054 dataset_size: 1419 - config_name: guw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 118 num_examples: 4 download_size: 1864 dataset_size: 118 - config_name: gv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20683485 num_examples: 631005 download_size: 14894590 dataset_size: 20683485 - config_name: ha features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14716168 num_examples: 455836 download_size: 10421790 dataset_size: 14716168 - config_name: hak features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6128644 num_examples: 193036 download_size: 3991729 dataset_size: 6128644 - config_name: haw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14158084 num_examples: 441511 download_size: 9952975 dataset_size: 14158084 - config_name: he features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43629050 num_examples: 884809 download_size: 27221301 dataset_size: 43629050 - config_name: hi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 37237187 num_examples: 668964 download_size: 17804873 dataset_size: 37237187 - config_name: hif features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14457954 num_examples: 449009 download_size: 10166264 dataset_size: 14457954 - config_name: hif-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14519845 num_examples: 454037 download_size: 10240704 dataset_size: 14519845 - config_name: hil features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12928914 num_examples: 409962 download_size: 9009705 dataset_size: 12928914 - config_name: ho features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13950504 num_examples: 435857 download_size: 9790849 dataset_size: 13950504 - config_name: hr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 61272623 num_examples: 1720527 download_size: 45307411 dataset_size: 61272623 - config_name: hrx features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12869295 num_examples: 407823 download_size: 8964114 dataset_size: 12869295 - config_name: hsb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23720349 num_examples: 707100 download_size: 17145693 dataset_size: 23720349 - config_name: ht features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16835529 num_examples: 509955 download_size: 11880404 dataset_size: 16835529 - config_name: hu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 85054175 num_examples: 2200589 download_size: 64143342 dataset_size: 85054175 - config_name: hu-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252810 num_examples: 143986 download_size: 2567582 dataset_size: 4252810 - config_name: hy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 39339286 num_examples: 773925 download_size: 22108994 dataset_size: 39339286 - config_name: hyw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5443608 num_examples: 166902 download_size: 3238370 dataset_size: 5443608 - config_name: hz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13948574 num_examples: 435804 download_size: 9788697 dataset_size: 13948574 - config_name: ia features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 229143237 num_examples: 5616433 download_size: 155877454 dataset_size: 229143237 - config_name: id features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 95220928 num_examples: 2512331 download_size: 69525046 dataset_size: 95220928 - config_name: ie features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 225725262 num_examples: 5533032 download_size: 153371930 dataset_size: 225725262 - config_name: ig features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20109388 num_examples: 617044 download_size: 14475407 dataset_size: 20109388 - config_name: ii features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4310418 num_examples: 145332 download_size: 2609723 dataset_size: 4310418 - config_name: ik features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13989609 num_examples: 436958 download_size: 9823174 dataset_size: 13989609 - config_name: ike-cans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4352278 num_examples: 146355 download_size: 2645174 dataset_size: 4352278 - config_name: ike-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13851135 num_examples: 432932 download_size: 9714057 dataset_size: 13851135 - config_name: ilo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15955483 num_examples: 480555 download_size: 11141942 dataset_size: 15955483 - config_name: inh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4634360 num_examples: 152226 download_size: 2831580 dataset_size: 4634360 - config_name: io features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 233656822 num_examples: 5757440 download_size: 159720058 dataset_size: 233656822 - config_name: is features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 51679396 num_examples: 1483610 download_size: 37965494 dataset_size: 51679396 - config_name: it features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 536601426 num_examples: 12631487 download_size: 375025347 dataset_size: 536601426 - config_name: iu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5360588 num_examples: 172215 download_size: 3402239 dataset_size: 5360588 - config_name: ja features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 140641579 num_examples: 2917962 download_size: 92145329 dataset_size: 140641579 - config_name: jam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18849751 num_examples: 571777 download_size: 13684422 dataset_size: 18849751 - config_name: jbo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14301985 num_examples: 446512 download_size: 9994516 dataset_size: 14301985 - config_name: jv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27232302 num_examples: 794181 download_size: 19651565 dataset_size: 27232302 - config_name: ka features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24073345 num_examples: 399546 download_size: 11679979 dataset_size: 24073345 - config_name: kaa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14082184 num_examples: 439411 download_size: 9902820 dataset_size: 14082184 - config_name: kab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18459676 num_examples: 557857 download_size: 13384218 dataset_size: 18459676 - config_name: kbd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4594409 num_examples: 149733 download_size: 2759503 dataset_size: 4594409 - config_name: kbd-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4417661 num_examples: 148017 download_size: 2687531 dataset_size: 4417661 - config_name: kbp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12873178 num_examples: 408039 download_size: 8965474 dataset_size: 12873178 - config_name: kea features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12793700 num_examples: 405901 download_size: 8896866 dataset_size: 12793700 - config_name: kg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40949149 num_examples: 1193499 download_size: 29766747 dataset_size: 40949149 - config_name: khw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4308653 num_examples: 145279 download_size: 2608581 dataset_size: 4308653 - config_name: ki features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14056900 num_examples: 439015 download_size: 9875534 dataset_size: 14056900 - config_name: kj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13881723 num_examples: 433861 download_size: 9733715 dataset_size: 13881723 - config_name: kjp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8504302 num_examples: 240339 download_size: 4341523 dataset_size: 8504302 - config_name: kk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19216115 num_examples: 428880 download_size: 11577682 dataset_size: 19216115 - config_name: kk-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7241749 num_examples: 211731 download_size: 4487032 dataset_size: 7241749 - config_name: kk-kz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4937945 num_examples: 160027 download_size: 3062906 dataset_size: 4937945 - config_name: kk-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22197825 num_examples: 677162 download_size: 16072332 dataset_size: 22197825 - config_name: kk-tr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20060635 num_examples: 616521 download_size: 14438929 dataset_size: 20060635 - config_name: ko features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 60335212 num_examples: 1364440 download_size: 39186630 dataset_size: 60335212 - config_name: ko-kp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4338717 num_examples: 146150 download_size: 2630925 dataset_size: 4338717 - config_name: koi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4737590 num_examples: 155082 download_size: 2894674 dataset_size: 4737590 - config_name: kr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13886057 num_examples: 433990 download_size: 9737602 dataset_size: 13886057 - config_name: krc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4646136 num_examples: 151026 download_size: 2785454 dataset_size: 4646136 - config_name: kri features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12798530 num_examples: 406032 download_size: 8902330 dataset_size: 12798530 - config_name: krj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13850324 num_examples: 433444 download_size: 9703460 dataset_size: 13850324 - config_name: krl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12788020 num_examples: 405729 download_size: 8893337 dataset_size: 12788020 - config_name: ks features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4390604 num_examples: 147033 download_size: 2671069 dataset_size: 4390604 - config_name: ks-deva features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8567518 num_examples: 241832 download_size: 4387687 dataset_size: 8567518 - config_name: ksh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20394712 num_examples: 624523 download_size: 14698860 dataset_size: 20394712 - config_name: ku features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8037777 num_examples: 239515 download_size: 5306097 dataset_size: 8037777 - config_name: ku-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4577826 num_examples: 151290 download_size: 2796159 dataset_size: 4577826 - config_name: ku-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14683841 num_examples: 458802 download_size: 10371977 dataset_size: 14683841 - config_name: kum features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252739 num_examples: 143985 download_size: 2567503 dataset_size: 4252739 - config_name: kv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4946978 num_examples: 158888 download_size: 2997865 dataset_size: 4946978 - config_name: kw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20245535 num_examples: 621432 download_size: 14581378 dataset_size: 20245535 - config_name: ky features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8909613 num_examples: 235165 download_size: 5462115 dataset_size: 8909613 - config_name: la features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 299766395 num_examples: 7085082 download_size: 201477460 dataset_size: 299766395 - config_name: lad features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20336417 num_examples: 622775 download_size: 14653199 dataset_size: 20336417 - config_name: lb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 56473066 num_examples: 1601093 download_size: 41410732 dataset_size: 56473066 - config_name: lbe features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4501470 num_examples: 149898 download_size: 2744786 dataset_size: 4501470 - config_name: lez features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4890798 num_examples: 155936 download_size: 2959653 dataset_size: 4890798 - config_name: lfn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14709210 num_examples: 456719 download_size: 10408539 dataset_size: 14709210 - config_name: lg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13979286 num_examples: 436009 download_size: 9802779 dataset_size: 13979286 - config_name: li features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43476868 num_examples: 1253970 download_size: 31750932 dataset_size: 43476868 - config_name: lij features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42327066 num_examples: 1227346 download_size: 30898971 dataset_size: 42327066 - config_name: liv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12781331 num_examples: 405236 download_size: 8895889 dataset_size: 12781331 - config_name: lki features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8039166 num_examples: 242526 download_size: 4363703 dataset_size: 8039166 - config_name: lld features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 90305 num_examples: 2634 download_size: 69672 dataset_size: 90305 - config_name: lmo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18287638 num_examples: 545398 download_size: 13130119 dataset_size: 18287638 - config_name: ln features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14123637 num_examples: 439731 download_size: 9915851 dataset_size: 14123637 - config_name: lo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9905189 num_examples: 271710 download_size: 5313218 dataset_size: 9905189 - config_name: loz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13695602 num_examples: 428723 download_size: 9581113 dataset_size: 13695602 - config_name: lt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 39902419 num_examples: 1096727 download_size: 29185765 dataset_size: 39902419 - config_name: ltg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13884707 num_examples: 433453 download_size: 9736637 dataset_size: 13884707 - config_name: lus features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13695197 num_examples: 428712 download_size: 9580538 dataset_size: 13695197 - config_name: luz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8459036 num_examples: 253454 download_size: 4687414 dataset_size: 8459036 - config_name: lv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27242119 num_examples: 764753 download_size: 19676667 dataset_size: 27242119 - config_name: lzh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 25067538 num_examples: 685152 download_size: 14998856 dataset_size: 25067538 - config_name: mdf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4634268 num_examples: 152141 download_size: 2820744 dataset_size: 4634268 - config_name: mg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43863002 num_examples: 1271074 download_size: 32016826 dataset_size: 43863002 - config_name: mh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13775721 num_examples: 431162 download_size: 9644397 dataset_size: 13775721 - config_name: mi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20857040 num_examples: 637118 download_size: 15060301 dataset_size: 20857040 - config_name: min features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53044258 num_examples: 1464128 download_size: 38587450 dataset_size: 53044258 - config_name: mk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24087229 num_examples: 449241 download_size: 12217912 dataset_size: 24087229 - config_name: ml features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 189266798 num_examples: 2664923 download_size: 71344031 dataset_size: 189266798 - config_name: mn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9311543 num_examples: 219695 download_size: 5272784 dataset_size: 9311543 - config_name: mni features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8696893 num_examples: 243616 download_size: 4470994 dataset_size: 8696893 - config_name: mnw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8861861 num_examples: 244906 download_size: 4517726 dataset_size: 8861861 - config_name: mo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5377009 num_examples: 172144 download_size: 3405661 dataset_size: 5377009 - config_name: mr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 26855182 num_examples: 526220 download_size: 12358679 dataset_size: 26855182 - config_name: mrh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 68 num_examples: 2 download_size: 1820 dataset_size: 68 - config_name: mrj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5007903 num_examples: 160889 download_size: 3073431 dataset_size: 5007903 - config_name: ms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 64674328 num_examples: 1803714 download_size: 47165217 dataset_size: 64674328 - config_name: ms-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 136496 num_examples: 2961 download_size: 92316 dataset_size: 136496 - config_name: mt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22632686 num_examples: 682867 download_size: 16352572 dataset_size: 22632686 - config_name: mus features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14013416 num_examples: 437688 download_size: 9835239 dataset_size: 14013416 - config_name: mwl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14493299 num_examples: 448926 download_size: 10225888 dataset_size: 14493299 - config_name: my features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16182182 num_examples: 345096 download_size: 7981905 dataset_size: 16182182 - config_name: mzn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17973941 num_examples: 447870 download_size: 9174617 dataset_size: 17973941 - config_name: na features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13992666 num_examples: 436956 download_size: 9823328 dataset_size: 13992666 - config_name: nah features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14490294 num_examples: 449748 download_size: 10192501 dataset_size: 14490294 - config_name: nan-hani features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 191 num_examples: 6 download_size: 1925 dataset_size: 191 - config_name: nap features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42362346 num_examples: 1229161 download_size: 30918265 dataset_size: 42362346 - config_name: nb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 142554768 num_examples: 3688026 download_size: 105549981 dataset_size: 142554768 - config_name: nds features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58766114 num_examples: 1666813 download_size: 43421948 dataset_size: 58766114 - config_name: nds-nl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 44121756 num_examples: 1273149 download_size: 32201410 dataset_size: 44121756 - config_name: ne features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11925386 num_examples: 295006 download_size: 6265232 dataset_size: 11925386 - config_name: new features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16906308 num_examples: 350362 download_size: 7680329 dataset_size: 16906308 - config_name: ng features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13870754 num_examples: 433582 download_size: 9723795 dataset_size: 13870754 - config_name: nia features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20649 num_examples: 515 download_size: 16535 dataset_size: 20649 - config_name: niu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12794247 num_examples: 405902 download_size: 8897260 dataset_size: 12794247 - config_name: nl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5016576732 num_examples: 61931959 download_size: 3380404239 dataset_size: 5016576732 - config_name: nn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 99997815 num_examples: 2708994 download_size: 74736304 dataset_size: 99997815 - config_name: 'no' features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2934 num_examples: 64 download_size: 4108 dataset_size: 2934 - config_name: nod features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4322068 num_examples: 145566 download_size: 2618106 dataset_size: 4322068 - config_name: nov features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14150434 num_examples: 440903 download_size: 9947798 dataset_size: 14150434 - config_name: nqo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8094271 num_examples: 243184 download_size: 4398836 dataset_size: 8094271 - config_name: nrm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 41330956 num_examples: 1203295 download_size: 30084065 dataset_size: 41330956 - config_name: nso features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14178321 num_examples: 443205 download_size: 9959708 dataset_size: 14178321 - config_name: nv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15351770 num_examples: 455188 download_size: 10472240 dataset_size: 15351770 - config_name: ny features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13989813 num_examples: 436764 download_size: 9821588 dataset_size: 13989813 - config_name: nys features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13092059 num_examples: 413241 download_size: 9153100 dataset_size: 13092059 - config_name: oc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 266612548 num_examples: 6569770 download_size: 180156462 dataset_size: 266612548 - config_name: olo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13200388 num_examples: 416935 download_size: 9214968 dataset_size: 13200388 - config_name: om features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5476389 num_examples: 175314 download_size: 3496637 dataset_size: 5476389 - config_name: or features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22798709 num_examples: 470237 download_size: 10322832 dataset_size: 22798709 - config_name: os features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5946062 num_examples: 177054 download_size: 3583703 dataset_size: 5946062 - config_name: ota features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8015024 num_examples: 241903 download_size: 4343478 dataset_size: 8015024 - config_name: pa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20505754 num_examples: 481522 download_size: 10552147 dataset_size: 20505754 - config_name: pam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14527964 num_examples: 451253 download_size: 10242443 dataset_size: 14527964 - config_name: pap features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 54505401 num_examples: 1449881 download_size: 40415776 dataset_size: 54505401 - config_name: pcd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42132826 num_examples: 1221362 download_size: 30766812 dataset_size: 42132826 - config_name: pdc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14435256 num_examples: 448055 download_size: 10178322 dataset_size: 14435256 - config_name: pdt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13994892 num_examples: 437200 download_size: 9819388 dataset_size: 13994892 - config_name: pfl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15461023 num_examples: 474198 download_size: 10893651 dataset_size: 15461023 - config_name: pi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8913354 num_examples: 250251 download_size: 4651392 dataset_size: 8913354 - config_name: pih features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13971081 num_examples: 436214 download_size: 9810653 dataset_size: 13971081 - config_name: pl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 426030491 num_examples: 10025139 download_size: 295767506 dataset_size: 426030491 - config_name: pms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 51268512 num_examples: 1477043 download_size: 37698831 dataset_size: 51268512 - config_name: pnb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16192682 num_examples: 409037 download_size: 9196626 dataset_size: 16192682 - config_name: pnt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4439173 num_examples: 148336 download_size: 2703117 dataset_size: 4439173 - config_name: prg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17940420 num_examples: 544030 download_size: 12958482 dataset_size: 17940420 - config_name: ps features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8860902 num_examples: 259186 download_size: 4916502 dataset_size: 8860902 - config_name: pt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 491184040 num_examples: 11574568 download_size: 340831923 dataset_size: 491184040 - config_name: pt-br features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 318857431 num_examples: 7782980 download_size: 223442911 dataset_size: 318857431 - config_name: pwn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8500 num_examples: 269 download_size: 8738 dataset_size: 8500 - config_name: qu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15254702 num_examples: 468823 download_size: 10750388 dataset_size: 15254702 - config_name: quc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32 num_examples: 1 download_size: 1772 dataset_size: 32 - config_name: qug features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13798264 num_examples: 431733 download_size: 9661685 dataset_size: 13798264 - config_name: rgn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17001688 num_examples: 519871 download_size: 12258201 dataset_size: 17001688 - config_name: rif features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13792951 num_examples: 431588 download_size: 9657698 dataset_size: 13792951 - config_name: rm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 44450577 num_examples: 1284908 download_size: 32519630 dataset_size: 44450577 - config_name: rmc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 159 num_examples: 4 download_size: 1963 dataset_size: 159 - config_name: rmy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5610156 num_examples: 179191 download_size: 3608283 dataset_size: 5610156 - config_name: rn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13935534 num_examples: 435271 download_size: 9779486 dataset_size: 13935534 - config_name: ro features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 247469452 num_examples: 5878366 download_size: 177525205 dataset_size: 247469452 - config_name: roa-tara features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14425120 num_examples: 448972 download_size: 10152875 dataset_size: 14425120 - config_name: ru features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 405103215 num_examples: 7485811 download_size: 257215625 dataset_size: 405103215 - config_name: rue features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4953403 num_examples: 159530 download_size: 3037824 dataset_size: 4953403 - config_name: rup features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14459686 num_examples: 450345 download_size: 10198398 dataset_size: 14459686 - config_name: ruq-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4434290 num_examples: 148404 download_size: 2700920 dataset_size: 4434290 - config_name: ruq-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13783683 num_examples: 430978 download_size: 9656941 dataset_size: 13783683 - config_name: rw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14090196 num_examples: 439172 download_size: 9901257 dataset_size: 14090196 - config_name: rwr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8568706 num_examples: 241841 download_size: 4388475 dataset_size: 8568706 - config_name: ryu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2852 num_examples: 82 download_size: 4237 dataset_size: 2852 - config_name: sa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21404327 num_examples: 455674 download_size: 9692464 dataset_size: 21404327 - config_name: sat features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10810040 num_examples: 284911 download_size: 5750917 dataset_size: 10810040 - config_name: sc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47195572 num_examples: 1348137 download_size: 34521764 dataset_size: 47195572 - config_name: scn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43458983 num_examples: 1259067 download_size: 31775157 dataset_size: 43458983 - config_name: sco features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 56960413 num_examples: 1611092 download_size: 41724559 dataset_size: 56960413 - config_name: sd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14257513 num_examples: 363318 download_size: 7844047 dataset_size: 14257513 - config_name: sdc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13975497 num_examples: 436913 download_size: 9800517 dataset_size: 13975497 - config_name: se features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23962268 num_examples: 711439 download_size: 17409387 dataset_size: 23962268 - config_name: sei features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13827581 num_examples: 432520 download_size: 9684192 dataset_size: 13827581 - config_name: sg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13913524 num_examples: 434751 download_size: 9761739 dataset_size: 13913524 - config_name: sh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30173635 num_examples: 746207 download_size: 20133594 dataset_size: 30173635 - config_name: shi-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13783218 num_examples: 430968 download_size: 9656828 dataset_size: 13783218 - config_name: shi-tfng features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4308577 num_examples: 145279 download_size: 2608525 dataset_size: 4308577 - config_name: shn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10139002 num_examples: 260808 download_size: 4952168 dataset_size: 10139002 - config_name: shy-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4255322 num_examples: 144058 download_size: 2570625 dataset_size: 4255322 - config_name: si features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7405400 num_examples: 189718 download_size: 4270591 dataset_size: 7405400 - config_name: sjd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4300688 num_examples: 145047 download_size: 2604357 dataset_size: 4300688 - config_name: sje features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20970223 num_examples: 637639 download_size: 15120381 dataset_size: 20970223 - config_name: sju features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4315103 num_examples: 145655 download_size: 2620763 dataset_size: 4315103 - config_name: sk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 75586366 num_examples: 2050873 download_size: 54951330 dataset_size: 75586366 - config_name: skr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4274062 num_examples: 144443 download_size: 2585286 dataset_size: 4274062 - config_name: sl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 157883240 num_examples: 4112048 download_size: 118047353 dataset_size: 157883240 - config_name: sli features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13909208 num_examples: 434986 download_size: 9745964 dataset_size: 13909208 - config_name: sm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13984823 num_examples: 436830 download_size: 9817472 dataset_size: 13984823 - config_name: sma features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20653595 num_examples: 630437 download_size: 14902319 dataset_size: 20653595 - config_name: smj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19640206 num_examples: 604326 download_size: 14133964 dataset_size: 19640206 - config_name: smn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10902411 num_examples: 337543 download_size: 7576850 dataset_size: 10902411 - config_name: sms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4462345 num_examples: 149355 download_size: 2741038 dataset_size: 4462345 - config_name: sn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20116601 num_examples: 618231 download_size: 14463728 dataset_size: 20116601 - config_name: sq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 304708913 num_examples: 7311820 download_size: 225592169 dataset_size: 304708913 - config_name: sr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 52787253 num_examples: 1018361 download_size: 31364006 dataset_size: 52787253 - config_name: sr-ec features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9237541 num_examples: 248556 download_size: 5875548 dataset_size: 9237541 - config_name: sr-el features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 48848162 num_examples: 1418824 download_size: 35859120 dataset_size: 48848162 - config_name: srq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12796525 num_examples: 405957 download_size: 8899493 dataset_size: 12796525 - config_name: ss features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13823630 num_examples: 432423 download_size: 9682165 dataset_size: 13823630 - config_name: st features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13938937 num_examples: 435419 download_size: 9785161 dataset_size: 13938937 - config_name: stq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14484394 num_examples: 449885 download_size: 10228446 dataset_size: 14484394 - config_name: su features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20025826 num_examples: 583096 download_size: 14042822 dataset_size: 20025826 - config_name: sv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 339074900 num_examples: 8115455 download_size: 236022796 dataset_size: 339074900 - config_name: sw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 50612064 num_examples: 1465385 download_size: 37096369 dataset_size: 50612064 - config_name: szl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16772062 num_examples: 500107 download_size: 11868254 dataset_size: 16772062 - config_name: szy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4332021 num_examples: 146136 download_size: 2633271 dataset_size: 4332021 - config_name: ta features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31251824 num_examples: 546558 download_size: 15157673 dataset_size: 31251824 - config_name: tay features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4345269 num_examples: 146938 download_size: 2632535 dataset_size: 4345269 - config_name: tcy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8723594 num_examples: 244350 download_size: 4487471 dataset_size: 8723594 - config_name: te features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27587665 num_examples: 569615 download_size: 13669398 dataset_size: 27587665 - config_name: tet features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15092299 num_examples: 466244 download_size: 10702917 dataset_size: 15092299 - config_name: tg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12643125 num_examples: 304625 download_size: 7622522 dataset_size: 12643125 - config_name: tg-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4504034 num_examples: 149533 download_size: 2755000 dataset_size: 4504034 - config_name: tg-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19845835 num_examples: 610020 download_size: 14264492 dataset_size: 19845835 - config_name: th features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32693750 num_examples: 537447 download_size: 15849247 dataset_size: 32693750 - config_name: ti features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4366995 num_examples: 146479 download_size: 2648869 dataset_size: 4366995 - config_name: tk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5797050 num_examples: 184302 download_size: 3728802 dataset_size: 5797050 - config_name: tl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13661554 num_examples: 387377 download_size: 9456413 dataset_size: 13661554 - config_name: tly features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4309748 num_examples: 145312 download_size: 2609307 dataset_size: 4309748 - config_name: tly-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 35 num_examples: 1 download_size: 1793 dataset_size: 35 - config_name: tn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13936132 num_examples: 435219 download_size: 9780279 dataset_size: 13936132 - config_name: to features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13980327 num_examples: 436460 download_size: 9810650 dataset_size: 13980327 - config_name: tpi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14169019 num_examples: 442133 download_size: 9961827 dataset_size: 14169019 - config_name: tr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 72134544 num_examples: 1770267 download_size: 51032484 dataset_size: 72134544 - config_name: tru features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5322844 num_examples: 171327 download_size: 3371105 dataset_size: 5322844 - config_name: trv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 94285 num_examples: 3109 download_size: 65138 dataset_size: 94285 - config_name: ts features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13943481 num_examples: 435408 download_size: 9783789 dataset_size: 13943481 - config_name: tt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24182976 num_examples: 548502 download_size: 14868166 dataset_size: 24182976 - config_name: tt-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4943914 num_examples: 158198 download_size: 3048932 dataset_size: 4943914 - config_name: tt-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13842972 num_examples: 432513 download_size: 9702714 dataset_size: 13842972 - config_name: tum features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13924159 num_examples: 435110 download_size: 9770501 dataset_size: 13924159 - config_name: tw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13830508 num_examples: 432669 download_size: 9688164 dataset_size: 13830508 - config_name: ty features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16816401 num_examples: 507332 download_size: 12098154 dataset_size: 16816401 - config_name: tyv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4583082 num_examples: 149929 download_size: 2779632 dataset_size: 4583082 - config_name: tzm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4253588 num_examples: 144002 download_size: 2569067 dataset_size: 4253588 - config_name: udm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4854947 num_examples: 156300 download_size: 2958444 dataset_size: 4854947 - config_name: ug-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4316690 num_examples: 145443 download_size: 2614962 dataset_size: 4316690 - config_name: ug-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13786474 num_examples: 431056 download_size: 9659723 dataset_size: 13786474 - config_name: uk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 251058352 num_examples: 5108733 download_size: 168140976 dataset_size: 251058352 - config_name: ur features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 57063750 num_examples: 987011 download_size: 28328459 dataset_size: 57063750 - config_name: uz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11731793 num_examples: 344615 download_size: 8102734 dataset_size: 11731793 - config_name: uz-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252574 num_examples: 143981 download_size: 2567325 dataset_size: 4252574 - config_name: ve features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13932174 num_examples: 435216 download_size: 9777266 dataset_size: 13932174 - config_name: vec features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 52081230 num_examples: 1466867 download_size: 37307805 dataset_size: 52081230 - config_name: vep features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6174898 num_examples: 192298 download_size: 3994582 dataset_size: 6174898 - config_name: vi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 246835524 num_examples: 5743737 download_size: 172949263 dataset_size: 246835524 - config_name: vls features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42789297 num_examples: 1239359 download_size: 31228294 dataset_size: 42789297 - config_name: vmf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18352990 num_examples: 555205 download_size: 13289296 dataset_size: 18352990 - config_name: vo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 228352533 num_examples: 5610875 download_size: 155496988 dataset_size: 228352533 - config_name: vot features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5406190 num_examples: 173486 download_size: 3439433 dataset_size: 5406190 - config_name: wa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 49235347 num_examples: 1426584 download_size: 36167816 dataset_size: 49235347 - config_name: war features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 190306474 num_examples: 4449062 download_size: 133786270 dataset_size: 190306474 - config_name: wls features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4033 num_examples: 104 download_size: 5150 dataset_size: 4033 - config_name: wo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40961626 num_examples: 1193626 download_size: 29778666 dataset_size: 40961626 - config_name: wuu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40570130 num_examples: 1127741 download_size: 24209117 dataset_size: 40570130 - config_name: wya features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 28 num_examples: 1 download_size: 1740 dataset_size: 28 - config_name: xal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4475344 num_examples: 149984 download_size: 2722459 dataset_size: 4475344 - config_name: xh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20036194 num_examples: 615514 download_size: 14405310 dataset_size: 20036194 - config_name: xmf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5943645 num_examples: 169507 download_size: 3418593 dataset_size: 5943645 - config_name: xsy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4262789 num_examples: 144305 download_size: 2573349 dataset_size: 4262789 - config_name: yav features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4070 num_examples: 102 download_size: 4718 dataset_size: 4070 - config_name: yi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5495313 num_examples: 170277 download_size: 3373820 dataset_size: 5495313 - config_name: yo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 25424749 num_examples: 724345 download_size: 18086773 dataset_size: 25424749 - config_name: za features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15159230 num_examples: 365892 download_size: 7774767 dataset_size: 15159230 - config_name: zea features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14538518 num_examples: 451577 download_size: 10262897 dataset_size: 14538518 - config_name: zgh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4253917 num_examples: 144006 download_size: 2569373 dataset_size: 4253917 - config_name: zh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 264353677 num_examples: 5424320 download_size: 174420118 dataset_size: 264353677 - config_name: zh-cn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42868611 num_examples: 1158755 download_size: 27243799 dataset_size: 42868611 - config_name: zh-hans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 57233156 num_examples: 1483225 download_size: 36583522 dataset_size: 57233156 - config_name: zh-hant features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53502814 num_examples: 1356560 download_size: 36755083 dataset_size: 53502814 - config_name: zh-hk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15325323 num_examples: 408391 download_size: 10455809 dataset_size: 15325323 - config_name: zh-mo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6568267 num_examples: 180950 download_size: 3547260 dataset_size: 6568267 - config_name: zh-my features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32637498 num_examples: 916876 download_size: 19289581 dataset_size: 32637498 - config_name: zh-sg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 35325327 num_examples: 979652 download_size: 21150070 dataset_size: 35325327 - config_name: zh-tw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17500668 num_examples: 443057 download_size: 11121104 dataset_size: 17500668 - config_name: zh-yue features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1352 num_examples: 30 download_size: 2963 dataset_size: 1352 - config_name: zu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47349379 num_examples: 1380550 download_size: 34649660 dataset_size: 47349379 configs: - config_name: aa data_files: - split: label path: aa/label-* - config_name: ab data_files: - split: label path: ab/label-* - config_name: abs data_files: - split: label path: abs/label-* - config_name: ace data_files: - split: label path: ace/label-* - config_name: ady data_files: - split: label path: ady/label-* - config_name: ady-cyrl data_files: - split: label path: ady-cyrl/label-* - config_name: aeb data_files: - split: label path: aeb/label-* - config_name: aeb-arab data_files: - split: label path: aeb-arab/label-* - config_name: aeb-latn data_files: - split: label path: aeb-latn/label-* - config_name: af data_files: - split: label path: af/label-* - config_name: agq data_files: - split: label path: agq/label-* - config_name: ak data_files: - split: label path: ak/label-* - config_name: aln data_files: - split: label path: aln/label-* - config_name: als data_files: - split: label path: als/label-* - config_name: alt data_files: - split: label path: alt/label-* - config_name: am data_files: - split: label path: am/label-* - config_name: ami data_files: - split: label path: ami/label-* - config_name: an data_files: - split: label path: an/label-* - config_name: ang data_files: - split: label path: ang/label-* - config_name: anp data_files: - split: label path: anp/label-* - config_name: ar data_files: - split: label path: ar/label-* - config_name: arc data_files: - split: label path: arc/label-* - config_name: arn data_files: - split: label path: arn/label-* - config_name: arq data_files: - split: label path: arq/label-* - config_name: ary data_files: - split: label path: ary/label-* - config_name: arz data_files: - split: label path: arz/label-* - config_name: as data_files: - split: label path: as/label-* - config_name: ase data_files: - split: label path: ase/label-* - config_name: ast data_files: - split: label path: ast/label-* - config_name: atj data_files: - split: label path: atj/label-* - config_name: av data_files: - split: label path: av/label-* - config_name: avk data_files: - split: label path: avk/label-* - config_name: awa data_files: - split: label path: awa/label-* - config_name: ay data_files: - split: label path: ay/label-* - config_name: az data_files: - split: label path: az/label-* - config_name: azb data_files: - split: label path: azb/label-* - config_name: ba data_files: - split: label path: ba/label-* - config_name: ban data_files: - split: label path: ban/label-* - config_name: ban-bali data_files: - split: label path: ban-bali/label-* - config_name: bar data_files: - split: label path: bar/label-* - config_name: bbc data_files: - split: label path: bbc/label-* - config_name: bcc data_files: - split: label path: bcc/label-* - config_name: be data_files: - split: label path: be/label-* - config_name: be-tarask data_files: - split: label path: be-tarask/label-* - config_name: bg data_files: - split: label path: bg/label-* - config_name: bgn data_files: - split: label path: bgn/label-* - config_name: bi data_files: - split: label path: bi/label-* - config_name: bjn data_files: - split: label path: bjn/label-* - config_name: bm data_files: - split: label path: bm/label-* - config_name: bn data_files: - split: label path: bn/label-* - config_name: bo data_files: - split: label path: bo/label-* - config_name: bpy data_files: - split: label path: bpy/label-* - config_name: bqi data_files: - split: label path: bqi/label-* - config_name: br data_files: - split: label path: br/label-* - config_name: brh data_files: - split: label path: brh/label-* - config_name: bs data_files: - split: label path: bs/label-* - config_name: btm data_files: - split: label path: btm/label-* - config_name: bto data_files: - split: label path: bto/label-* - config_name: bug data_files: - split: label path: bug/label-* - config_name: bxr data_files: - split: label path: bxr/label-* - config_name: ca data_files: - split: label path: ca/label-* - config_name: cbk-zam data_files: - split: label path: cbk-zam/label-* - config_name: cdo data_files: - split: label path: cdo/label-* - config_name: ce data_files: - split: label path: ce/label-* - config_name: ceb data_files: - split: label path: ceb/label-* - config_name: ch data_files: - split: label path: ch/label-* - config_name: cho data_files: - split: label path: cho/label-* - config_name: chr data_files: - split: label path: chr/label-* - config_name: chy data_files: - split: label path: chy/label-* - config_name: ckb data_files: - split: label path: ckb/label-* - config_name: co data_files: - split: label path: co/label-* - config_name: cps data_files: - split: label path: cps/label-* - config_name: cr data_files: - split: label path: cr/label-* - config_name: crh data_files: - split: label path: crh/label-* - config_name: crh-cyrl data_files: - split: label path: crh-cyrl/label-* - config_name: crh-latn data_files: - split: label path: crh-latn/label-* - config_name: cs data_files: - split: label path: cs/label-* - config_name: csb data_files: - split: label path: csb/label-* - config_name: cv data_files: - split: label path: cv/label-* - config_name: cy data_files: - split: label path: cy/label-* - config_name: da data_files: - split: label path: da/label-* - config_name: dag data_files: - split: label path: dag/label-* - config_name: de data_files: - split: label path: de/label-* - config_name: de-at data_files: - split: label path: de-at/label-* - config_name: de-ch data_files: - split: label path: de-ch/label-* - config_name: de-formal data_files: - split: label path: de-formal/label-* - config_name: din data_files: - split: label path: din/label-* - config_name: diq data_files: - split: label path: diq/label-* - config_name: dsb data_files: - split: label path: dsb/label-* - config_name: dtp data_files: - split: label path: dtp/label-* - config_name: dty data_files: - split: label path: dty/label-* - config_name: dua data_files: - split: label path: dua/label-* - config_name: dv data_files: - split: label path: dv/label-* - config_name: dz data_files: - split: label path: dz/label-* - config_name: ee data_files: - split: label path: ee/label-* - config_name: egl data_files: - split: label path: egl/label-* - config_name: el data_files: - split: label path: el/label-* - config_name: eml data_files: - split: label path: eml/label-* - config_name: en data_files: - split: label path: en/label-* default: true - config_name: en-ca data_files: - split: label path: en-ca/label-* - config_name: en-gb data_files: - split: label path: en-gb/label-* - config_name: en-us data_files: - split: label path: en-us/label-* - config_name: eo data_files: - split: label path: eo/label-* - config_name: es data_files: - split: label path: es/label-* - config_name: es-419 data_files: - split: label path: es-419/label-* - config_name: es-formal data_files: - split: label path: es-formal/label-* - config_name: et data_files: - split: label path: et/label-* - config_name: eu data_files: - split: label path: eu/label-* - config_name: ext data_files: - split: label path: ext/label-* - config_name: fa data_files: - split: label path: fa/label-* - config_name: ff data_files: - split: label path: ff/label-* - config_name: fi data_files: - split: label path: fi/label-* - config_name: fit data_files: - split: label path: fit/label-* - config_name: fj data_files: - split: label path: fj/label-* - config_name: fkv data_files: - split: label path: fkv/label-* - config_name: fo data_files: - split: label path: fo/label-* - config_name: fr data_files: - split: label path: fr/label-* - config_name: frc data_files: - split: label path: frc/label-* - config_name: frp data_files: - split: label path: frp/label-* - config_name: frr data_files: - split: label path: frr/label-* - config_name: fur data_files: - split: label path: fur/label-* - config_name: ga data_files: - split: label path: ga/label-* - config_name: gag data_files: - split: label path: gag/label-* - config_name: gan data_files: - split: label path: gan/label-* - config_name: gan-hans data_files: - split: label path: gan-hans/label-* - config_name: gan-hant data_files: - split: label path: gan-hant/label-* - config_name: gcr data_files: - split: label path: gcr/label-* - config_name: gd data_files: - split: label path: gd/label-* - config_name: gl data_files: - split: label path: gl/label-* - config_name: glk data_files: - split: label path: glk/label-* - config_name: gn data_files: - split: label path: gn/label-* - config_name: gom data_files: - split: label path: gom/label-* - config_name: gom-deva data_files: - split: label path: gom-deva/label-* - config_name: gom-latn data_files: - split: label path: gom-latn/label-* - config_name: gor data_files: - split: label path: gor/label-* - config_name: got data_files: - split: label path: got/label-* - config_name: grc data_files: - split: label path: grc/label-* - config_name: gu data_files: - split: label path: gu/label-* - config_name: guc data_files: - split: label path: guc/label-* - config_name: guw data_files: - split: label path: guw/label-* - config_name: gv data_files: - split: label path: gv/label-* - config_name: ha data_files: - split: label path: ha/label-* - config_name: hak data_files: - split: label path: hak/label-* - config_name: haw data_files: - split: label path: haw/label-* - config_name: he data_files: - split: label path: he/label-* - config_name: hi data_files: - split: label path: hi/label-* - config_name: hif data_files: - split: label path: hif/label-* - config_name: hif-latn data_files: - split: label path: hif-latn/label-* - config_name: hil data_files: - split: label path: hil/label-* - config_name: ho data_files: - split: label path: ho/label-* - config_name: hr data_files: - split: label path: hr/label-* - config_name: hrx data_files: - split: label path: hrx/label-* - config_name: hsb data_files: - split: label path: hsb/label-* - config_name: ht data_files: - split: label path: ht/label-* - config_name: hu data_files: - split: label path: hu/label-* - config_name: hu-formal data_files: - split: label path: hu-formal/label-* - config_name: hy data_files: - split: label path: hy/label-* - config_name: hyw data_files: - split: label path: hyw/label-* - config_name: hz data_files: - split: label path: hz/label-* - config_name: ia data_files: - split: label path: ia/label-* - config_name: id data_files: - split: label path: id/label-* - config_name: ie data_files: - split: label path: ie/label-* - config_name: ig data_files: - split: label path: ig/label-* - config_name: ii data_files: - split: label path: ii/label-* - config_name: ik data_files: - split: label path: ik/label-* - config_name: ike-cans data_files: - split: label path: ike-cans/label-* - config_name: ike-latn data_files: - split: label path: ike-latn/label-* - config_name: ilo data_files: - split: label path: ilo/label-* - config_name: inh data_files: - split: label path: inh/label-* - config_name: io data_files: - split: label path: io/label-* - config_name: is data_files: - split: label path: is/label-* - config_name: it data_files: - split: label path: it/label-* - config_name: iu data_files: - split: label path: iu/label-* - config_name: ja data_files: - split: label path: ja/label-* - config_name: jam data_files: - split: label path: jam/label-* - config_name: jbo data_files: - split: label path: jbo/label-* - config_name: jv data_files: - split: label path: jv/label-* - config_name: ka data_files: - split: label path: ka/label-* - config_name: kaa data_files: - split: label path: kaa/label-* - config_name: kab data_files: - split: label path: kab/label-* - config_name: kbd data_files: - split: label path: kbd/label-* - config_name: kbd-cyrl data_files: - split: label path: kbd-cyrl/label-* - config_name: kbp data_files: - split: label path: kbp/label-* - config_name: kea data_files: - split: label path: kea/label-* - config_name: kg data_files: - split: label path: kg/label-* - config_name: khw data_files: - split: label path: khw/label-* - config_name: ki data_files: - split: label path: ki/label-* - config_name: kj data_files: - split: label path: kj/label-* - config_name: kjp data_files: - split: label path: kjp/label-* - config_name: kk data_files: - split: label path: kk/label-* - config_name: kk-arab data_files: - split: label path: kk-arab/label-* - config_name: kk-kz data_files: - split: label path: kk-kz/label-* - config_name: kk-latn data_files: - split: label path: kk-latn/label-* - config_name: kk-tr data_files: - split: label path: kk-tr/label-* - config_name: ko data_files: - split: label path: ko/label-* - config_name: ko-kp data_files: - split: label path: ko-kp/label-* - config_name: koi data_files: - split: label path: koi/label-* - config_name: kr data_files: - split: label path: kr/label-* - config_name: krc data_files: - split: label path: krc/label-* - config_name: kri data_files: - split: label path: kri/label-* - config_name: krj data_files: - split: label path: krj/label-* - config_name: krl data_files: - split: label path: krl/label-* - config_name: ks data_files: - split: label path: ks/label-* - config_name: ks-deva data_files: - split: label path: ks-deva/label-* - config_name: ksh data_files: - split: label path: ksh/label-* - config_name: ku data_files: - split: label path: ku/label-* - config_name: ku-arab data_files: - split: label path: ku-arab/label-* - config_name: ku-latn data_files: - split: label path: ku-latn/label-* - config_name: kum data_files: - split: label path: kum/label-* - config_name: kv data_files: - split: label path: kv/label-* - config_name: kw data_files: - split: label path: kw/label-* - config_name: ky data_files: - split: label path: ky/label-* - config_name: la data_files: - split: label path: la/label-* - config_name: lad data_files: - split: label path: lad/label-* - config_name: lb data_files: - split: label path: lb/label-* - config_name: lbe data_files: - split: label path: lbe/label-* - config_name: lez data_files: - split: label path: lez/label-* - config_name: lfn data_files: - split: label path: lfn/label-* - config_name: lg data_files: - split: label path: lg/label-* - config_name: li data_files: - split: label path: li/label-* - config_name: lij data_files: - split: label path: lij/label-* - config_name: liv data_files: - split: label path: liv/label-* - config_name: lki data_files: - split: label path: lki/label-* - config_name: lld data_files: - split: label path: lld/label-* - config_name: lmo data_files: - split: label path: lmo/label-* - config_name: ln data_files: - split: label path: ln/label-* - config_name: lo data_files: - split: label path: lo/label-* - config_name: loz data_files: - split: label path: loz/label-* - config_name: lt data_files: - split: label path: lt/label-* - config_name: ltg data_files: - split: label path: ltg/label-* - config_name: lus data_files: - split: label path: lus/label-* - config_name: luz data_files: - split: label path: luz/label-* - config_name: lv data_files: - split: label path: lv/label-* - config_name: lzh data_files: - split: label path: lzh/label-* - config_name: mdf data_files: - split: label path: mdf/label-* - config_name: mg data_files: - split: label path: mg/label-* - config_name: mh data_files: - split: label path: mh/label-* - config_name: mi data_files: - split: label path: mi/label-* - config_name: min data_files: - split: label path: min/label-* - config_name: mk data_files: - split: label path: mk/label-* - config_name: ml data_files: - split: label path: ml/label-* - config_name: mn data_files: - split: label path: mn/label-* - config_name: mni data_files: - split: label path: mni/label-* - config_name: mnw data_files: - split: label path: mnw/label-* - config_name: mo data_files: - split: label path: mo/label-* - config_name: mr data_files: - split: label path: mr/label-* - config_name: mrh data_files: - split: label path: mrh/label-* - config_name: mrj data_files: - split: label path: mrj/label-* - config_name: ms data_files: - split: label path: ms/label-* - config_name: ms-arab data_files: - split: label path: ms-arab/label-* - config_name: mt data_files: - split: label path: mt/label-* - config_name: mus data_files: - split: label path: mus/label-* - config_name: mwl data_files: - split: label path: mwl/label-* - config_name: my data_files: - split: label path: my/label-* - config_name: mzn data_files: - split: label path: mzn/label-* - config_name: na data_files: - split: label path: na/label-* - config_name: nah data_files: - split: label path: nah/label-* - config_name: nan-hani data_files: - split: label path: nan-hani/label-* - config_name: nap data_files: - split: label path: nap/label-* - config_name: nb data_files: - split: label path: nb/label-* - config_name: nds data_files: - split: label path: nds/label-* - config_name: nds-nl data_files: - split: label path: nds-nl/label-* - config_name: ne data_files: - split: label path: ne/label-* - config_name: new data_files: - split: label path: new/label-* - config_name: ng data_files: - split: label path: ng/label-* - config_name: nia data_files: - split: label path: nia/label-* - config_name: niu data_files: - split: label path: niu/label-* - config_name: nl data_files: - split: label path: nl/label-* - config_name: nn data_files: - split: label path: nn/label-* - config_name: 'no' data_files: - split: label path: no/label-* - config_name: nod data_files: - split: label path: nod/label-* - config_name: nov data_files: - split: label path: nov/label-* - config_name: nqo data_files: - split: label path: nqo/label-* - config_name: nrm data_files: - split: label path: nrm/label-* - config_name: nso data_files: - split: label path: nso/label-* - config_name: nv data_files: - split: label path: nv/label-* - config_name: ny data_files: - split: label path: ny/label-* - config_name: nys data_files: - split: label path: nys/label-* - config_name: oc data_files: - split: label path: oc/label-* - config_name: olo data_files: - split: label path: olo/label-* - config_name: om data_files: - split: label path: om/label-* - config_name: or data_files: - split: label path: or/label-* - config_name: os data_files: - split: label path: os/label-* - config_name: ota data_files: - split: label path: ota/label-* - config_name: pa data_files: - split: label path: pa/label-* - config_name: pam data_files: - split: label path: pam/label-* - config_name: pap data_files: - split: label path: pap/label-* - config_name: pcd data_files: - split: label path: pcd/label-* - config_name: pdc data_files: - split: label path: pdc/label-* - config_name: pdt data_files: - split: label path: pdt/label-* - config_name: pfl data_files: - split: label path: pfl/label-* - config_name: pi data_files: - split: label path: pi/label-* - config_name: pih data_files: - split: label path: pih/label-* - config_name: pl data_files: - split: label path: pl/label-* - config_name: pms data_files: - split: label path: pms/label-* - config_name: pnb data_files: - split: label path: pnb/label-* - config_name: pnt data_files: - split: label path: pnt/label-* - config_name: prg data_files: - split: label path: prg/label-* - config_name: ps data_files: - split: label path: ps/label-* - config_name: pt data_files: - split: label path: pt/label-* - config_name: pt-br data_files: - split: label path: pt-br/label-* - config_name: pwn data_files: - split: label path: pwn/label-* - config_name: qu data_files: - split: label path: qu/label-* - config_name: quc data_files: - split: label path: quc/label-* - config_name: qug data_files: - split: label path: qug/label-* - config_name: rgn data_files: - split: label path: rgn/label-* - config_name: rif data_files: - split: label path: rif/label-* - config_name: rm data_files: - split: label path: rm/label-* - config_name: rmc data_files: - split: label path: rmc/label-* - config_name: rmy data_files: - split: label path: rmy/label-* - config_name: rn data_files: - split: label path: rn/label-* - config_name: ro data_files: - split: label path: ro/label-* - config_name: roa-tara data_files: - split: label path: roa-tara/label-* - config_name: ru data_files: - split: label path: ru/label-* - config_name: rue data_files: - split: label path: rue/label-* - config_name: rup data_files: - split: label path: rup/label-* - config_name: ruq-cyrl data_files: - split: label path: ruq-cyrl/label-* - config_name: ruq-latn data_files: - split: label path: ruq-latn/label-* - config_name: rw data_files: - split: label path: rw/label-* - config_name: rwr data_files: - split: label path: rwr/label-* - config_name: ryu data_files: - split: label path: ryu/label-* - config_name: sa data_files: - split: label path: sa/label-* - config_name: sat data_files: - split: label path: sat/label-* - config_name: sc data_files: - split: label path: sc/label-* - config_name: scn data_files: - split: label path: scn/label-* - config_name: sco data_files: - split: label path: sco/label-* - config_name: sd data_files: - split: label path: sd/label-* - config_name: sdc data_files: - split: label path: sdc/label-* - config_name: se data_files: - split: label path: se/label-* - config_name: sei data_files: - split: label path: sei/label-* - config_name: sg data_files: - split: label path: sg/label-* - config_name: sh data_files: - split: label path: sh/label-* - config_name: shi-latn data_files: - split: label path: shi-latn/label-* - config_name: shi-tfng data_files: - split: label path: shi-tfng/label-* - config_name: shn data_files: - split: label path: shn/label-* - config_name: shy-latn data_files: - split: label path: shy-latn/label-* - config_name: si data_files: - split: label path: si/label-* - config_name: sjd data_files: - split: label path: sjd/label-* - config_name: sje data_files: - split: label path: sje/label-* - config_name: sju data_files: - split: label path: sju/label-* - config_name: sk data_files: - split: label path: sk/label-* - config_name: skr data_files: - split: label path: skr/label-* - config_name: sl data_files: - split: label path: sl/label-* - config_name: sli data_files: - split: label path: sli/label-* - config_name: sm data_files: - split: label path: sm/label-* - config_name: sma data_files: - split: label path: sma/label-* - config_name: smj data_files: - split: label path: smj/label-* - config_name: smn data_files: - split: label path: smn/label-* - config_name: sms data_files: - split: label path: sms/label-* - config_name: sn data_files: - split: label path: sn/label-* - config_name: sq data_files: - split: label path: sq/label-* - config_name: sr data_files: - split: label path: sr/label-* - config_name: sr-ec data_files: - split: label path: sr-ec/label-* - config_name: sr-el data_files: - split: label path: sr-el/label-* - config_name: srq data_files: - split: label path: srq/label-* - config_name: ss data_files: - split: label path: ss/label-* - config_name: st data_files: - split: label path: st/label-* - config_name: stq data_files: - split: label path: stq/label-* - config_name: su data_files: - split: label path: su/label-* - config_name: sv data_files: - split: label path: sv/label-* - config_name: sw data_files: - split: label path: sw/label-* - config_name: szl data_files: - split: label path: szl/label-* - config_name: szy data_files: - split: label path: szy/label-* - config_name: ta data_files: - split: label path: ta/label-* - config_name: tay data_files: - split: label path: tay/label-* - config_name: tcy data_files: - split: label path: tcy/label-* - config_name: te data_files: - split: label path: te/label-* - config_name: tet data_files: - split: label path: tet/label-* - config_name: tg data_files: - split: label path: tg/label-* - config_name: tg-cyrl data_files: - split: label path: tg-cyrl/label-* - config_name: tg-latn data_files: - split: label path: tg-latn/label-* - config_name: th data_files: - split: label path: th/label-* - config_name: ti data_files: - split: label path: ti/label-* - config_name: tk data_files: - split: label path: tk/label-* - config_name: tl data_files: - split: label path: tl/label-* - config_name: tly data_files: - split: label path: tly/label-* - config_name: tly-cyrl data_files: - split: label path: tly-cyrl/label-* - config_name: tn data_files: - split: label path: tn/label-* - config_name: to data_files: - split: label path: to/label-* - config_name: tpi data_files: - split: label path: tpi/label-* - config_name: tr data_files: - split: label path: tr/label-* - config_name: tru data_files: - split: label path: tru/label-* - config_name: trv data_files: - split: label path: trv/label-* - config_name: ts data_files: - split: label path: ts/label-* - config_name: tt data_files: - split: label path: tt/label-* - config_name: tt-cyrl data_files: - split: label path: tt-cyrl/label-* - config_name: tt-latn data_files: - split: label path: tt-latn/label-* - config_name: tum data_files: - split: label path: tum/label-* - config_name: tw data_files: - split: label path: tw/label-* - config_name: ty data_files: - split: label path: ty/label-* - config_name: tyv data_files: - split: label path: tyv/label-* - config_name: tzm data_files: - split: label path: tzm/label-* - config_name: udm data_files: - split: label path: udm/label-* - config_name: ug-arab data_files: - split: label path: ug-arab/label-* - config_name: ug-latn data_files: - split: label path: ug-latn/label-* - config_name: uk data_files: - split: label path: uk/label-* - config_name: ur data_files: - split: label path: ur/label-* - config_name: uz data_files: - split: label path: uz/label-* - config_name: uz-cyrl data_files: - split: label path: uz-cyrl/label-* - config_name: ve data_files: - split: label path: ve/label-* - config_name: vec data_files: - split: label path: vec/label-* - config_name: vep data_files: - split: label path: vep/label-* - config_name: vi data_files: - split: label path: vi/label-* - config_name: vls data_files: - split: label path: vls/label-* - config_name: vmf data_files: - split: label path: vmf/label-* - config_name: vo data_files: - split: label path: vo/label-* - config_name: vot data_files: - split: label path: vot/label-* - config_name: wa data_files: - split: label path: wa/label-* - config_name: war data_files: - split: label path: war/label-* - config_name: wls data_files: - split: label path: wls/label-* - config_name: wo data_files: - split: label path: wo/label-* - config_name: wuu data_files: - split: label path: wuu/label-* - config_name: wya data_files: - split: label path: wya/label-* - config_name: xal data_files: - split: label path: xal/label-* - config_name: xh data_files: - split: label path: xh/label-* - config_name: xmf data_files: - split: label path: xmf/label-* - config_name: xsy data_files: - split: label path: xsy/label-* - config_name: yav data_files: - split: label path: yav/label-* - config_name: yi data_files: - split: label path: yi/label-* - config_name: yo data_files: - split: label path: yo/label-* - config_name: za data_files: - split: label path: za/label-* - config_name: zea data_files: - split: label path: zea/label-* - config_name: zgh data_files: - split: label path: zgh/label-* - config_name: zh data_files: - split: label path: zh/label-* - config_name: zh-cn data_files: - split: label path: zh-cn/label-* - config_name: zh-hans data_files: - split: label path: zh-hans/label-* - config_name: zh-hant data_files: - split: label path: zh-hant/label-* - config_name: zh-hk data_files: - split: label path: zh-hk/label-* - config_name: zh-mo data_files: - split: label path: zh-mo/label-* - config_name: zh-my data_files: - split: label path: zh-my/label-* - config_name: zh-sg data_files: - split: label path: zh-sg/label-* - config_name: zh-tw data_files: - split: label path: zh-tw/label-* - config_name: zh-yue data_files: - split: label path: zh-yue/label-* - config_name: zu data_files: - split: label path: zu/label-* task_categories: - translation - text2text-generation language: - en - fr - de - ja - zh - hi - ar - bn - ru - es --- # Wikidata Labels Large parallel corpus for machine translation - Entity label data extracted from Wikidata (2022-01-03), filtered for item entities only - Only download the languages you need with `datasets>=2.14.0` - Similar dataset: https://huggingface.co/datasets/wmt/wikititles (18 Wikipedia titles pairs instead of all Wikidata entities) ## Dataset Details ### Dataset Sources - Wikidata JSON dump (wikidata-20220103-all.json.gz) https://www.wikidata.org/wiki/Wikidata:Database_download ## Uses You can generate parallel text examples from this dataset like below: ```python from datasets import load_dataset import pandas as pd def parallel_labels(lang_codes: list, how="inner", repo_id="rayliuca/wikidata_entity_label", merge_config={}, datasets_config={}) -> pd.DataFrame: out_df = None for lc in lang_codes: dataset = load_dataset(repo_id, lc, **datasets_config) dataset_df = dataset['label'].to_pandas().rename(columns={"label":lc}).drop(columns=['lastrevid']) if out_df is None: out_df = dataset_df else: out_df = out_df.merge( dataset_df, on='wikidata_id', how=how, **merge_config ) return out_df # Note: the "en" subset is >4GB parallel_labels(['en', 'fr', 'ja', 'zh']).head() ``` ### Output | | wikidata_id | en | fr | ja | zh | |---:|:--------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------|:---------------------------------------------| | 0 | Q109739412 | SARS-CoV-2 Omicron variant | variant Omicron du SARS-CoV-2 | SARSコロナウイルス2-オミクロン株 | 嚴重急性呼吸道症候群冠狀病毒2型Omicron變異株 | | 1 | Q108460606 | Ulughbegsaurus | Ulughbegsaurus | ウルグベグサウルス | 兀魯伯龍屬 | | 2 | Q108556886 | AUKUS | AUKUS | AUKUS | AUKUS | | 3 | Q106496152 | Claude Joseph | Claude Joseph | クロード・ジョゼフ | 克洛德·约瑟夫 | | 4 | Q105519361 | The World's Finest Assassin Gets Reincarnated in a Different World as an Aristocrat | The World's Finest Assassin Gets Reincarnated in Another World as an Aristocrat | 世界最高の暗殺者、異世界貴族に転生する | 世界頂尖的暗殺者轉生為異世界貴族 | Note: this example table above shows a quirk(?) of the Wiki data. The French Wikipedia page [The World's Finest Assassin Gets Reincarnated in Another World as an Aristocrat](https://fr.wikipedia.org/wiki/The_World%27s_Finest_Assassin_Gets_Reincarnated_in_Another_World_as_an_Aristocrat) uses English for its title. While this could be disadvantageous for direct translation training, it also provides insights into how native speakers might call this entity instead of the literal translation on the Wiki page as well ## Dataset Structure Each language has its own subset (aka config), which means you only have to download the languages you need with `datasets>=2.14.0` Each subset has these fields: - wikidata_id - lastrevid - label ## Dataset Creation #### Data Collection and Processing - Filtered for item entities only - Ignored the descriptions as those texts are not very parallel ## Bias, Risks, and Limitations - Might be slightly outdated (2022) - Popular languages have more entries - Labels are not guaranteed to be literal translations (see examples above)

Intraferon/iNat-XC-1000

Intraferon

--- language: - en pretty_name: i --- # iNat-XC-1000 A multi-modal bird species classification dataset consisting of the sightings of 1000 bird species from two citizen science projects: [iNaturalist](https://www.inaturalist.org/) and [Xeno Canto](https://xeno-canto.org/).

airtrain-ai/fineweb-edu-fortified

airtrain-ai

--- language: - en license: odc-by task_categories: - text-generation dataset_info: - config_name: CC-MAIN-2013-20 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 71683996286 num_examples: 10800000 download_size: 55571546426 dataset_size: 71683996286 - config_name: CC-MAIN-2013-48 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 38878994623 num_examples: 5800000 download_size: 30087644388 dataset_size: 38878994623 - config_name: CC-MAIN-2014-10 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 24971658588 num_examples: 3550000 download_size: 19058832929 dataset_size: 24971658588 - config_name: CC-MAIN-2014-15 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 13615746365 num_examples: 1850000 download_size: 10299687552 dataset_size: 13615746365 - config_name: CC-MAIN-2014-23 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21798450754 num_examples: 3100000 download_size: 16663899441 dataset_size: 21798450754 - config_name: CC-MAIN-2014-35 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 10954201796 num_examples: 1500000 download_size: 8309419357 dataset_size: 10954201796 - config_name: CC-MAIN-2014-41 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 11392615401 num_examples: 1600000 download_size: 8694382261 dataset_size: 11392615401 - config_name: CC-MAIN-2014-42 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 8491740156 num_examples: 1150000 download_size: 6430841610 dataset_size: 8491740156 - config_name: CC-MAIN-2014-49 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7754099049 num_examples: 1050000 download_size: 5866979308 dataset_size: 7754099049 - config_name: CC-MAIN-2014-52 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 9953666568 num_examples: 1350000 download_size: 7521103037 dataset_size: 9953666568 - config_name: CC-MAIN-2015-06 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 8988649992 num_examples: 1200000 download_size: 6771650647 dataset_size: 8988649992 - config_name: CC-MAIN-2015-11 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 9212466984 num_examples: 1200000 download_size: 6893305603 dataset_size: 9212466984 - config_name: CC-MAIN-2015-14 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7773258320 num_examples: 1000000 download_size: 5810026390 dataset_size: 7773258320 - config_name: CC-MAIN-2015-18 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 9906342182 num_examples: 1300000 download_size: 7420897339 dataset_size: 9906342182 - config_name: CC-MAIN-2015-22 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 8677092389 num_examples: 1100000 download_size: 6445775687 dataset_size: 8677092389 - config_name: CC-MAIN-2015-27 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 8168934142 num_examples: 1050000 download_size: 6095866065 dataset_size: 8168934142 - config_name: CC-MAIN-2015-32 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7248096143 num_examples: 950000 download_size: 5438870914 dataset_size: 7248096143 - config_name: CC-MAIN-2015-35 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7905807405 num_examples: 1000000 download_size: 5886313414 dataset_size: 7905807405 - config_name: CC-MAIN-2015-40 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 6756795023 num_examples: 850000 download_size: 5020668048 dataset_size: 6756795023 - config_name: CC-MAIN-2015-48 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 9500987324 num_examples: 1200000 download_size: 7050820902 dataset_size: 9500987324 - config_name: CC-MAIN-2016-07 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 10612088943 num_examples: 1300000 download_size: 7816414470 dataset_size: 10612088943 - config_name: CC-MAIN-2016-18 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7478953157 num_examples: 1050000 download_size: 5691425154 dataset_size: 7478953157 - config_name: CC-MAIN-2016-22 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 7617762727 num_examples: 1050000 download_size: 5760598348 dataset_size: 7617762727 - config_name: CC-MAIN-2016-26 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 4620338482 num_examples: 650000 download_size: 3516183695 dataset_size: 4620338482 - config_name: CC-MAIN-2016-30 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 10574077837 num_examples: 1250000 download_size: 7732067436 dataset_size: 10574077837 - config_name: CC-MAIN-2016-36 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 8503905267 num_examples: 1000000 download_size: 6208206855 dataset_size: 8503905267 - config_name: CC-MAIN-2016-40 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 15377835627 num_examples: 2350000 download_size: 11940941268 dataset_size: 15377835627 - config_name: CC-MAIN-2016-44 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 29529872165 num_examples: 4800000 download_size: 23162984623 dataset_size: 29529872165 - config_name: CC-MAIN-2016-50 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 20468372716 num_examples: 3050000 download_size: 15709742655 dataset_size: 20468372716 - config_name: CC-MAIN-2017-04 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21037186856 num_examples: 3050000 download_size: 16038345746 dataset_size: 21037186856 - config_name: CC-MAIN-2017-09 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 24443091987 num_examples: 3450000 download_size: 18578003959 dataset_size: 24443091987 - config_name: CC-MAIN-2017-13 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 42541966320 num_examples: 6350000 download_size: 32897843366 dataset_size: 42541966320 - config_name: CC-MAIN-2017-17 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 28067316341 num_examples: 4200000 download_size: 21670006912 dataset_size: 28067316341 - config_name: CC-MAIN-2017-22 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21612347473 num_examples: 3250000 download_size: 16727380174 dataset_size: 21612347473 - config_name: CC-MAIN-2017-26 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 26930164929 num_examples: 4150000 download_size: 21000453887 dataset_size: 26930164929 - config_name: CC-MAIN-2017-30 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 19514567064 num_examples: 3050000 download_size: 15274197942 dataset_size: 19514567064 - config_name: CC-MAIN-2017-34 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21825880789 num_examples: 3450000 download_size: 17131331406 dataset_size: 21825880789 - config_name: CC-MAIN-2017-39 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21861199076 num_examples: 3250000 download_size: 16864955620 dataset_size: 21861199076 - config_name: CC-MAIN-2017-43 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22225780468 num_examples: 3250000 download_size: 17081326644 dataset_size: 22225780468 - config_name: CC-MAIN-2017-47 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 20302441730 num_examples: 2950000 download_size: 15588692671 dataset_size: 20302441730 - config_name: CC-MAIN-2017-51 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 17337207614 num_examples: 2550000 download_size: 13346917136 dataset_size: 17337207614 - config_name: CC-MAIN-2018-05 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22738512950 num_examples: 3450000 download_size: 17607554751 dataset_size: 22738512950 - config_name: CC-MAIN-2018-09 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 23340323268 num_examples: 3600000 download_size: 18151119519 dataset_size: 23340323268 - config_name: CC-MAIN-2018-13 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 19001159420 num_examples: 2900000 download_size: 14753194653 dataset_size: 19001159420 - config_name: CC-MAIN-2018-17 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 17258341719 num_examples: 2600000 download_size: 13340501927 dataset_size: 17258341719 - config_name: CC-MAIN-2018-22 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 17491169826 num_examples: 2600000 download_size: 13470743712 dataset_size: 17491169826 - config_name: CC-MAIN-2018-26 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21455735998 num_examples: 3100000 download_size: 16280241314 dataset_size: 21455735998 - config_name: CC-MAIN-2018-30 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 18192174874 num_examples: 2500000 download_size: 13725747144 dataset_size: 18192174874 - config_name: CC-MAIN-2018-34 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 15796036932 num_examples: 2200000 download_size: 11987788874 dataset_size: 15796036932 - config_name: CC-MAIN-2018-39 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 16307757771 num_examples: 2200000 download_size: 12290791012 dataset_size: 16307757771 - config_name: CC-MAIN-2018-43 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 25677124234 num_examples: 3800000 download_size: 19573087580 dataset_size: 25677124234 - config_name: CC-MAIN-2018-47 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22875798193 num_examples: 3150000 download_size: 17281464409 dataset_size: 22875798193 - config_name: CC-MAIN-2018-51 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22594268378 num_examples: 3300000 download_size: 17343595987 dataset_size: 22594268378 - config_name: CC-MAIN-2019-04 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21133044139 num_examples: 3050000 download_size: 16192299666 dataset_size: 21133044139 - config_name: CC-MAIN-2019-09 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 20593069774 num_examples: 2850000 download_size: 15604520079 dataset_size: 20593069774 - config_name: CC-MAIN-2019-13 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 18350086234 num_examples: 2500000 download_size: 13859628789 dataset_size: 18350086234 - config_name: CC-MAIN-2019-18 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 19748675634 num_examples: 2650000 download_size: 14875559796 dataset_size: 19748675634 - config_name: CC-MAIN-2019-22 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22315609811 num_examples: 3100000 download_size: 16925720280 dataset_size: 22315609811 - config_name: CC-MAIN-2019-26 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 20009950205 num_examples: 2750000 download_size: 15138826344 dataset_size: 20009950205 - config_name: CC-MAIN-2019-30 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 20153093525 num_examples: 2750000 download_size: 15229175301 dataset_size: 20153093525 - config_name: CC-MAIN-2019-35 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 23793900737 num_examples: 3300000 download_size: 18011655759 dataset_size: 23793900737 - config_name: CC-MAIN-2019-39 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21250081982 num_examples: 2950000 download_size: 16107325180 dataset_size: 21250081982 - config_name: CC-MAIN-2019-43 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 23381976513 num_examples: 3150000 download_size: 17578322332 dataset_size: 23381976513 - config_name: CC-MAIN-2019-47 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 22916970895 num_examples: 3150000 download_size: 17302792952 dataset_size: 22916970895 - config_name: CC-MAIN-2019-51 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 19001480990 num_examples: 2600000 download_size: 14340161761 dataset_size: 19001480990 - config_name: CC-MAIN-2020-05 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21571233444 num_examples: 2950000 download_size: 16258182796 dataset_size: 21571233444 - config_name: CC-MAIN-2020-10 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 21550911640 num_examples: 3000000 download_size: 16304815033 dataset_size: 21550911640 - config_name: CC-MAIN-2020-16 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 23381117349 num_examples: 3300000 download_size: 17744530068 dataset_size: 23381117349 - config_name: CC-MAIN-2020-24 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 25046680820 num_examples: 3550000 download_size: 19043052442 dataset_size: 25046680820 - config_name: CC-MAIN-2020-29 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 28072475139 num_examples: 3900000 download_size: 21219908593 dataset_size: 28072475139 - config_name: CC-MAIN-2020-34 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 23905419397 num_examples: 3300000 download_size: 18053065929 dataset_size: 23905419397 - config_name: CC-MAIN-2020-40 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 31964517781 num_examples: 4650000 download_size: 24445166342 dataset_size: 31964517781 - config_name: CC-MAIN-2020-45 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 28978958859 num_examples: 4150000 download_size: 22052543740 dataset_size: 28978958859 - config_name: CC-MAIN-2020-50 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 25828281117 num_examples: 3650000 download_size: 19596280713 dataset_size: 25828281117 - config_name: CC-MAIN-2021-04 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 32044317476 num_examples: 4450000 download_size: 24218057264 dataset_size: 32044317476 - config_name: CC-MAIN-2021-10 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 30664456445 num_examples: 4200000 download_size: 23053325617 dataset_size: 30664456445 - config_name: CC-MAIN-2021-17 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 33620957572 num_examples: 4450000 download_size: 25055730596 dataset_size: 33620957572 - config_name: CC-MAIN-2021-21 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 26740503282 num_examples: 3600000 download_size: 20011648584 dataset_size: 26740503282 - config_name: CC-MAIN-2021-25 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 29160290793 num_examples: 3950000 download_size: 21855396161 dataset_size: 29160290793 - config_name: CC-MAIN-2021-31 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 29149182919 num_examples: 3900000 download_size: 21785469714 dataset_size: 29149182919 - config_name: CC-MAIN-2021-39 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 33379845273 num_examples: 4550000 download_size: 25057576194 dataset_size: 33379845273 - config_name: CC-MAIN-2021-43 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 34332026077 num_examples: 4700000 download_size: 25789733401 dataset_size: 34332026077 - config_name: CC-MAIN-2021-49 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 31418299354 num_examples: 4350000 download_size: 23666249860 dataset_size: 31418299354 - config_name: CC-MAIN-2022-05 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 32596625853 num_examples: 4450000 download_size: 24458356127 dataset_size: 32596625853 - config_name: CC-MAIN-2022-21 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 47752322889 num_examples: 6550000 download_size: 35853678975 dataset_size: 47752322889 - config_name: CC-MAIN-2022-27 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 40292830914 num_examples: 5550000 download_size: 30279346466 dataset_size: 40292830914 - config_name: CC-MAIN-2022-33 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 34010483286 num_examples: 4750000 download_size: 25633769458 dataset_size: 34010483286 - config_name: CC-MAIN-2022-40 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 39211229907 num_examples: 5350000 download_size: 29318062267 dataset_size: 39211229907 - config_name: CC-MAIN-2022-49 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 40322136408 num_examples: 5450000 download_size: 30095433549 dataset_size: 40322136408 - config_name: CC-MAIN-2023-06 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 39078745132 num_examples: 5250000 download_size: 29058170760 dataset_size: 39078745132 - config_name: CC-MAIN-2023-14 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 76461834465 num_examples: 10050000 download_size: 56751401774 dataset_size: 76461834465 - config_name: CC-MAIN-2023-23 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 76112971386 num_examples: 9950000 download_size: 56347776355 dataset_size: 76112971386 - config_name: CC-MAIN-2023-40 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 63452197995 num_examples: 8100000 download_size: 46078925605 dataset_size: 63452197995 - config_name: CC-MAIN-2023-50 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 63566623396 num_examples: 8200000 download_size: 46245587660 dataset_size: 63566623396 - config_name: CC-MAIN-2024-10 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 - name: embedding sequence: float32 - name: count dtype: int64 splits: - name: train num_bytes: 43172700112 num_examples: 5750000 download_size: 31501561162 dataset_size: 43172700112 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: data/CC-MAIN-2013-20/train-* - config_name: CC-MAIN-2013-48 data_files: - split: train path: data/CC-MAIN-2013-48/train-* - config_name: CC-MAIN-2014-10 data_files: - split: train path: data/CC-MAIN-2014-10/train-* - config_name: CC-MAIN-2014-15 data_files: - split: train path: data/CC-MAIN-2014-15/train-* - config_name: CC-MAIN-2014-23 data_files: - split: train path: data/CC-MAIN-2014-23/train-* - config_name: CC-MAIN-2014-35 data_files: - split: train path: data/CC-MAIN-2014-35/train-* - config_name: CC-MAIN-2014-41 data_files: - split: train path: data/CC-MAIN-2014-41/train-* - config_name: CC-MAIN-2014-42 data_files: - split: train path: data/CC-MAIN-2014-42/train-* - config_name: CC-MAIN-2014-49 data_files: - split: train path: data/CC-MAIN-2014-49/train-* - config_name: CC-MAIN-2014-52 data_files: - split: train path: data/CC-MAIN-2014-52/train-* - config_name: CC-MAIN-2015-06 data_files: - split: train path: data/CC-MAIN-2015-06/train-* - config_name: CC-MAIN-2015-11 data_files: - split: train path: data/CC-MAIN-2015-11/train-* - config_name: CC-MAIN-2015-14 data_files: - split: train path: data/CC-MAIN-2015-14/train-* - config_name: CC-MAIN-2015-18 data_files: - split: train path: data/CC-MAIN-2015-18/train-* - config_name: CC-MAIN-2015-22 data_files: - split: train path: data/CC-MAIN-2015-22/train-* - config_name: CC-MAIN-2015-27 data_files: - split: train path: data/CC-MAIN-2015-27/train-* - config_name: CC-MAIN-2015-32 data_files: - split: train path: data/CC-MAIN-2015-32/train-* - config_name: CC-MAIN-2015-35 data_files: - split: train path: data/CC-MAIN-2015-35/train-* - config_name: CC-MAIN-2015-40 data_files: - split: train path: data/CC-MAIN-2015-40/train-* - config_name: CC-MAIN-2015-48 data_files: - split: train path: data/CC-MAIN-2015-48/train-* - config_name: CC-MAIN-2016-07 data_files: - split: train path: data/CC-MAIN-2016-07/train-* - config_name: CC-MAIN-2016-18 data_files: - split: train path: data/CC-MAIN-2016-18/train-* - config_name: CC-MAIN-2016-22 data_files: - split: train path: data/CC-MAIN-2016-22/train-* - config_name: CC-MAIN-2016-26 data_files: - split: train path: data/CC-MAIN-2016-26/train-* - config_name: CC-MAIN-2016-30 data_files: - split: train path: data/CC-MAIN-2016-30/train-* - config_name: CC-MAIN-2016-36 data_files: - split: train path: data/CC-MAIN-2016-36/train-* - config_name: CC-MAIN-2016-40 data_files: - split: train path: data/CC-MAIN-2016-40/train-* - config_name: CC-MAIN-2016-44 data_files: - split: train path: data/CC-MAIN-2016-44/train-* - config_name: CC-MAIN-2016-50 data_files: - split: train path: data/CC-MAIN-2016-50/train-* - config_name: CC-MAIN-2017-04 data_files: - split: train path: data/CC-MAIN-2017-04/train-* - config_name: CC-MAIN-2017-09 data_files: - split: train path: data/CC-MAIN-2017-09/train-* - config_name: CC-MAIN-2017-13 data_files: - split: train path: data/CC-MAIN-2017-13/train-* - config_name: CC-MAIN-2017-17 data_files: - split: train path: data/CC-MAIN-2017-17/train-* - config_name: CC-MAIN-2017-22 data_files: - split: train path: data/CC-MAIN-2017-22/train-* - config_name: CC-MAIN-2017-26 data_files: - split: train path: data/CC-MAIN-2017-26/train-* - config_name: CC-MAIN-2017-30 data_files: - split: train path: data/CC-MAIN-2017-30/train-* - config_name: CC-MAIN-2017-34 data_files: - split: train path: data/CC-MAIN-2017-34/train-* - config_name: CC-MAIN-2017-39 data_files: - split: train path: data/CC-MAIN-2017-39/train-* - config_name: CC-MAIN-2017-43 data_files: - split: train path: data/CC-MAIN-2017-43/train-* - config_name: CC-MAIN-2017-47 data_files: - split: train path: data/CC-MAIN-2017-47/train-* - config_name: CC-MAIN-2017-51 data_files: - split: train path: data/CC-MAIN-2017-51/train-* - config_name: CC-MAIN-2018-05 data_files: - split: train path: data/CC-MAIN-2018-05/train-* - config_name: CC-MAIN-2018-09 data_files: - split: train path: data/CC-MAIN-2018-09/train-* - config_name: CC-MAIN-2018-13 data_files: - split: train path: data/CC-MAIN-2018-13/train-* - config_name: CC-MAIN-2018-17 data_files: - split: train path: data/CC-MAIN-2018-17/train-* - config_name: CC-MAIN-2018-22 data_files: - split: train path: data/CC-MAIN-2018-22/train-* - config_name: CC-MAIN-2018-26 data_files: - split: train path: data/CC-MAIN-2018-26/train-* - config_name: CC-MAIN-2018-30 data_files: - split: train path: data/CC-MAIN-2018-30/train-* - config_name: CC-MAIN-2018-34 data_files: - split: train path: data/CC-MAIN-2018-34/train-* - config_name: CC-MAIN-2018-39 data_files: - split: train path: data/CC-MAIN-2018-39/train-* - config_name: CC-MAIN-2018-43 data_files: - split: train path: data/CC-MAIN-2018-43/train-* - config_name: CC-MAIN-2018-47 data_files: - split: train path: data/CC-MAIN-2018-47/train-* - config_name: CC-MAIN-2018-51 data_files: - split: train path: data/CC-MAIN-2018-51/train-* - config_name: CC-MAIN-2019-04 data_files: - split: train path: data/CC-MAIN-2019-04/train-* - config_name: CC-MAIN-2019-09 data_files: - split: train path: data/CC-MAIN-2019-09/train-* - config_name: CC-MAIN-2019-13 data_files: - split: train path: data/CC-MAIN-2019-13/train-* - config_name: CC-MAIN-2019-18 data_files: - split: train path: data/CC-MAIN-2019-18/train-* - config_name: CC-MAIN-2019-22 data_files: - split: train path: data/CC-MAIN-2019-22/train-* - config_name: CC-MAIN-2019-26 data_files: - split: train path: data/CC-MAIN-2019-26/train-* - config_name: CC-MAIN-2019-30 data_files: - split: train path: data/CC-MAIN-2019-30/train-* - config_name: CC-MAIN-2019-35 data_files: - split: train path: data/CC-MAIN-2019-35/train-* - config_name: CC-MAIN-2019-39 data_files: - split: train path: data/CC-MAIN-2019-39/train-* - config_name: CC-MAIN-2019-43 data_files: - split: train path: data/CC-MAIN-2019-43/train-* - config_name: CC-MAIN-2019-47 data_files: - split: train path: data/CC-MAIN-2019-47/train-* - config_name: CC-MAIN-2019-51 data_files: - split: train path: data/CC-MAIN-2019-51/train-* - config_name: CC-MAIN-2020-05 data_files: - split: train path: data/CC-MAIN-2020-05/train-* - config_name: CC-MAIN-2020-10 data_files: - split: train path: data/CC-MAIN-2020-10/train-* - config_name: CC-MAIN-2020-16 data_files: - split: train path: data/CC-MAIN-2020-16/train-* - config_name: CC-MAIN-2020-24 data_files: - split: train path: data/CC-MAIN-2020-24/train-* - config_name: CC-MAIN-2020-29 data_files: - split: train path: data/CC-MAIN-2020-29/train-* - config_name: CC-MAIN-2020-34 data_files: - split: train path: data/CC-MAIN-2020-34/train-* - config_name: CC-MAIN-2020-40 data_files: - split: train path: data/CC-MAIN-2020-40/train-* - config_name: CC-MAIN-2020-45 data_files: - split: train path: data/CC-MAIN-2020-45/train-* - config_name: CC-MAIN-2020-50 data_files: - split: train path: data/CC-MAIN-2020-50/train-* - config_name: CC-MAIN-2021-04 data_files: - split: train path: data/CC-MAIN-2021-04/train-* - config_name: CC-MAIN-2021-10 data_files: - split: train path: data/CC-MAIN-2021-10/train-* - config_name: CC-MAIN-2021-17 data_files: - split: train path: data/CC-MAIN-2021-17/train-* - config_name: CC-MAIN-2021-21 data_files: - split: train path: data/CC-MAIN-2021-21/train-* - config_name: CC-MAIN-2021-25 data_files: - split: train path: data/CC-MAIN-2021-25/train-* - config_name: CC-MAIN-2021-31 data_files: - split: train path: data/CC-MAIN-2021-31/train-* - config_name: CC-MAIN-2021-39 data_files: - split: train path: data/CC-MAIN-2021-39/train-* - config_name: CC-MAIN-2021-43 data_files: - split: train path: data/CC-MAIN-2021-43/train-* - config_name: CC-MAIN-2021-49 data_files: - split: train path: data/CC-MAIN-2021-49/train-* - config_name: CC-MAIN-2022-05 data_files: - split: train path: data/CC-MAIN-2022-05/train-* - config_name: CC-MAIN-2022-21 data_files: - split: train path: data/CC-MAIN-2022-21/train-* - config_name: CC-MAIN-2022-27 data_files: - split: train path: data/CC-MAIN-2022-27/train-* - config_name: CC-MAIN-2022-33 data_files: - split: train path: data/CC-MAIN-2022-33/train-* - config_name: CC-MAIN-2022-40 data_files: - split: train path: data/CC-MAIN-2022-40/train-* - config_name: CC-MAIN-2022-49 data_files: - split: train path: data/CC-MAIN-2022-49/train-* - config_name: CC-MAIN-2023-06 data_files: - split: train path: data/CC-MAIN-2023-06/train-* - config_name: CC-MAIN-2023-14 data_files: - split: train path: data/CC-MAIN-2023-14/train-* - config_name: CC-MAIN-2023-23 data_files: - split: train path: data/CC-MAIN-2023-23/train-* - config_name: CC-MAIN-2023-40 data_files: - split: train path: data/CC-MAIN-2023-40/train-* - config_name: CC-MAIN-2023-50 data_files: - split: train path: data/CC-MAIN-2023-50/train-* - config_name: CC-MAIN-2024-10 data_files: - split: train path: data/CC-MAIN-2024-10/train-* --- # Fineweb-Edu-Fortified <figure> <img src="https://cdn-uploads.huggingface.co/production/uploads/646516d2200b583e1e50faf8/79yPdK79m9mA0cCz-3h4v.png" width="500" style="margin-left:auto; margin-right: auto"/> <figcaption style="text-align: center; margin-left: auto; margin-right: auto; font-style: italic;"> The composition of fineweb-edu-fortified, produced by automatically clustering a 500k row sample in <a href="https://app.airtrain.ai/dataset/c232b33f-4f4a-49a7-ba55-8167a5f433da/null/1/0"> Airtrain </a> </figcaption> </figure> ## What is it? Fineweb-Edu-Fortified is a dataset derived from [Fineweb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) by applying exact-match deduplication across the whole dataset and producing an embedding for each row. The number of times the text from each row appears is also included as a `count` column. The embeddings were produced using [TaylorAI/bge-micro](https://huggingface.co/TaylorAI/bge-micro) Fineweb and Fineweb-Edu were obtained by processing data from 95 crawls of [Common Crawl](https://commoncrawl.org/), covering a time period from 2013 to 2024. More information about the original datasets can be found by consulting: - [Fineweb-edu dataset card](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) - [Fineweb dataset card](https://huggingface.co/datasets/HuggingFaceFW/fineweb) - [Fineweb release blog post](https://huggingface.co/spaces/HuggingFaceFW/blogpost-fineweb-v1) - [Fineweb paper](https://arxiv.org/abs/2406.17557) The contents of a randomly selected 500k rows from this dataset can be interactively explored in this [Airtrain](https://app.airtrain.ai/dataset/c232b33f-4f4a-49a7-ba55-8167a5f433da/null/1/0) dashboard. ## Deduplication ### Deduplication in original Fineweb and Fineweb-Edu During creation of the original Fineweb dataset, a variety of deduplication strategies were explored. The evaluation criteria used to assess deduplication strategies was to train ablation models on randomly selected subsets of the data, using a subset of up to ~350 billion tokens. Using this mechanism, the Fineweb authors selected a MinHash algorithm, using parameters considering documents with approximately 75% similarity or higher to be duplicates. This deduplication was performed *within* each Common Crawl crawl. For example, it would have removed all approximate duplicates from the 20th crawl from 2013, but would have retained an identical record that showed up in both the 2013-20 crawl and the 2013-48 crawl. The authors note that applying the deduplication *across crawls* reduced the evaluation performance of the ablation models used for assessment. The proposed reason for this performance degredation is that data duplicated across crawls is more likely to be high-quality compared to data that is not, so leaving in the duplicates effectively upsamples the higer-quality data. Following deduplication in Fineweb, Fineweb-Edu was extracted using a model-based quality classifier targeting educational content. It thus inherited the same inter-crawl deduplication strategy of Fineweb. ### Deduplication in this dataset #### Motivation Given the findings that cross-crawl deduplication reduced ablation model performance, one might ask what the motivation is for producing a dataset that uses it. Our motivation was threefold: - Reduce the number of rows that needed to be embedded by avoiding embedding of exact-match content - Enable easier filtering of the dataset for subsets-of-interest - Provide a version of the dataset for users whose training goals include avoiding training on non-unique tokens. For use cases that would benefit from "re-hydrating" or filtering the rows based on how frequently the text appeared in the original dataset, the new `count` column retains the number of appearances of the associated text. #### Procedure The overall procedure was to remove exact matches that appeared in multiple crawls (also referred to as "dumps"). This was achieved by performing an md5 hash on the text column and removing rows with duplicate hashes. To make this tractable at scale, we first grouped all rows by the first two hex digits of their hashes, then looked for exact hash matches within each of the resulting 256 buckets of data. Note that unlike the intra-crawl deduplication, we only eliminated exact matches across crawls. For duplicated rows, a strong preference was given to keep the metadata (ex: dump, url) from the oldest crawl where the text appeared. Following deduplication and embedding, the data were grouped by the "dump" column, mirroring the organization of the original Fineweb-Edu dataset. ### Deduplication stats Deduplication removed approximately 74.7% of rows from the original dataset (from 1.279 billion in Fineweb-Edu to 0.324 billion rows in Fineweb-Edu-Fortified). This indicates that a substantial amount of data in Fineweb-Edu is present across multiple crawls. The total token count in the deduplicated dataset is approximately 375 billion, compared to the 1,320 billion tokens in Fineweb-Edu. <figure> <img src="https://cdn-uploads.huggingface.co/production/uploads/646516d2200b583e1e50faf8/mUFyO1fUWJEXbYwiteR9e.png" width="750" style="margin-left:auto; margin-right: auto"/> <figcaption style="text-align: center; margin-left: auto; margin-right: auto; font-style: italic;"> A histogram of the `count` column. Histogram was generated using a 500k row sample after performing global per-row text duplication counting. </figcaption> </figure> ## Embeddings To support use cases with Fineweb-Edu such as classification, clustering, semantic search, etc., we have produced an embedding vector for each row in the dataset. The embedding model [TaylorAI/bge-micro](https://huggingface.co/TaylorAI/bge-micro) was selected for its tradeoff of strong performance on [MTEB](https://huggingface.co/spaces/mteb/leaderboard) benchmarks relative to its size (17 million parameters). The model's embedding space has 384 dimensions. The context-window of the model is 512 tokens (roughly several paragraphs of text); each row is embedded by using the first 512 tokens in its text field. Producing the embeddings took approximately 412 GPU-hours on Nvidia T4 GPUs. ## Using via `datasets` ```python from datasets import load_dataset fw = load_dataset("airtrain-ai/fineweb-edu-fortified", name="CC-MAIN-2024-10", split="train", streaming=True) ``` ## Considerations for Using the Data This "Considerations" section is copied from the parent dataset: [FineWeb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu). ### Social Impact of Dataset With the release of this dataset we aim to make model training more accessible to the machine learning community at large. While multiple open-weights models with strong performance have been publicly released in the past, more often than not these releases are not accompanied by the corresponding training dataset. This is unfortunate as the dataset specificities and characteristics have been demonstrated to have a very large impact and role in the performances of the models. As the creation of a high quality training dataset is a fundamental requirement to training an LLM capable of excelling at downstream tasks, with 🍷 FineWeb we (a) not only make the dataset creation process more transparent, by sharing our entire processing setup including the codebase used, we also (b) help alleviate the costs of dataset curation, both in time and in compute, for model creators by publicly releasing our dataset with the community. ### Discussion of Biases Efforts were made to minimize the amount of NSFW and toxic content present in the dataset by employing filtering on the URL level. However, there are still a significant number of documents present in the final dataset that could be considered toxic or contain harmful content. As 🍷 FineWeb was sourced from the web as a whole, any harmful biases typically present in it may be reproduced on our dataset. We deliberately avoided using machine learning filtering methods that define text quality based on the similarity to a “gold” source such as wikipedia or toxicity classifiers as these methods have been known to [disproportionately remove content in specific dialects](https://aclanthology.org/D16-1120/) and [overclassify as toxic text related to specific social identities](https://arxiv.org/pdf/2109.07445.pdf), respectively. ### Other Known Limitations As a consequence of some of the filtering steps applied, it is likely that code content is not prevalent in our dataset. If you are training a model that should also perform code tasks, we recommend you use 🍷 FineWeb with a code dataset, such as [The Stack v2](https://huggingface.co/datasets/bigcode/the-stack-v2). You should also probably consider complementing 🍷 FineWeb with specialized curated sources (such as Wikipedia, for example) as they will likely have better formatting than the wikipedia content included in 🍷 FineWeb (we did not tailor the processing to individual websites). ## Additional Information ### Acknowledgements Airtrain would like to thank the Fineweb/Fineweb-Edu team at Hugging Face for producing the original datasets, as well as for their support during work on Fineweb-Edu-Fortified. We'd also like to thank [@underspirit](https://huggingface.co/underspirit) for [pointing out](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu/discussions/7) the amount of reduction in dataset size that could be achieved via deduplication. We owe gratitude to [TaylorAI](https://huggingface.co/TaylorAI) for the `bge-micro` embedding model. Finally, thank you to the Hugging Face community for fostering a thriving ecosystem of models, datasets, and tools to support open-source AI. ### Licensing Information The dataset is released under the **Open Data Commons Attribution License (ODC-By) v1.0** [license](https://opendatacommons.org/licenses/by/1-0/). The use of this dataset is also subject to [CommonCrawl's Terms of Use](https://commoncrawl.org/terms-of-use).

codeparrot/github-code

codeparrot

--- annotations_creators: [] language_creators: - crowdsourced - expert-generated language: - code license: - other multilinguality: - multilingual pretty_name: github-code size_categories: - unknown source_datasets: [] task_categories: - text-generation task_ids: - language-modeling --- # GitHub Code Dataset ## Dataset Description The GitHub Code dataset consists of 115M code files from GitHub in 32 programming languages with 60 extensions totaling in 1TB of data. The dataset was created from the public GitHub dataset on Google BiqQuery. ### How to use it The GitHub Code dataset is a very large dataset so for most use cases it is recommended to make use of the streaming API of `datasets`. You can load and iterate through the dataset with the following two lines of code: ```python from datasets import load_dataset ds = load_dataset("codeparrot/github-code", streaming=True, split="train") print(next(iter(ds))) #OUTPUT: { 'code': "import mod189 from './mod189';\nvar value=mod189+1;\nexport default value;\n", 'repo_name': 'MirekSz/webpack-es6-ts', 'path': 'app/mods/mod190.js', 'language': 'JavaScript', 'license': 'isc', 'size': 73 } ``` You can see that besides the code, repo name, and path also the programming language, license, and the size of the file are part of the dataset. You can also filter the dataset for any subset of the 30 included languages (see the full list below) in the dataset. Just pass the list of languages as a list. E.g. if your dream is to build a Codex model for Dockerfiles use the following configuration: ```python ds = load_dataset("codeparrot/github-code", streaming=True, split="train", languages=["Dockerfile"]) print(next(iter(ds))["code"]) #OUTPUT: """\ FROM rockyluke/ubuntu:precise ENV DEBIAN_FRONTEND="noninteractive" \ TZ="Europe/Amsterdam" ... """ ``` We also have access to the license of the origin repo of a file so we can filter for licenses in the same way we filtered for languages: ```python ds = load_dataset("codeparrot/github-code", streaming=True, split="train", licenses=["mit", "isc"]) licenses = [] for element in iter(ds).take(10_000): licenses.append(element["license"]) print(Counter(licenses)) #OUTPUT: Counter({'mit': 9896, 'isc': 104}) ``` Naturally, you can also download the full dataset. Note that this will download ~300GB compressed text data and the uncompressed dataset will take up ~1TB of storage: ```python ds = load_dataset("codeparrot/github-code", split="train") ``` ## Data Structure ### Data Instances ```python { 'code': "import mod189 from './mod189';\nvar value=mod189+1;\nexport default value;\n", 'repo_name': 'MirekSz/webpack-es6-ts', 'path': 'app/mods/mod190.js', 'language': 'JavaScript', 'license': 'isc', 'size': 73 } ``` ### Data Fields |Field|Type|Description| |---|---|---| |code|string|content of source file| |repo_name|string|name of the GitHub repository| |path|string|path of file in GitHub repository| |language|string|programming language as inferred by extension| |license|string|license of GitHub repository| |size|int|size of source file in bytes| ### Data Splits The dataset only contains a train split. ## Languages The dataset contains 30 programming languages with over 60 extensions: ```python { "Assembly": [".asm"], "Batchfile": [".bat", ".cmd"], "C": [".c", ".h"], "C#": [".cs"], "C++": [".cpp", ".hpp", ".c++", ".h++", ".cc", ".hh", ".C", ".H"], "CMake": [".cmake"], "CSS": [".css"], "Dockerfile": [".dockerfile", "Dockerfile"], "FORTRAN": ['.f90', '.f', '.f03', '.f08', '.f77', '.f95', '.for', '.fpp'], "GO": [".go"], "Haskell": [".hs"], "HTML":[".html"], "Java": [".java"], "JavaScript": [".js"], "Julia": [".jl"], "Lua": [".lua"], "Makefile": ["Makefile"], "Markdown": [".md", ".markdown"], "PHP": [".php", ".php3", ".php4", ".php5", ".phps", ".phpt"], "Perl": [".pl", ".pm", ".pod", ".perl"], "PowerShell": ['.ps1', '.psd1', '.psm1'], "Python": [".py"], "Ruby": [".rb"], "Rust": [".rs"], "SQL": [".sql"], "Scala": [".scala"], "Shell": [".sh", ".bash", ".command", ".zsh"], "TypeScript": [".ts", ".tsx"], "TeX": [".tex"], "Visual Basic": [".vb"] } ``` ## Licenses Each example is also annotated with the license of the associated repository. There are in total 15 licenses: ```python [ 'mit', 'apache-2.0', 'gpl-3.0', 'gpl-2.0', 'bsd-3-clause', 'agpl-3.0', 'lgpl-3.0', 'lgpl-2.1', 'bsd-2-clause', 'cc0-1.0', 'epl-1.0', 'mpl-2.0', 'unlicense', 'isc', 'artistic-2.0' ] ``` ## Dataset Statistics The dataset contains 115M files and the sum of all the source code file sizes is 873 GB (note that the size of the dataset is larger due to the extra fields). A breakdown per language is given in the plot and table below:  | | Language |File Count| Size (GB)| |---:|:-------------|---------:|-------:| | 0 | Java | 19548190 | 107.70 | | 1 | C | 14143113 | 183.83 | | 2 | JavaScript | 11839883 | 87.82 | | 3 | HTML | 11178557 | 118.12 | | 4 | PHP | 11177610 | 61.41 | | 5 | Markdown | 8464626 | 23.09 | | 6 | C++ | 7380520 | 87.73 | | 7 | Python | 7226626 | 52.03 | | 8 | C# | 6811652 | 36.83 | | 9 | Ruby | 4473331 | 10.95 | | 10 | GO | 2265436 | 19.28 | | 11 | TypeScript | 1940406 | 24.59 | | 12 | CSS | 1734406 | 22.67 | | 13 | Shell | 1385648 | 3.01 | | 14 | Scala | 835755 | 3.87 | | 15 | Makefile | 679430 | 2.92 | | 16 | SQL | 656671 | 5.67 | | 17 | Lua | 578554 | 2.81 | | 18 | Perl | 497949 | 4.70 | | 19 | Dockerfile | 366505 | 0.71 | | 20 | Haskell | 340623 | 1.85 | | 21 | Rust | 322431 | 2.68 | | 22 | TeX | 251015 | 2.15 | | 23 | Batchfile | 236945 | 0.70 | | 24 | CMake | 175282 | 0.54 | | 25 | Visual Basic | 155652 | 1.91 | | 26 | FORTRAN | 142038 | 1.62 | | 27 | PowerShell | 136846 | 0.69 | | 28 | Assembly | 82905 | 0.78 | | 29 | Julia | 58317 | 0.29 | ## Dataset Creation The dataset was created in two steps: 1. Files of with the extensions given in the list above were retrieved from the GitHub dataset on BigQuery (full query [here](https://huggingface.co/datasets/codeparrot/github-code/blob/main/query.sql)). The query was executed on _Mar 16, 2022, 6:23:39 PM UTC+1_. 2. Files with lines longer than 1000 characters and duplicates (exact duplicates ignoring whitespaces) were dropped (full preprocessing script [here](https://huggingface.co/datasets/codeparrot/github-code/blob/main/github_preprocessing.py)). ## Considerations for Using the Data The dataset consists of source code from a wide range of repositories. As such they can potentially include harmful or biased code as well as sensitive information like passwords or usernames. ## Releases You can load any older version of the dataset with the `revision` argument: ```Python ds = load_dataset("codeparrot/github-code", revision="v1.0") ``` ### v1.0 - Initial release of dataset - The query was executed on _Feb 14, 2022, 12:03:16 PM UTC+1_ ### v1.1 - Fix missing Scala/TypeScript - Fix deduplication issue with inconsistent Python `hash` - The query was executed on _Mar 16, 2022, 6:23:39 PM UTC+1_

fixie-ai/peoples_speech

fixie-ai

--- dataset_info: - config_name: clean features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 2511523987.692 num_examples: 18622 - name: test num_bytes: 4259695510.794 num_examples: 34898 - name: train num_bytes: 401646320552.671 num_examples: 1501271 download_size: 398922548670 dataset_size: 408417540051 - config_name: dirty_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 144432442623.054 num_examples: 548014 - name: validation num_bytes: 2511524241.692 num_examples: 18622 - name: test num_bytes: 4259695588.794 num_examples: 34898 download_size: 149491764186 dataset_size: 151203662453.53998 configs: - config_name: clean data_files: - split: validation path: clean/validation-* - split: test path: clean/test-* - split: train path: data/train-* - config_name: dirty_sa data_files: - split: train path: dirty_sa/train-* - split: validation path: dirty_sa/validation-* - split: test path: dirty_sa/test-* ---

fixie-ai/librispeech_asr

fixie-ai

--- language: - en dataset_info: - config_name: clean features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: test num_bytes: 623948478.48 num_examples: 2620 - name: validation num_bytes: 622190064.956 num_examples: 2703 - name: train.360 num_bytes: 41953890926.124 num_examples: 104014 - name: train.100 num_bytes: 11606313661.774 num_examples: 28539 download_size: 53886816833 dataset_size: 54806343131.334 - config_name: other features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: train.500 num_bytes: 57330687390.808 num_examples: 148688 - name: validation num_bytes: 591511495.496 num_examples: 2864 - name: test num_bytes: 616939198.113 num_examples: 2939 download_size: 57019309170 dataset_size: 58539138084.417 configs: - config_name: clean data_files: - split: test path: clean/test-* - split: validation path: clean/validation-* - split: train.360 path: clean/train.360-* - split: train.100 path: clean/train.100-* - config_name: other data_files: - split: train.500 path: other/train.500-* - split: validation path: other/validation-* - split: test path: other/test-* ---

CohereForAI/aya_collection

CohereForAI

--- language: - ace - afr - amh - ara - aze - ban - bbc - bel - bem - ben - bjn - bul - cat - ceb - ces - cym - dan - deu - ell - eng - epo - est - eus - fil - fin - fon - fra - gla - gle - glg - guj - hat - hau - heb - hin - hrv - hun - hye - ibo - ind - isl - ita - jav - jpn - kan - kas - kat - kau - kaz - khm - kin - kir - kor - kur - lao - lav - lij - lit - ltz - mad - mal - man - mar - min - mkd - mlg - mlt - mon - mri - msa - mya - nep - nij - nld - nor - nso - nya - pan - pes - pol - por - pus - ron - rus - sin - slk - slv - smo - sna - snd - som - sot - spa - sqi - srp - sun - swa - swe - tam - taq - tel - tgk - tha - tur - twi - ukr - urd - uzb - vie - wol - xho - yid - yor - zho - zul license: apache-2.0 size_categories: - 100M<n<1B task_categories: - text-classification - summarization - translation pretty_name: Aya Collection dataset_info: - config_name: aya_dataset features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 245523658 num_examples: 202364 download_size: 134230030 dataset_size: 245523658 - config_name: templated_afriqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1053208.8833372337 num_examples: 6834 - name: train num_bytes: 785976.7786098759 num_examples: 5100 - name: validation num_bytes: 794915.3380528903 num_examples: 5158 download_size: 945238 dataset_size: 2634101.0 - config_name: templated_afrisenti features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 13970874.910620399 num_examples: 42576 - name: train num_bytes: 32313882.88468279 num_examples: 98476 - name: validation num_bytes: 6141462.204696811 num_examples: 18716 download_size: 13309887 dataset_size: 52426220.0 - config_name: templated_amharic_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1563941.8685517767 num_examples: 523 - name: train num_bytes: 5475291.704241497 num_examples: 1831 - name: validation num_bytes: 786456.4272067252 num_examples: 263 download_size: 3648433 dataset_size: 7825689.999999999 - config_name: templated_armenian_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1864796.3648305084 num_examples: 3063 - name: train num_bytes: 2445604.6351694916 num_examples: 4017 download_size: 1825641 dataset_size: 4310401.0 - config_name: templated_bengali_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 14242457 num_examples: 19096 download_size: 4609132 dataset_size: 14242457 - config_name: templated_dutch_imdb features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 39967063.5 num_examples: 24992 - name: train num_bytes: 39967063.5 num_examples: 24992 download_size: 44533807 dataset_size: 79934127.0 - config_name: templated_hindi_headline features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 228788501.12729776 num_examples: 23452 - name: train num_bytes: 919144047.8727022 num_examples: 94217 download_size: 243324488 dataset_size: 1147932549.0 - config_name: templated_hindi_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 109524809.11948325 num_examples: 10655 - name: train num_bytes: 437112433.88051677 num_examples: 42524 download_size: 112865381 dataset_size: 546637243.0 - config_name: templated_indic_paraphrase features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 5340504 num_examples: 7523 download_size: 1724626 dataset_size: 5340504 - config_name: templated_indic_sentiment features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 7496187 num_examples: 11559 download_size: 3003109 dataset_size: 7496187 - config_name: templated_indo_stories features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 2042351 num_examples: 2599 download_size: 813713 dataset_size: 2042351 - config_name: templated_japanese_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1345341895 num_examples: 2463624 download_size: 580330810 dataset_size: 1345341895 - config_name: templated_joke_explaination features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 591008 num_examples: 754 download_size: 157851 dataset_size: 591008 - config_name: templated_ligurian_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 105221.25 num_examples: 54 - name: test num_bytes: 140295.0 num_examples: 72 - name: train num_bytes: 596253.75 num_examples: 306 download_size: 546344 dataset_size: 841770.0 - config_name: templated_masakhanews features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 31426840.99009901 num_examples: 9240 - name: train num_bytes: 109538186.24752475 num_examples: 32206 - name: validation num_bytes: 15679408.762376238 num_examples: 4610 download_size: 86433056 dataset_size: 156644436.0 - config_name: templated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 41153051.4 num_examples: 156000 - name: train num_bytes: 144035679.9 num_examples: 546000 - name: validation num_bytes: 20576525.7 num_examples: 78000 download_size: 43108344 dataset_size: 205765257.0 - config_name: templated_ntx_llm features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 10019994 num_examples: 5983 download_size: 1037270 dataset_size: 10019994 - config_name: templated_nusax_senti features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 2684840.4 num_examples: 8000 - name: train num_bytes: 3356050.5 num_examples: 10000 - name: validation num_bytes: 671210.1 num_examples: 2000 download_size: 2336444 dataset_size: 6712101.0 - config_name: templated_persian_farstail features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 731412.1801486664 num_examples: 1029 - name: train num_bytes: 3424629.62483603 num_examples: 4818 - name: validation num_bytes: 720750.1950153039 num_examples: 1014 download_size: 1417008 dataset_size: 4876792.0 - config_name: templated_persian_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 38518994.420354694 num_examples: 11186 - name: train num_bytes: 564885564.1599021 num_examples: 164044 - name: validation num_bytes: 38512107.41974315 num_examples: 11184 download_size: 280563392 dataset_size: 641916666.0 - config_name: templated_scirepeval features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 53956804 num_examples: 32973 download_size: 27742964 dataset_size: 53956804 - config_name: templated_seed_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 186542.23316647828 num_examples: 380 - name: test num_bytes: 197342.04666559017 num_examples: 402 - name: train num_bytes: 5696410.720167931 num_examples: 11604 download_size: 2674875 dataset_size: 6080295.0 - config_name: templated_soda features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 487742788.92976975 num_examples: 595872 - name: train num_bytes: 2519225981.566041 num_examples: 3077721 - name: validation num_bytes: 479157981.5041894 num_examples: 585384 download_size: 1668121549 dataset_size: 3486126752.0 - config_name: templated_tamil_stories features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 14555943 num_examples: 1202 download_size: 4912529 dataset_size: 14555943 - config_name: templated_tamil_thirukkural features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 7722387 num_examples: 3990 download_size: 1441119 dataset_size: 7722387 - config_name: templated_telugu_food features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1108509 num_examples: 441 download_size: 312391 dataset_size: 1108509 - config_name: templated_telugu_jokes features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 966698 num_examples: 929 download_size: 298210 dataset_size: 966698 - config_name: templated_telugu_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1150840295 num_examples: 467090 download_size: 423260269 dataset_size: 1150840295 - config_name: templated_telugu_poems features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 8244805 num_examples: 5115 download_size: 2713433 dataset_size: 8244805 - config_name: templated_telugu_riddles features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 339040 num_examples: 844 download_size: 79031 dataset_size: 339040 - config_name: templated_thai_pos features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 319580.309461865 num_examples: 1000 - name: train num_bytes: 41690529.69053814 num_examples: 130454 download_size: 7405764 dataset_size: 42010110.0 - config_name: templated_thai_scb features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 131923007.25034823 num_examples: 177862 - name: train num_bytes: 1188824615.223528 num_examples: 1602804 - name: validation num_bytes: 131917073.5261238 num_examples: 177854 download_size: 441007386 dataset_size: 1452664696.0 - config_name: templated_thai_usembassy features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 10002322 num_examples: 1230 download_size: 3958145 dataset_size: 10002322 - config_name: templated_thai_wikitionary features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 12238652 num_examples: 19729 download_size: 2641369 dataset_size: 12238652 - config_name: templated_turku_paraphrase features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 9449925.655740838 num_examples: 31413 - name: train num_bytes: 75488399.52960008 num_examples: 250935 - name: validation num_bytes: 9502269.814659085 num_examples: 31587 download_size: 28908781 dataset_size: 94440595.00000001 - config_name: templated_ukranian_gec features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 21369624 num_examples: 29958 download_size: 9511988 dataset_size: 21369624 - config_name: templated_uner_llm features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 59421032.72376601 num_examples: 54957 - name: test num_bytes: 16164354.663105734 num_examples: 14950 - name: validation num_bytes: 8420601.613128258 num_examples: 7788 download_size: 12453483 dataset_size: 84005989.0 - config_name: templated_urdu_news_category features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29923228.33936761 num_examples: 11187 - name: train num_bytes: 269284981.6606324 num_examples: 100674 download_size: 118185925 dataset_size: 299208210.0 - config_name: templated_urdu_news_gen features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29497844.81704079 num_examples: 11187 - name: train num_bytes: 265456872.1829592 num_examples: 100674 download_size: 123276747 dataset_size: 294954717.0 - config_name: templated_urdu_news_headline features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29258423.35545901 num_examples: 11187 - name: train num_bytes: 263302271.644541 num_examples: 100674 download_size: 123095949 dataset_size: 292560695.0 - config_name: templated_wiki_split features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 4608986.773259303 num_examples: 10000 - name: train num_bytes: 912527760.4534814 num_examples: 1979888 - name: validation num_bytes: 4608986.773259303 num_examples: 10000 download_size: 395631256 dataset_size: 921745734.0 - config_name: templated_xcsqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 6315047.0 num_examples: 17000 download_size: 2125506 dataset_size: 6315047.0 - config_name: templated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 493033268.5027245 num_examples: 621319 - name: train num_bytes: 3671177872.612755 num_examples: 4626407 - name: validation num_bytes: 420416838.88452065 num_examples: 529808 download_size: 2363004380 dataset_size: 4584627980.0 - config_name: templated_xwikis features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 219985468.96557257 num_examples: 34987 - name: train num_bytes: 8995693557.81201 num_examples: 1430696 - name: validation num_bytes: 251360765.22241676 num_examples: 39977 download_size: 5713306872 dataset_size: 9467039791.999998 - config_name: translated_adversarial_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 167379954.08333334 num_examples: 119000 - name: train num_bytes: 1673799540.8333333 num_examples: 1190000 - name: validation num_bytes: 167379954.08333334 num_examples: 119000 download_size: 595462085 dataset_size: 2008559448.9999998 - config_name: translated_cnn_dailymail features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 4825107898.98773 num_examples: 1378800 - name: train num_bytes: 41993976492.495476 num_examples: 12000000 - name: validation num_bytes: 5613754777.516795 num_examples: 1604160 download_size: 25383694727 dataset_size: 52432839169.0 - config_name: translated_dolly features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 2188278931 num_examples: 1762152 download_size: 1089137630 dataset_size: 2188278931 - config_name: translated_flan_coqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 2884413536 num_examples: 762671 download_size: 1416350365 dataset_size: 2884413536 - config_name: translated_flan_cot features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 7470682150.0 num_examples: 11029200 download_size: 3086804878 dataset_size: 7470682150.0 - config_name: translated_flan_gem_wiki features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 11446176046 num_examples: 3230493 download_size: 5342129672 dataset_size: 11446176046 - config_name: translated_flan_lambada features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 223527122 num_examples: 509201 download_size: 99315916 dataset_size: 223527122 - config_name: translated_flan_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 34188800 num_examples: 64260 download_size: 14245088 dataset_size: 34188800 - config_name: translated_hotpotqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 13234982265.87797 num_examples: 42301644 - name: validation num_bytes: 833990488.1220294 num_examples: 2665600 download_size: 4862020346 dataset_size: 14068972754.0 - config_name: translated_joke_explaination features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 96548938 num_examples: 89726 download_size: 40366737 dataset_size: 96548938 - config_name: translated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 131276187.4 num_examples: 476000 - name: train num_bytes: 459466655.9 num_examples: 1666000 - name: validation num_bytes: 65638093.7 num_examples: 238000 download_size: 130340546 dataset_size: 656380937.0 - config_name: translated_mlqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 3730486242.0756793 num_examples: 2746830 - name: validation num_bytes: 369508041.92432094 num_examples: 272076 download_size: 1662296336 dataset_size: 4099994284.0 - config_name: translated_nqopen features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 4456165405.095046 num_examples: 20926150 - name: validation num_bytes: 182959989.9049544 num_examples: 859180 download_size: 1482593128 dataset_size: 4639125395.0 - config_name: translated_paws features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 536748719.07157385 num_examples: 952000 - name: train num_bytes: 3314490433.8568525 num_examples: 5878719 - name: validation num_bytes: 536748719.07157385 num_examples: 952000 download_size: 686023556 dataset_size: 4387987872.0 - config_name: translated_piqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 1324751595.2891204 num_examples: 1917447 - name: validation num_bytes: 151113599.71087962 num_examples: 218722 download_size: 504206733 dataset_size: 1475865195.0 - config_name: translated_soda features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 9332736341.158312 num_examples: 17876160 - name: validation num_bytes: 9168469957.193184 num_examples: 17561520 - name: train num_bytes: 74651741547.6485 num_examples: 142989840 download_size: 32022718450 dataset_size: 93152947846.0 - config_name: translated_wiki_split features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 72471632064.9965 num_examples: 117803336 - name: validation num_bytes: 366039049.0017441 num_examples: 595000 - name: test num_bytes: 366039049.0017441 num_examples: 595000 download_size: 27980267627 dataset_size: 73203710163.0 - config_name: translated_wikiqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 15512870.67820774 num_examples: 34867 - name: train num_bytes: 55062749.16496945 num_examples: 123760 - name: validation num_bytes: 7412293.156822811 num_examples: 16660 download_size: 32773189 dataset_size: 77987913.00000001 - config_name: translated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 8449087876.213723 num_examples: 8755108 - name: validation num_bytes: 7326325551.677284 num_examples: 7591680 - name: train num_bytes: 60579299633.10899 num_examples: 62773440 download_size: 35927637128 dataset_size: 76354713061.0 configs: - config_name: aya_dataset data_files: - split: train path: aya_dataset/train-* - config_name: templated_afriqa data_files: - split: test path: templated_afriqa/test-* - split: train path: templated_afriqa/train-* - split: validation path: templated_afriqa/validation-* - config_name: templated_afrisenti data_files: - split: test path: templated_afrisenti/test-* - split: train path: templated_afrisenti/train-* - split: validation path: templated_afrisenti/validation-* - config_name: templated_amharic_qa data_files: - split: test path: templated_amharic_qa/test-* - split: train path: templated_amharic_qa/train-* - split: validation path: templated_amharic_qa/validation-* - config_name: templated_armenian_instruct data_files: - split: test path: templated_armenian_instruct/test-* - split: train path: templated_armenian_instruct/train-* - config_name: templated_bengali_news data_files: - split: train path: templated_bengali_news/train-* - config_name: templated_dutch_imdb data_files: - split: test path: templated_dutch_imdb/test-* - split: train path: templated_dutch_imdb/train-* - config_name: templated_hindi_headline data_files: - split: test path: templated_hindi_headline/test-* - split: train path: templated_hindi_headline/train-* - config_name: templated_hindi_news data_files: - split: test path: templated_hindi_news/test-* - split: train path: templated_hindi_news/train-* - config_name: templated_indic_paraphrase data_files: - split: train path: templated_indic_paraphrase/train-* - config_name: templated_indic_sentiment data_files: - split: train path: templated_indic_sentiment/train-* - config_name: templated_indo_stories data_files: - split: train path: templated_indo_stories/train-* - config_name: templated_japanese_instruct data_files: - split: train path: templated_japanese_instruct/train-* - config_name: templated_joke_explaination data_files: - split: train path: templated_joke_explaination/train-* - config_name: templated_ligurian_news data_files: - split: validation path: templated_ligurian_news/validation-* - split: test path: templated_ligurian_news/test-* - split: train path: templated_ligurian_news/train-* - config_name: templated_masakhanews data_files: - split: test path: templated_masakhanews/test-* - split: train path: templated_masakhanews/train-* - split: validation path: templated_masakhanews/validation-* - config_name: templated_mintaka data_files: - split: test path: templated_mintaka/test-* - split: train path: templated_mintaka/train-* - split: validation path: templated_mintaka/validation-* - config_name: templated_ntx_llm data_files: - split: train path: templated_ntx_llm/train-* - config_name: templated_nusax_senti data_files: - split: test path: templated_nusax_senti/test-* - split: train path: templated_nusax_senti/train-* - split: validation path: templated_nusax_senti/validation-* - config_name: templated_persian_farstail data_files: - split: test path: templated_persian_farstail/test-* - split: train path: templated_persian_farstail/train-* - split: validation path: templated_persian_farstail/validation-* - config_name: templated_persian_instruct data_files: - split: test path: templated_persian_instruct/test-* - split: train path: templated_persian_instruct/train-* - split: validation path: templated_persian_instruct/validation-* - config_name: templated_scirepeval data_files: - split: validation path: templated_scirepeval/validation-* - config_name: templated_seed_instruct data_files: - split: validation path: templated_seed_instruct/validation-* - split: test path: templated_seed_instruct/test-* - split: train path: templated_seed_instruct/train-* - config_name: templated_soda data_files: - split: test path: templated_soda/test-* - split: train path: templated_soda/train-* - split: validation path: templated_soda/validation-* - config_name: templated_tamil_stories data_files: - split: train path: templated_tamil_stories/train-* - config_name: templated_tamil_thirukkural data_files: - split: train path: templated_tamil_thirukkural/train-* - config_name: templated_telugu_food data_files: - split: train path: templated_telugu_food/train-* - config_name: templated_telugu_jokes data_files: - split: train path: templated_telugu_jokes/train-* - config_name: templated_telugu_news data_files: - split: train path: templated_telugu_news/train-* - config_name: templated_telugu_poems data_files: - split: train path: templated_telugu_poems/train-* - config_name: templated_telugu_riddles data_files: - split: train path: templated_telugu_riddles/train-* - config_name: templated_thai_pos data_files: - split: test path: templated_thai_pos/test-* - split: train path: templated_thai_pos/train-* - config_name: templated_thai_scb data_files: - split: test path: templated_thai_scb/test-* - split: train path: templated_thai_scb/train-* - split: validation path: templated_thai_scb/validation-* - config_name: templated_thai_usembassy data_files: - split: train path: templated_thai_usembassy/train-* - config_name: templated_thai_wikitionary data_files: - split: train path: templated_thai_wikitionary/train-* - config_name: templated_turku_paraphrase data_files: - split: test path: templated_turku_paraphrase/test-* - split: train path: templated_turku_paraphrase/train-* - split: validation path: templated_turku_paraphrase/validation-* - config_name: templated_ukranian_gec data_files: - split: train path: templated_ukranian_gec/train-* - config_name: templated_uner_llm data_files: - split: train path: templated_uner_llm/train-* - split: test path: templated_uner_llm/test-* - split: validation path: templated_uner_llm/validation-* - config_name: templated_urdu_news_category data_files: - split: test path: templated_urdu_news_category/test-* - split: train path: templated_urdu_news_category/train-* - config_name: templated_urdu_news_gen data_files: - split: test path: templated_urdu_news_gen/test-* - split: train path: templated_urdu_news_gen/train-* - config_name: templated_urdu_news_headline data_files: - split: test path: templated_urdu_news_headline/test-* - split: train path: templated_urdu_news_headline/train-* - config_name: templated_wiki_split data_files: - split: test path: templated_wiki_split/test-* - split: train path: templated_wiki_split/train-* - split: validation path: templated_wiki_split/validation-* - config_name: templated_xcsqa data_files: - split: validation path: templated_xcsqa/validation-* - config_name: templated_xlel_wd data_files: - split: test path: templated_xlel_wd/test-* - split: train path: templated_xlel_wd/train-* - split: validation path: templated_xlel_wd/validation-* - config_name: templated_xwikis data_files: - split: test path: templated_xwikis/test-* - split: train path: templated_xwikis/train-* - split: validation path: templated_xwikis/validation-* - config_name: translated_adversarial_qa data_files: - split: test path: translated_adversarial_qa/test-* - split: train path: translated_adversarial_qa/train-* - split: validation path: translated_adversarial_qa/validation-* - config_name: translated_cnn_dailymail data_files: - split: test path: translated_cnn_dailymail/test-* - split: train path: translated_cnn_dailymail/train-* - split: validation path: translated_cnn_dailymail/validation-* - config_name: translated_dolly data_files: - split: train path: translated_dolly/train-* - config_name: translated_flan_coqa data_files: - split: train path: translated_flan_coqa/train-* - config_name: translated_flan_cot data_files: - split: train path: translated_flan_cot/train-* - config_name: translated_flan_gem_wiki data_files: - split: train path: translated_flan_gem_wiki/train-* - config_name: translated_flan_lambada data_files: - split: train path: translated_flan_lambada/train-* - config_name: translated_flan_qa data_files: - split: train path: translated_flan_qa/train-* - config_name: translated_hotpotqa data_files: - split: train path: translated_hotpotqa/train-* - split: validation path: translated_hotpotqa/validation-* - config_name: translated_joke_explaination data_files: - split: train path: translated_joke_explaination/train-* - config_name: translated_mintaka data_files: - split: test path: translated_mintaka/test-* - split: train path: translated_mintaka/train-* - split: validation path: translated_mintaka/validation-* - config_name: translated_mlqa data_files: - split: test path: translated_mlqa/test-* - split: validation path: translated_mlqa/validation-* - config_name: translated_nqopen data_files: - split: train path: translated_nqopen/train-* - split: validation path: translated_nqopen/validation-* - config_name: translated_paws data_files: - split: test path: translated_paws/test-* - split: train path: translated_paws/train-* - split: validation path: translated_paws/validation-* - config_name: translated_piqa data_files: - split: train path: translated_piqa/train-* - split: validation path: translated_piqa/validation-* - config_name: translated_soda data_files: - split: test path: translated_soda/test-* - split: validation path: translated_soda/validation-* - split: train path: translated_soda/train-* - config_name: translated_wiki_split data_files: - split: test path: translated_wiki_split/test-* - split: train path: translated_wiki_split/train-* - split: validation path: translated_wiki_split/validation-* - config_name: translated_wikiqa data_files: - split: test path: translated_wikiqa/test-* - split: train path: translated_wikiqa/train-* - split: validation path: translated_wikiqa/validation-* - config_name: translated_xlel_wd data_files: - split: test path: translated_xlel_wd/test-* - split: validation path: translated_xlel_wd/validation-* - split: train path: translated_xlel_wd/train-* ---  ****This dataset is uploaded in two places: here and additionally [here](https://huggingface.co/datasets/CohereForAI/aya_collection_language_split) as 'Aya Collection Language Split.' These datasets are identical in content but differ in structure of upload. This dataset is structured by folders split according to dataset name. The version [here](https://huggingface.co/datasets/CohereForAI/aya_collection_language_split) instead divides the Aya collection into folders split by language. We recommend you use the language split version if you are only interested in downloading data for a single or smaller set of languages, and this version if you want to download dataset according to data source or the entire collection.**** # Dataset Summary The Aya Collection is a massive multilingual collection consisting of 513 million instances of prompts and completions covering a wide range of tasks. This collection incorporates instruction-style templates from fluent speakers and applies them to a curated list of datasets, as well as translations of instruction-style datasets into 101 languages. Aya Dataset, a human-curated multilingual instruction and response dataset, is also part of this collection. See our paper for more details regarding the collection. - **Curated by:** Contributors of [Aya Open Science Intiative](https://cohere.com/research/aya) - **Language(s):** 115 languages - **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) - **Aya Datasets Family:** | Name | Explanation | |------|--------------| | [aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset) | Human-annotated multilingual instruction finetuning dataset, comprising over 204K instances across 65 languages. | | [aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection) | Created by applying instruction-style templates from fluent speakers to 44 datasets, including translations of 19 instruction-style datasets into 101 languages. This collection structured based on dataset level subsets. An alternative version of the collection structured by language subsets is also available.| | [aya_collection_language_split](https://huggingface.co/datasets/CohereForAI/aya_collection_language_split) | Aya Collection structured based on language level subsets. | | [aya_evaluation_suite](https://huggingface.co/datasets/CohereForAI/aya_evaluation_suite) | A diverse evaluation set for multilingual open-ended generation, featuring 250 culturally grounded prompts in 7 languages, 200 translated prompts in 24 languages, and human-edited versions selected for cross-cultural relevance from English Dolly in 6 languages.| | [aya_redteaming](https://huggingface.co/datasets/CohereForAI/aya_redteaming)| A red-teaming dataset consisting of harmful prompts in 8 languages across 9 different categories of harm with explicit labels for "global" and "local" harm.| # Dataset The `Aya Collection` is a comprehensive, large corpus of datasets that can be used by researchers around the world to train multilingual models. Our goal is only to include datasets with permissive licensing for manipulation and redistribution. The `Aya Collection` consists of three different sources of data: 1. Templated data: We collaborated with fluent speakers to create templates that allowed for the automatic expansion of existing datasets into various languages. 2. Translated data: We translated a hand-selected subset of 19 datasets into 101 languages (114 dialects) using the NLLB 3.3B parameter machine translation model. 3. Aya Dataset: We release the [Aya Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset) as a subset of the overall collection. This is the only dataset in the collection that is human-annotated in its entirety. ## Load with Datasets To load this dataset with Datasets, you'll need to install Datasets as `pip install datasets --upgrade` and then use the following code: ```python from datasets import load_dataset dataset = load_dataset("CohereForAI/aya_collection", "templated_mintaka") ``` In the above code snippet, "templated_mintaka" refers to a subset of the aya_collection. You can load other subsets by specifying its name at the time of loading the dataset. ## Data Instances An example of a `train` instance looks as follows: ```json {'id': 246001, 'inputs': 'The following query in English is taken from the geography category. What could be the answer to the question?\nWhat is the seventh tallest mountain in North America?', 'targets': 'The answer is Mount Lucania.', 'dataset_name': 'Mintaka-inst', 'sub_dataset_name': '-', 'task_type': 'question-answering', 'template_id': 3, 'language': 'eng', 'split': 'train', 'script': 'Latn' } ``` ## Data Fields The data fields are the same among all splits: - `id:` Unique id of the data point - `inputs:` Prompt or input to the language model. - `targets:` Completion or output of the language model. - `dataset_name:` The name of the source dataset that the data point was taken from - `sub_dataset_name:` If the source is a collection, this field indicates which part of that collection the data point was taken from. If it is not a collection, this field is left blank. - `task_type:` The task type that this conversation belongs to. - `template_id`: The id of the template applied to this data point. - `language:` The ISO code of the dialect of the conversation. - `script:` The script of the language. - `split:` Indicates whether the data point is part of the `train` or the `test` split. ### Statistics The total number of data points, including the Aya Dataset` is 513,758,189. To view the breakdown of dialect codes and the respective templated and translated data point counts in the Aya Collection , refer to the toggled table below. <details> <summary> <b> Breakdown of Aya Collection data point counts grouped by dialects </b> </summary> |dialect code|language|translated data point count|templated data point count|total count | |------------|--------|---------------------------|--------------------------|---------------| |ace |Achinese|8240684 |2000 |8242684 | |acm |Arabic |4120342 |0 |4120342 | |acq |Arabic |4120342 |0 |4120342 | |aeb |Arabic |4120342 |0 |4120342 | |afr |Afrikaans|4120342 |6108 |4126450 | |ajp |Arabic |4120342 |0 |4120342 | |als |Albanian|4120342 |0 |4120342 | |amh |Amharic |4120342 |25327 |4145669 | |apc |Arabic |4120342 |0 |4120342 | |arb |Arabic |6424999 |216430 |6641429 | |ars |Arabic |4120342 |0 |4120342 | |ary |Arabic |4120342 |18076 |4138418 | |arz |Arabic |4120342 |0 |4120342 | |azb |Azerbaijani|4120342 |0 |4120342 | |azj |Azerbaijani|4120342 |0 |4120342 | |bel |Belarusian|4120342 |21273 |4141615 | |ben |Bengali |4120342 |30661 |4151003 | |bjn |Banjar |8240684 |2000 |8242684 | |bul |Bulgarian|4120342 |37722 |4158064 | |cat |Catalan |4120342 |66900 |4187242 | |ceb |Cebuano |4120342 |0 |4120342 | |ces |Czech |4120342 |179604 |4299946 | |ckb |Kurdish |4120342 |0 |4120342 | |cym |Welsh |4120342 |0 |4120342 | |dan |Danish |4120342 |36310 |4156652 | |deu |German |4120342 |1326722 |5447064 | |ell |Greek |4120342 |40291 |4160633 | |eng |English |9771427 |8066678 |17838105 | |epo |Esperanto|4120342 |0 |4120342 | |est |Estonian|4120342 |0 |4120342 | |eus |Basque |4120342 |0 |4120342 | |fin |Finnish |4120342 |457895 |4578237 | |fra |French |4120342 |835520 |4955862 | |gla |Scottish Gaelic|4120342 |0 |4120342 | |gle |Irish |4120342 |0 |4120342 | |glg |Galician|4120342 |0 |4120342 | |guj |Gujarati|4120342 |2157 |4122499 | |hat |Haitian Creole|4120342 |0 |4120342 | |hau |Hausa |4120342 |51396 |4171738 | |heb |Hebrew |4120342 |103466 |4223808 | |hin |Hindi |4120342 |260387 |4380729 | |hun |Hungarian|4120342 |82039 |4202381 | |hye |Armenian|4120342 |7080 |4127422 | |ibo |Igbo |4120342 |36312 |4156654 | |ind |Indonesian|4120342 |45709 |4166051 | |isl |Icelandic|4120342 |0 |4120342 | |ita |Italian |4120342 |405682 |4526024 | |jav |Javanese|4120342 |829 |4121171 | |jpn |Japanese|4120342 |2693177 |6813519 | |kan |Kannada |4120342 |1156 |4121498 | |kas |Kashmiri|4120342 |0 |4120342 | |kat |Georgian|4120342 |0 |4120342 | |kaz |Kazakh |4120342 |0 |4120342 | |khk |Mongolian|4120342 |0 |4120342 | |khm |Khmer |4120342 |0 |4120342 | |kir |Kyrgyz |4120342 |0 |4120342 | |kmr |Kurdish |4120342 |0 |4120342 | |knc |Kanuri |8240684 |0 |8240684 | |kor |Korean |4120342 |41011 |4161353 | |lao |Lao |4120342 |0 |4120342 | |lit |Lithuanian|4120342 |0 |4120342 | |ltz |Luxembourgish|4120342 |0 |4120342 | |lvs |Latvian |4120342 |0 |4120342 | |mal |Malayalam|4120342 |4347 |4124689 | |mar |Marathi |4120342 |3678 |4124020 | |min |Minangkabau|6753788 |2000 |6755788 | |mkd |Macedonian|4120342 |0 |4120342 | |mlt |Maltese |4120342 |0 |4120342 | |mni |Manipuri|4120342 |0 |4120342 | |mri |Maori |4120342 |0 |4120342 | |mya |Burmese |4120342 |0 |4120342 | |nld |Dutch |4120342 |220181 |4340523 | |nno |Norwegian|4120342 |0 |4120342 | |nob |Norwegian|4120342 |0 |4120342 | |npi |Nepali |4120342 |0 |4120342 | |nso |Northern Sotho|4120342 |0 |4120342 | |pbt |Pashto |4120342 |0 |4120342 | |pes |Persian |4120342 |245520 |4365862 | |plt |Malagasy|4120342 |0 |4120342 | |pol |Polish |4120342 |332503 |4452845 | |por |Portuguese|4120342 |287432 |4407774 | |ron |Romanian|4120342 |36359 |4156701 | |rus |Russian |4120342 |545920 |4666262 | |sin |Sinhala |4120342 |195 |4120537 | |slk |Slovak |4120342 |27845 |4148187 | |slv |Slovenian|4120342 |25731 |4146073 | |smo |Samoan |4120342 |0 |4120342 | |sna |Shona |4120342 |3684 |4124026 | |snd |Sindhi |4120342 |0 |4120342 | |som |Somali |4120342 |2926 |4123268 | |sot |Southern Sotho|4120342 |0 |4120342 | |spa |Spanish |4120342 |379194 |4499536 | |srp |Serbian |4120342 |77124 |4197466 | |sun |Sundanese|4120342 |2208 |4122550 | |swe |Swedish |4120342 |76486 |4196828 | |swh |Swahili |4120342 |12726 |4133068 | |tam |Tamil |4120342 |11462 |4131804 | |taq |Tamasheq|4120342 |0 |4120342 | |tel |Telugu |4120342 |477821 |4598163 | |tgk |Tajik |4120342 |0 |4120342 | |tha |Thai |4120342 |2125180 |6245522 | |tur |Turkish |4120342 |59932 |4180274 | |ukr |Ukrainian|4120342 |189384 |4309726 | |urd |Urdu |4120342 |337739 |4458081 | |uzn |Uzbek |4120342 |0 |4120342 | |vie |Vietnamese|4120342 |42232 |4162574 | |xho |Xhosa |4120342 |2952 |4123294 | |ydd |Yiddish |4120342 |0 |4120342 | |yor |Yoruba |4120342 |4907 |4125249 | |yue |Chinese |4120342 |0 |4120342 | |zho-Hans |Chinese |4120342 |54528 |4174870 | |zho-Hant |Chinese |4120342 |0 |4120342 | |zsm |Malay |4120342 |13950 |4134292 | |zul |Zulu |4120342 |786 |4121128 | |arq |Arabic |0 |6046 |6046 | |ban |Balinese|0 |2000 |2000 | |bbc |Toba Batak|0 |2000 |2000 | |bem |Bemba |0 |776 |776 | |fil |Filipino|0 |220 |220 | |fon |Fon |0 |845 |845 | |hrv |Croatian|0 |9007 |9007 | |kin |Kinyarwanda|0 |11165 |11165 | |lij |Ligurian|0 |6409 |6409 | |mad |Madurese|0 |2000 |2000 | |nij |Ngaju |0 |2000 |2000 | |nor |Norwegian|0 |72352 |72352 | |pan |Punjabi |0 |2156 |2156 | |twi |Twi |0 |10840 |10840 | |wol |Wolof |0 |785 |785 | |zho |Chinese |0 |74972 |74972 | PS: Templated data also includes Mozambican Portuguese, which doesn't have its own ISO language code. </details> <br> # Motivations & Intentions - **Curation Rationale:** Automatic augmentation of existing datasets serves to enhance the available linguistic resources for multiple languages. The list of languages was initially established from mT5 and aligned with the annotators’ language list and NLLB translation model. The datasets were translated directly from English for all languages. # Additional Information ## Provenance - **Methods Used:** A combination of crowd-sourced templating and automatic translation was employed to source this dataset. - **Methodology Details:** - *Source:* Existing NLP datasets - *Dates of Collection:* May 2023 - Dec 2023 ## Dataset Version and Maintenance - **Maintenance Status:** Actively Maintained - **Version Details:** - *Current version:* 1.0 - *Last Update:* 02/2024 - *First Release:* 02/2024 ## Authorship - **Publishing Organization:** [Cohere For AI](https://cohere.com/research) - **Industry Type:** Not-for-profit - Tech - **Contact Details:** https://cohere.com/research/aya ## Licensing Information This dataset can be used for any purpose, whether academic or commercial, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Citation Information ```bibtex @misc{singh2024aya, title={Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning}, author={Shivalika Singh and Freddie Vargus and Daniel Dsouza and Börje F. Karlsson and Abinaya Mahendiran and Wei-Yin Ko and Herumb Shandilya and Jay Patel and Deividas Mataciunas and Laura OMahony and Mike Zhang and Ramith Hettiarachchi and Joseph Wilson and Marina Machado and Luisa Souza Moura and Dominik Krzemiński and Hakimeh Fadaei and Irem Ergün and Ifeoma Okoh and Aisha Alaagib and Oshan Mudannayake and Zaid Alyafeai and Vu Minh Chien and Sebastian Ruder and Surya Guthikonda and Emad A. Alghamdi and Sebastian Gehrmann and Niklas Muennighoff and Max Bartolo and Julia Kreutzer and Ahmet Üstün and Marzieh Fadaee and Sara Hooker}, year={2024}, eprint={2402.06619}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

databricks/databricks-dolly-15k

databricks

--- license: cc-by-sa-3.0 task_categories: - question-answering - summarization language: - en size_categories: - 10K<n<100K --- # Summary `databricks-dolly-15k` is an open source dataset of instruction-following records generated by thousands of Databricks employees in several of the behavioral categories outlined in the [InstructGPT](https://arxiv.org/abs/2203.02155) paper, including brainstorming, classification, closed QA, generation, information extraction, open QA, and summarization. This dataset can be used for any purpose, whether academic or commercial, under the terms of the [Creative Commons Attribution-ShareAlike 3.0 Unported License](https://creativecommons.org/licenses/by-sa/3.0/legalcode). Supported Tasks: - Training LLMs - Synthetic Data Generation - Data Augmentation Languages: English Version: 1.0 **Owner: Databricks, Inc.** # Dataset Overview `databricks-dolly-15k` is a corpus of more than 15,000 records generated by thousands of Databricks employees to enable large language models to exhibit the magical interactivity of ChatGPT. Databricks employees were invited to create prompt / response pairs in each of eight different instruction categories, including the seven outlined in the InstructGPT paper, as well as an open-ended free-form category. The contributors were instructed to avoid using information from any source on the web with the exception of Wikipedia (for particular subsets of instruction categories), and explicitly instructed to avoid using generative AI in formulating instructions or responses. Examples of each behavior were provided to motivate the types of questions and instructions appropriate to each category. Halfway through the data generation process, contributors were given the option of answering questions posed by other contributors. They were asked to rephrase the original question and only select questions they could be reasonably expected to answer correctly. For certain categories contributors were asked to provide reference texts copied from Wikipedia. Reference text (indicated by the `context` field in the actual dataset) may contain bracketed Wikipedia citation numbers (e.g. `[42]`) which we recommend users remove for downstream applications. # Intended Uses While immediately valuable for instruction fine tuning large language models, as a corpus of human-generated instruction prompts, this dataset also presents a valuable opportunity for synthetic data generation in the methods outlined in the Self-Instruct paper. For example, contributor--generated prompts could be submitted as few-shot examples to a large open language model to generate a corpus of millions of examples of instructions in each of the respective InstructGPT categories. Likewise, both the instructions and responses present fertile ground for data augmentation. A paraphrasing model might be used to restate each prompt or short responses, with the resulting text associated to the respective ground-truth sample. Such an approach might provide a form of regularization on the dataset that could allow for more robust instruction-following behavior in models derived from these synthetic datasets. # Dataset ## Purpose of Collection As part of our continuing commitment to open source, Databricks developed what is, to the best of our knowledge, the first open source, human-generated instruction corpus specifically designed to enable large language models to exhibit the magical interactivity of ChatGPT. Unlike other datasets that are limited to non-commercial use, this dataset can be used, modified, and extended for any purpose, including academic or commercial applications. ## Sources - **Human-generated data**: Databricks employees were invited to create prompt / response pairs in each of eight different instruction categories. - **Wikipedia**: For instruction categories that require an annotator to consult a reference text (information extraction, closed QA, summarization) contributors selected passages from Wikipedia for particular subsets of instruction categories. No guidance was given to annotators as to how to select the target passages. ## Annotator Guidelines To create a record, employees were given a brief description of the annotation task as well as examples of the types of prompts typical of each annotation task. Guidelines were succinct by design so as to encourage a high task completion rate, possibly at the cost of rigorous compliance to an annotation rubric that concretely and reliably operationalizes the specific task. Caveat emptor. The annotation guidelines for each of the categories are as follows: - **Creative Writing**: Write a question or instruction that requires a creative, open-ended written response. The instruction should be reasonable to ask of a person with general world knowledge and should not require searching. In this task, your prompt should give very specific instructions to follow. Constraints, instructions, guidelines, or requirements all work, and the more of them the better. - **Closed QA**: Write a question or instruction that requires factually correct response based on a passage of text from Wikipedia. The question can be complex and can involve human-level reasoning capabilities, but should not require special knowledge. To create a question for this task include both the text of the question as well as the reference text in the form. - **Open QA**: Write a question that can be answered using general world knowledge or at most a single search. This task asks for opinions and facts about the world at large and does not provide any reference text for consultation. - **Summarization**: Give a summary of a paragraph from Wikipedia. Please don't ask questions that will require more than 3-5 minutes to answer. To create a question for this task include both the text of the question as well as the reference text in the form. - **Information Extraction**: These questions involve reading a paragraph from Wikipedia and extracting information from the passage. Everything required to produce an answer (e.g. a list, keywords etc) should be included in the passages. To create a question for this task include both the text of the question as well as the reference text in the form. - **Classification**: These prompts contain lists or examples of entities to be classified, e.g. movie reviews, products, etc. In this task the text or list of entities under consideration is contained in the prompt (e.g. there is no reference text.). You can choose any categories for classification you like, the more diverse the better. - **Brainstorming**: Think up lots of examples in response to a question asking to brainstorm ideas. ## Personal or Sensitive Data This dataset contains public information (e.g., some information from Wikipedia). To our knowledge, there are no private person’s personal identifiers or sensitive information. ## Language American English # Known Limitations - Wikipedia is a crowdsourced corpus and the contents of this dataset may reflect the bias, factual errors and topical focus found in Wikipedia - Some annotators may not be native English speakers - Annotator demographics and subject matter may reflect the makeup of Databricks employees # Citation ``` @online{DatabricksBlog2023DollyV2, author = {Mike Conover and Matt Hayes and Ankit Mathur and Jianwei Xie and Jun Wan and Sam Shah and Ali Ghodsi and Patrick Wendell and Matei Zaharia and Reynold Xin}, title = {Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM}, year = {2023}, url = {https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm}, urldate = {2023-06-30} } ``` # License/Attribution **Copyright (2023) Databricks, Inc.** This dataset was developed at Databricks (https://www.databricks.com) and its use is subject to the CC BY-SA 3.0 license. Certain categories of material in the dataset include materials from the following sources, licensed under the CC BY-SA 3.0 license: Wikipedia (various pages) - https://www.wikipedia.org/ Copyright © Wikipedia editors and contributors.