Hugging Face's logo

Hanhpt23
/
whisper-small-frenchmed-free_ED3-11

Automatic Speech Recognition
Transformers
Safetensors
French
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
Hanhpt23 commited on
Commit
b22254c
•
1 Parent(s): 41fd3af

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,8 +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/FrenchMed dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.2271
23
- - Wer: 40.1026
 
24
 
25
  ## Model description
26
 
@@ -50,28 +51,28 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.8705 | 1.0 | 215 | 0.8589 | 164.5161 |
56
- | 0.6103 | 2.0 | 430 | 0.8569 | 150.7331 |
57
- | 0.3958 | 3.0 | 645 | 0.9063 | 72.4340 |
58
- | 0.2181 | 4.0 | 860 | 0.9451 | 94.7947 |
59
- | 0.137 | 5.0 | 1075 | 0.9824 | 113.8563 |
60
- | 0.0827 | 6.0 | 1290 | 1.0459 | 68.6950 |
61
- | 0.0429 | 7.0 | 1505 | 1.0825 | 86.7302 |
62
- | 0.0259 | 8.0 | 1720 | 1.1261 | 113.0499 |
63
- | 0.0215 | 9.0 | 1935 | 1.1081 | 44.6481 |
64
- | 0.0161 | 10.0 | 2150 | 1.1658 | 64.5161 |
65
- | 0.007 | 11.0 | 2365 | 1.1593 | 38.9296 |
66
- | 0.0048 | 12.0 | 2580 | 1.1756 | 39.0029 |
67
- | 0.0032 | 13.0 | 2795 | 1.1836 | 37.5367 |
68
- | 0.002 | 14.0 | 3010 | 1.1991 | 38.9296 |
69
- | 0.0038 | 15.0 | 3225 | 1.2011 | 37.7566 |
70
- | 0.0011 | 16.0 | 3440 | 1.2117 | 40.7625 |
71
- | 0.001 | 17.0 | 3655 | 1.2195 | 38.5630 |
72
- | 0.0009 | 18.0 | 3870 | 1.2237 | 40.1760 |
73
- | 0.0008 | 19.0 | 4085 | 1.2262 | 39.9560 |
74
- | 0.0008 | 20.0 | 4300 | 1.2271 | 40.1026 |
75
 
76
 
77
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the pphuc25/FrenchMed dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.2159
23
+ - Wer: 71.8475
24
+ - Cer: 60.7403
25
 
26
  ## Model description
27
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
56
+ | 0.8706 | 1.0 | 215 | 0.8600 | 178.2258 | 102.3256 |
57
+ | 0.6025 | 2.0 | 430 | 0.8573 | 114.1496 | 71.0059 |
58
+ | 0.3962 | 3.0 | 645 | 0.8968 | 88.9296 | 67.1529 |
59
+ | 0.2239 | 4.0 | 860 | 0.9412 | 96.1877 | 60.4651 |
60
+ | 7.0487 | 5.0 | 1075 | 6.4281 | 779.6188 | 546.2915 |
61
+ | 5.2135 | 6.0 | 1290 | 4.5960 | 95.0147 | 76.2626 |
62
+ | 0.2569 | 7.0 | 1505 | 1.0109 | 228.7390 | 163.0246 |
63
+ | 0.2082 | 8.0 | 1720 | 1.0642 | 215.1026 | 163.8090 |
64
+ | 0.1511 | 9.0 | 1935 | 1.0990 | 162.3167 | 156.4882 |
65
+ | 0.0247 | 10.0 | 2150 | 1.1002 | 160.6305 | 182.1660 |
66
+ | 0.0155 | 11.0 | 2365 | 1.1253 | 59.9707 | 62.7081 |
67
+ | 0.007 | 12.0 | 2580 | 1.1525 | 134.8240 | 131.4298 |
68
+ | 0.0042 | 13.0 | 2795 | 1.1656 | 164.0762 | 154.8507 |
69
+ | 0.0024 | 14.0 | 3010 | 1.1838 | 118.9883 | 105.3530 |
70
+ | 0.0027 | 15.0 | 3225 | 1.1876 | 87.5367 | 71.3362 |
71
+ | 0.0015 | 16.0 | 3440 | 1.1978 | 57.2581 | 44.8190 |
72
+ | 0.0017 | 17.0 | 3655 | 1.1999 | 72.2874 | 60.8504 |
73
+ | 0.0012 | 18.0 | 3870 | 1.2119 | 71.8475 | 60.7541 |
74
+ | 0.0011 | 19.0 | 4085 | 1.2144 | 71.8475 | 60.7403 |
75
+ | 0.0011 | 20.0 | 4300 | 1.2159 | 71.8475 | 60.7403 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9881d60c8f7939aff9df3cc617d54bfd61e5363d788fda68d8e8d03f3bceae01
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7806a1915d5f2de51625302619408c9bb20d672cfab04f3fe2ce8877eb50f209
3
  size 966995080