Hugging Face's logo

Hanhpt23
/
whisper-small-chinesemed-free_ED0-8

Automatic Speech Recognition
Transformers
Safetensors
Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
Hanhpt23 commited on
Commit
f6fe861
•
1 Parent(s): 95bc7dd

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -6
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the pphuc25/ChiMed dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6547
23
- - Wer: 109.6267
24
- - Cer: 33.2888
25
 
26
  ## Model description
27
 
@@ -47,14 +47,32 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 100
50
- - num_epochs: 2
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|
56
- | 0.5536 | 1.0 | 161 | 0.6982 | 96.8566 | 31.0160 |
57
- | 0.2083 | 2.0 | 322 | 0.6547 | 109.6267 | 33.2888 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the pphuc25/ChiMed dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.9626
23
+ - Wer: 102.9470
24
+ - Cer: 27.5178
25
 
26
  ## Model description
27
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 100
50
+ - num_epochs: 20
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|
56
+ | 0.5624 | 1.0 | 161 | 0.7102 | 103.7328 | 36.8093 |
57
+ | 0.2753 | 2.0 | 322 | 0.7326 | 117.6817 | 44.2291 |
58
+ | 0.127 | 3.0 | 483 | 0.7775 | 86.0511 | 31.1720 |
59
+ | 0.0519 | 4.0 | 644 | 0.8256 | 103.5363 | 31.2834 |
60
+ | 0.0423 | 5.0 | 805 | 0.8966 | 119.4499 | 36.9207 |
61
+ | 0.0251 | 6.0 | 966 | 0.8908 | 105.8939 | 29.3449 |
62
+ | 0.0137 | 7.0 | 1127 | 0.9214 | 84.6758 | 26.2478 |
63
+ | 0.0169 | 8.0 | 1288 | 0.9114 | 87.0334 | 24.3761 |
64
+ | 0.0107 | 9.0 | 1449 | 0.9319 | 104.9116 | 28.4759 |
65
+ | 0.0025 | 10.0 | 1610 | 0.9353 | 103.5363 | 27.3173 |
66
+ | 0.0007 | 11.0 | 1771 | 0.9370 | 105.6974 | 28.9216 |
67
+ | 0.0017 | 12.0 | 1932 | 0.9412 | 103.3399 | 27.8075 |
68
+ | 0.0006 | 13.0 | 2093 | 0.9438 | 102.3576 | 27.7852 |
69
+ | 0.0003 | 14.0 | 2254 | 0.9575 | 103.5363 | 29.3449 |
70
+ | 0.0003 | 15.0 | 2415 | 0.9568 | 102.3576 | 27.8743 |
71
+ | 0.0002 | 16.0 | 2576 | 0.9591 | 103.1434 | 27.6738 |
72
+ | 0.0002 | 17.0 | 2737 | 0.9601 | 102.9470 | 27.5401 |
73
+ | 0.0002 | 18.0 | 2898 | 0.9613 | 102.7505 | 27.5178 |
74
+ | 0.0002 | 19.0 | 3059 | 0.9622 | 102.9470 | 27.5401 |
75
+ | 0.0002 | 20.0 | 3220 | 0.9626 | 102.9470 | 27.5178 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89e8027d22749e7f8500d764d21e6a4e5ffd7f6f9ea22185051089ff26a15d61
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22116097e605270a450036d17a8d0ec4420af5681173481d038ef2d4a75ae48
3
  size 966995080