Curiousfox commited on
Commit
ff06bd0
·
verified ·
1 Parent(s): 9fa04ab

End of training

Browse files
Files changed (2) hide show
  1. README.md +11 -8
  2. preprocessor_config.json +14 -0
README.md CHANGED
@@ -1,24 +1,27 @@
1
  ---
2
  library_name: transformers
3
- base_model: Curiousfox/H2E-ASR-ver-3-whisper
 
 
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - common_voice_17_0
8
  metrics:
9
  - wer
10
  model-index:
11
- - name: whisper_new_ver4
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
- name: common_voice_17_0
18
- type: common_voice_17_0
19
  config: nan-tw
20
  split: test
21
- args: nan-tw
22
  metrics:
23
  - name: Wer
24
  type: wer
@@ -28,9 +31,9 @@ model-index:
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # whisper_new_ver4
32
 
33
- This model is a fine-tuned version of [Curiousfox/H2E-ASR-ver-3-whisper](https://huggingface.co/Curiousfox/H2E-ASR-ver-3-whisper) on the common_voice_17_0 dataset.
34
  It achieves the following results on the evaluation set:
35
  - Loss: 0.4709
36
  - Wer: 84.1740
 
1
  ---
2
  library_name: transformers
3
+ language:
4
+ - nan
5
+ license: apache-2.0
6
+ base_model: openai/whisper-medium
7
  tags:
8
  - generated_from_trainer
9
  datasets:
10
+ - mozilla-foundation/common_voice_17_0
11
  metrics:
12
  - wer
13
  model-index:
14
+ - name: Hokkien-to-Tai Lo Whisper ver 4
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
+ name: Common Voice 16.0
21
+ type: mozilla-foundation/common_voice_17_0
22
  config: nan-tw
23
  split: test
24
+ args: 'config: hi, split: test'
25
  metrics:
26
  - name: Wer
27
  type: wer
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
+ # Hokkien-to-Tai Lo Whisper ver 4
35
 
36
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 16.0 dataset.
37
  It achieves the following results on the evaluation set:
38
  - Loss: 0.4709
39
  - Wer: 84.1740
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }