Hugging Face's logo

Hanhpt23
/
whisper-small-vietmed-free_E0-8D3-11

Automatic Speech Recognition
Transformers
Safetensors
Vietnamese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
Hanhpt23 commited on
Commit
5e56a71
•
1 Parent(s): 54fa9c0

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/VietMed-split-8-2 dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.8268
23
- - Wer: 39.2934
 
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
- | 0.5567 | 1.0 | 569 | 0.5442 | 110.6681 |
56
- | 0.3927 | 2.0 | 1138 | 0.5414 | 79.2641 |
57
- | 0.2763 | 3.0 | 1707 | 0.5484 | 81.6145 |
58
- | 0.1841 | 4.0 | 2276 | 0.5896 | 70.0897 |
59
- | 0.1059 | 5.0 | 2845 | 0.6430 | 59.4838 |
60
- | 0.0807 | 6.0 | 3414 | 0.6636 | 63.3132 |
61
- | 0.0459 | 7.0 | 3983 | 0.7000 | 71.0086 |
62
- | 0.0249 | 8.0 | 4552 | 0.7402 | 59.5643 |
63
- | 0.0188 | 9.0 | 5121 | 0.7577 | 70.7926 |
64
- | 0.0182 | 10.0 | 5690 | 0.7692 | 52.9599 |
65
- | 0.0049 | 11.0 | 6259 | 0.7727 | 77.1664 |
66
- | 0.0054 | 12.0 | 6828 | 0.7771 | 41.3619 |
67
- | 0.0019 | 13.0 | 7397 | 0.7908 | 49.6650 |
68
- | 0.0023 | 14.0 | 7966 | 0.8098 | 34.6403 |
69
- | 0.001 | 15.0 | 8535 | 0.8050 | 41.5669 |
70
- | 0.0005 | 16.0 | 9104 | 0.8027 | 35.4970 |
71
- | 0.0004 | 17.0 | 9673 | 0.8123 | 39.3520 |
72
- | 0.0007 | 18.0 | 10242 | 0.8224 | 43.5914 |
73
- | 0.0002 | 19.0 | 10811 | 0.8250 | 39.2532 |
74
- | 0.0001 | 20.0 | 11380 | 0.8268 | 39.2934 |
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/VietMed-split-8-2 dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.8271
23
+ - Wer: 58.2317
24
+ - Cer: 46.8054
25
 
26
  ## Model description
27
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
56
+ | 0.5609 | 1.0 | 569 | 0.5509 | 95.7642 | 78.5963 |
57
+ | 0.4081 | 2.0 | 1138 | 0.5360 | 68.6290 | 56.1987 |
58
+ | 0.278 | 3.0 | 1707 | 0.5530 | 34.9844 | 29.3423 |
59
+ | 0.187 | 4.0 | 2276 | 0.5937 | 71.8946 | 56.4435 |
60
+ | 0.1106 | 5.0 | 2845 | 0.6325 | 41.3839 | 34.3220 |
61
+ | 0.0761 | 6.0 | 3414 | 0.6773 | 44.9131 | 38.3312 |
62
+ | 0.0398 | 7.0 | 3983 | 0.6962 | 95.0394 | 82.5127 |
63
+ | 0.0317 | 8.0 | 4552 | 0.7284 | 55.6288 | 46.0103 |
64
+ | 0.0187 | 9.0 | 5121 | 0.7376 | 55.4347 | 44.4601 |
65
+ | 0.0099 | 10.0 | 5690 | 0.7598 | 53.4066 | 42.1512 |
66
+ | 0.01 | 11.0 | 6259 | 0.7753 | 82.2222 | 67.2734 |
67
+ | 0.0032 | 12.0 | 6828 | 0.7852 | 65.0119 | 47.9815 |
68
+ | 0.0019 | 13.0 | 7397 | 0.7838 | 53.5530 | 40.5203 |
69
+ | 0.0037 | 14.0 | 7966 | 0.7975 | 50.7377 | 40.2000 |
70
+ | 0.0007 | 15.0 | 8535 | 0.8026 | 45.6233 | 36.3097 |
71
+ | 0.0013 | 16.0 | 9104 | 0.8134 | 56.5001 | 44.4010 |
72
+ | 0.0002 | 17.0 | 9673 | 0.8082 | 57.5654 | 46.8896 |
73
+ | 0.0002 | 18.0 | 10242 | 0.8203 | 62.1234 | 49.8199 |
74
+ | 0.0001 | 19.0 | 10811 | 0.8270 | 57.0346 | 46.1639 |
75
+ | 0.0001 | 20.0 | 11380 | 0.8271 | 58.2317 | 46.8054 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b20a73c369a0726b21be307cb7e102f8b0a7c3445927c88db2a20ce1fb776733
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff07e1d3cd93360b80a34ae6969df3eb653579b7fc5b79ea596592ed9e94200
3
  size 966995080