minlik/docllm-yi-34b
Text Generation • 38B • Updated • 3 • 1
Document AI
-
-
JinghuiLuAstronaut/DocLLM_baichuan2_7b
Text Generation • 9B • Updated • 5 • 5 -
docling-project/docling-models
Updated • 873k • 199 -
DocLayout YOLO
🚀188Demo for DocLayout-YOLO
-
DocQuery — Document Query Engine
🦉290 -
impira/layoutlm-document-qa
Document Question Answering • 0.1B • Updated • 14.3k • 1.17k -
HURIDOCS/pdf-document-layout-analysis
Updated • 202 • 125 -
HuggingFaceM4/Docmatix
Viewer • Updated • 2.55M • 14.6k • 299 -
docling-project/DocLayNet-v1.1
Viewer • Updated • 63.5k • 1.48k • 26 -
cmarkea/doc-vqa
Viewer • Updated • 12.1k • 347 • 18 -
google/paligemma-3b-pt-224
Image-Text-to-Text • Updated • 61.5k • 422 -
Noise-Aware Training of Layout-Aware Language Models
Paper • 2404.00488 • Published • 10 -
Paligemma2 Vqav2
🐨48PaliGemma2 LoRA finetuned on VQAv2
-
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
Paper • 2412.07626 • Published • 29 -
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 156 -
docling-project/SmolDocling-256M-preview
Image-Text-to-Text • Updated • 67.3k • 1.61k -
Towards Effective Extraction and Evaluation of Factual Claims
Paper • 2502.10855 • Published • 3 -
ByteDance/Dolphin
Image-Text-to-Text • Updated • 1.41k • 515 -
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 49.1k • 1.59k -
Nanonets Ocr S
👁35https://nanonets.com/research/nanonets-ocr-s/
-
numind/NuMarkdown-8B-Thinking
Image-to-Text • Updated • 58.5k • 448 -
rednote-hilab/dots.ocr
Image-Text-to-Text • 3B • Updated • 255k • 1.28k -
Multimodal OCR2
💻140FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
microsoft/trocr-small-handwritten
Image-to-Text • Updated • 12.4k • 62 -
DunnBC22/trocr-base-handwritten-OCR-handwriting_recognition_v2
Image-to-Text • Updated • 115 • 21 -
ibm-granite/granite-docling-258M
Image-Text-to-Text • Updated • 80.5k • 1.14k -
granite-docling-258M demo
📝269Extract and convert document content from images
-
Granite Docling 258M WebGPU
🐣156Convert document images to HTML with Docling
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 8.21k • 1.57k -
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 122 -
PaddleOCR-VL Online Demo
📈238Extract text, tables, formulas, and charts from images
-
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • Updated • 337k • 493 -
nanonets/Nanonets-OCR2-1.5B-exp
Image-Text-to-Text • 2B • Updated • 6.79k • 47 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.98M • 3.19k -
lightonai/LightOnOCR-1B-1025
Image-to-Text • Updated • 165k • 246 -
HuggingFaceFW/ocr-annotations
Viewer • Updated • 1.62k • 159 • 17 -
HuggingFaceFW/finepdfs_lang_classification
Viewer • Updated • 3.08M • 34.1k • 4 -
HuggingFaceFW/finepdfs
Viewer • Updated • 476M • 37.2k • 826 -
microsoft/Fara-7B
Image-Text-to-Text • Updated • 41.4k • 480 -
tencent/HunyuanOCR
Image-Text-to-Text • Updated • 387k • 555 -
HunyuanOCR Technical Report
Paper • 2511.19575 • Published • 22 -
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-7B-v1
Visual Document Retrieval • 8B • Updated • 15.3k • 17 -
rootsautomation/GutenOCR-3B
Image-Text-to-Text • 4B • Updated • 873 • 26 -
rootsautomation/GutenOCR-7B
Image-Text-to-Text • 8B • Updated • 494 • 25 -
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 603k • 919 -
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Text-to-Speech • 2B • Updated • 561k • 299 -
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 1.02M • 1.31k -
Qwen3-TTS Technical Report
Paper • 2601.15621 • Published • 71 -
Qwen3-TTS Demo
🎙1.73kGenerate speech audio via voice design, cloning, or preset speakers
-
ibm-granite/granite-vision-3.3-2b-chart2csv-preview
Image-Text-to-Text • 3B • Updated • 3.3k • 14 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.05M • 615 -
AttentionRetriever: Attention Layers are Secretly Long Document Retrievers
Paper • 2602.12278 • Published • 2