Hugging Face's logo

noflm
/
whisper-small-ja-elite

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Japanese
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
noflm commited on
Commit
f239ec3
•
1 Parent(s): 72ddc76

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -25
README.md CHANGED
@@ -1,41 +1,38 @@
1
  ---
2
- language:
3
- - ja
4
- license: other
5
  tags:
6
- - whisper-event
7
  - generated_from_trainer
8
  datasets:
9
- - Elite35P-Server/EliteVoiceProject
10
  metrics:
11
  - wer
12
  model-index:
13
- - name: Whisper Small Japanese Elite
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
- name: Elite35P-Server/EliteVoiceProject twitch
20
- type: Elite35P-Server/EliteVoiceProject
21
- config: twitch
22
  split: test
23
- args: twitch
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 23.296888141295206
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
- # Whisper Small Japanese Elite
34
 
35
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Elite35P-Server/EliteVoiceProject twitch dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.9180
38
- - Wer: 23.2969
39
 
40
  ## Model description
41
 
@@ -68,16 +65,16 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|
71
- | 0.0033 | 18.0 | 1000 | 0.6728 | 25.3154 |
72
- | 0.008 | 37.0 | 2000 | 0.6984 | 23.3810 |
73
- | 0.0002 | 56.0 | 3000 | 0.7486 | 24.4743 |
74
- | 0.0001 | 75.0 | 4000 | 0.7753 | 24.4743 |
75
- | 0.0 | 94.0 | 5000 | 0.8014 | 24.0538 |
76
- | 0.0 | 113.0 | 6000 | 0.8244 | 24.3902 |
77
- | 0.0 | 132.0 | 7000 | 0.8468 | 23.8015 |
78
- | 0.0 | 150.0 | 8000 | 0.8699 | 23.4651 |
79
- | 0.0 | 169.0 | 9000 | 0.8936 | 23.2128 |
80
- | 0.0 | 188.0 | 10000 | 0.9180 | 23.2969 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
 
 
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
+ - elite_voice_project
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: whisper-small-ja-elite
11
  results:
12
  - task:
13
  name: Automatic Speech Recognition
14
  type: automatic-speech-recognition
15
  dataset:
16
+ name: elite_voice_project
17
+ type: elite_voice_project
18
+ config: youtube
19
  split: test
20
+ args: youtube
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 31.536388140161726
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
+ # whisper-small-ja-elite
31
 
32
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the elite_voice_project dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.1596
35
+ - Wer: 31.5364
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|
68
+ | 0.0003 | 52.0 | 1000 | 0.8053 | 28.8410 |
69
+ | 0.0 | 105.0 | 2000 | 0.8636 | 28.5714 |
70
+ | 0.0 | 157.0 | 3000 | 0.9056 | 28.0323 |
71
+ | 0.0 | 210.0 | 4000 | 0.9414 | 28.8410 |
72
+ | 0.0 | 263.0 | 5000 | 0.9842 | 31.2668 |
73
+ | 0.0 | 315.0 | 6000 | 1.0223 | 31.2668 |
74
+ | 0.0 | 368.0 | 7000 | 1.0677 | 31.2668 |
75
+ | 0.0 | 421.0 | 8000 | 1.1079 | 31.2668 |
76
+ | 0.0 | 473.0 | 9000 | 1.1468 | 31.5364 |
77
+ | 0.0 | 526.0 | 10000 | 1.1596 | 31.5364 |
78
 
79
 
80
  ### Framework versions