GGarri commited on
Commit
4c9474a
·
verified ·
1 Parent(s): 16864a5

End of training

Browse files
Files changed (1) hide show
  1. README.md +24 -24
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 2.590564448188711
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the customdata dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0041
36
- - Cer: 2.4925
37
- - Wer: 2.5906
38
 
39
  ## Model description
40
 
@@ -67,26 +67,26 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
70
- | 3.4996 | 0.89 | 25 | 3.1447 | 75.5887 | 19.7136 |
71
- | 2.655 | 1.79 | 50 | 2.1647 | 74.1483 | 18.1761 |
72
- | 1.7168 | 2.68 | 75 | 1.2822 | 71.8061 | 17.2283 |
73
- | 0.9261 | 3.57 | 100 | 0.6754 | 63.5396 | 51.5586 |
74
- | 0.4707 | 4.46 | 125 | 0.3511 | 40.5686 | 37.3842 |
75
- | 0.2485 | 5.36 | 150 | 0.2027 | 27.9309 | 25.6950 |
76
- | 0.1463 | 6.25 | 175 | 0.1315 | 24.7119 | 23.9890 |
77
- | 0.1022 | 7.14 | 200 | 0.0881 | 21.1924 | 19.9242 |
78
- | 0.0642 | 8.04 | 225 | 0.0501 | 18.7625 | 17.6917 |
79
- | 0.0249 | 8.93 | 250 | 0.0144 | 27.2044 | 26.3479 |
80
- | 0.0056 | 9.82 | 275 | 0.0082 | 12.4749 | 11.9208 |
81
- | 0.0036 | 10.71 | 300 | 0.0067 | 8.5922 | 8.7616 |
82
- | 0.0037 | 11.61 | 325 | 0.0119 | 6.4003 | 6.1500 |
83
- | 0.0021 | 12.5 | 350 | 0.0054 | 3.7450 | 3.6015 |
84
- | 0.0013 | 13.39 | 375 | 0.0052 | 2.8557 | 3.0329 |
85
- | 0.0017 | 14.29 | 400 | 0.0062 | 9.0681 | 8.3825 |
86
- | 0.0016 | 15.18 | 425 | 0.0081 | 4.9098 | 5.3917 |
87
- | 0.0012 | 16.07 | 450 | 0.0108 | 14.5541 | 13.3530 |
88
- | 0.0014 | 16.96 | 475 | 0.0033 | 3.4068 | 3.4120 |
89
- | 0.0005 | 17.86 | 500 | 0.0041 | 2.4925 | 2.5906 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 6.9309637730690365
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the customdata dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.0268
36
+ - Cer: 6.5045
37
+ - Wer: 6.9310
38
 
39
  ## Model description
40
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
70
+ | 3.6391 | 0.54 | 25 | 3.3230 | 83.6552 | 35.4340 |
71
+ | 2.7648 | 1.09 | 50 | 2.3011 | 81.2725 | 31.6473 |
72
+ | 1.8272 | 1.63 | 75 | 1.4490 | 85.9460 | 43.8688 |
73
+ | 1.0827 | 2.17 | 100 | 0.8137 | 72.8033 | 59.1524 |
74
+ | 0.6201 | 2.72 | 125 | 0.4756 | 50.5476 | 49.9522 |
75
+ | 0.3539 | 3.26 | 150 | 0.3005 | 31.1094 | 31.5926 |
76
+ | 0.2358 | 3.8 | 175 | 0.1969 | 29.5962 | 31.3192 |
77
+ | 0.1501 | 4.35 | 200 | 0.1352 | 21.1688 | 21.7772 |
78
+ | 0.0967 | 4.89 | 225 | 0.0846 | 18.6941 | 19.0431 |
79
+ | 0.0471 | 5.43 | 250 | 0.0350 | 18.3931 | 18.9200 |
80
+ | 0.0162 | 5.98 | 275 | 0.0335 | 18.9616 | 19.5215 |
81
+ | 0.0121 | 6.52 | 300 | 0.0324 | 14.1293 | 15.5707 |
82
+ | 0.011 | 7.07 | 325 | 0.0261 | 12.9755 | 14.3267 |
83
+ | 0.0078 | 7.61 | 350 | 0.0223 | 9.3220 | 10.5400 |
84
+ | 0.0075 | 8.15 | 375 | 0.0217 | 5.8106 | 6.5482 |
85
+ | 0.0052 | 8.7 | 400 | 0.0208 | 7.9926 | 8.6945 |
86
+ | 0.0048 | 9.24 | 425 | 0.0213 | 5.3424 | 5.7280 |
87
+ | 0.0053 | 9.78 | 450 | 0.0212 | 7.5328 | 7.9973 |
88
+ | 0.004 | 10.33 | 475 | 0.0213 | 5.7186 | 5.9740 |
89
+ | 0.0054 | 10.87 | 500 | 0.0268 | 6.5045 | 6.9310 |
90
 
91
 
92
  ### Framework versions