nrshoudi commited on
Commit
005a93d
1 Parent(s): 8d659e0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -33
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0136
20
- - Wer: 0.0322
21
- - Cer: 0.0110
22
 
23
  ## Model description
24
 
@@ -53,36 +53,36 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
56
- | 11.9559 | 1.0 | 51 | 4.0498 | 1.0 | 1.0 |
57
- | 3.4291 | 2.0 | 102 | 3.1451 | 1.0 | 1.0 |
58
- | 3.1695 | 3.0 | 153 | 3.1403 | 1.0 | 1.0 |
59
- | 3.1385 | 4.0 | 204 | 3.0922 | 1.0 | 1.0 |
60
- | 3.0936 | 5.0 | 255 | 3.0580 | 1.0 | 1.0 |
61
- | 3.0079 | 6.0 | 306 | 2.8385 | 1.0 | 1.0 |
62
- | 2.6483 | 7.0 | 357 | 2.1765 | 1.0 | 0.9806 |
63
- | 1.6589 | 8.0 | 408 | 0.7955 | 0.8652 | 0.4629 |
64
- | 0.5616 | 9.0 | 459 | 0.1553 | 0.2185 | 0.0561 |
65
- | 0.2056 | 10.0 | 510 | 0.0578 | 0.0867 | 0.0225 |
66
- | 0.1104 | 11.0 | 561 | 0.0485 | 0.0881 | 0.0277 |
67
- | 0.0903 | 12.0 | 612 | 0.0345 | 0.0480 | 0.0132 |
68
- | 0.067 | 13.0 | 663 | 0.0279 | 0.0365 | 0.0110 |
69
- | 0.0616 | 14.0 | 714 | 0.0292 | 0.0570 | 0.0183 |
70
- | 0.043 | 15.0 | 765 | 0.0210 | 0.0554 | 0.0199 |
71
- | 0.0353 | 16.0 | 816 | 0.0190 | 0.0494 | 0.0173 |
72
- | 0.0329 | 17.0 | 867 | 0.0203 | 0.0443 | 0.0147 |
73
- | 0.0318 | 18.0 | 918 | 0.0248 | 0.0446 | 0.0160 |
74
- | 0.0283 | 19.0 | 969 | 0.0203 | 0.0337 | 0.0100 |
75
- | 0.0242 | 20.0 | 1020 | 0.0193 | 0.0230 | 0.0056 |
76
- | 0.0216 | 21.0 | 1071 | 0.0185 | 0.0233 | 0.0066 |
77
- | 0.02 | 22.0 | 1122 | 0.0159 | 0.0267 | 0.0077 |
78
- | 0.0176 | 23.0 | 1173 | 0.0165 | 0.0244 | 0.0078 |
79
- | 0.0184 | 24.0 | 1224 | 0.0171 | 0.0298 | 0.0090 |
80
- | 0.0146 | 25.0 | 1275 | 0.0154 | 0.0344 | 0.0129 |
81
- | 0.0126 | 26.0 | 1326 | 0.0156 | 0.0337 | 0.0119 |
82
- | 0.0135 | 27.0 | 1377 | 0.0143 | 0.0354 | 0.0121 |
83
- | 0.0148 | 28.0 | 1428 | 0.0136 | 0.0313 | 0.0110 |
84
- | 0.011 | 29.0 | 1479 | 0.0140 | 0.0324 | 0.0107 |
85
- | 0.0107 | 30.0 | 1530 | 0.0136 | 0.0322 | 0.0110 |
86
 
87
 
88
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0028
20
+ - Wer: 0.0691
21
+ - Cer: 0.0318
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
56
+ | 17.5167 | 1.0 | 51 | 4.8815 | 1.0 | 1.0 |
57
+ | 4.0416 | 2.0 | 102 | 3.1278 | 1.0 | 1.0 |
58
+ | 3.1594 | 3.0 | 153 | 3.1154 | 1.0 | 1.0 |
59
+ | 3.1534 | 4.0 | 204 | 3.0524 | 1.0 | 1.0 |
60
+ | 3.0361 | 5.0 | 255 | 2.8827 | 1.0 | 1.0 |
61
+ | 2.799 | 6.0 | 306 | 2.4063 | 1.0 | 0.9571 |
62
+ | 1.9731 | 7.0 | 357 | 1.0794 | 0.9762 | 0.5933 |
63
+ | 0.7265 | 8.0 | 408 | 0.2350 | 0.4686 | 0.1378 |
64
+ | 0.2788 | 9.0 | 459 | 0.0527 | 0.1055 | 0.0265 |
65
+ | 0.1396 | 10.0 | 510 | 0.0263 | 0.1063 | 0.0386 |
66
+ | 0.0891 | 11.0 | 561 | 0.0245 | 0.0829 | 0.0247 |
67
+ | 0.0667 | 12.0 | 612 | 0.0119 | 0.0368 | 0.0091 |
68
+ | 0.0594 | 13.0 | 663 | 0.0154 | 0.0405 | 0.0113 |
69
+ | 0.0467 | 14.0 | 714 | 0.0109 | 0.0509 | 0.0203 |
70
+ | 0.0354 | 15.0 | 765 | 0.0129 | 0.0818 | 0.0320 |
71
+ | 0.0332 | 16.0 | 816 | 0.0086 | 0.0933 | 0.0486 |
72
+ | 0.0283 | 17.0 | 867 | 0.0135 | 0.0970 | 0.0431 |
73
+ | 0.0244 | 18.0 | 918 | 0.0083 | 0.0650 | 0.0276 |
74
+ | 0.0268 | 19.0 | 969 | 0.0071 | 0.0286 | 0.0101 |
75
+ | 0.0245 | 20.0 | 1020 | 0.0058 | 0.0320 | 0.0120 |
76
+ | 0.0206 | 21.0 | 1071 | 0.0031 | 0.1059 | 0.0455 |
77
+ | 0.0162 | 22.0 | 1122 | 0.0050 | 0.0699 | 0.0292 |
78
+ | 0.0152 | 23.0 | 1173 | 0.0054 | 0.0517 | 0.0192 |
79
+ | 0.014 | 24.0 | 1224 | 0.0037 | 0.0654 | 0.0266 |
80
+ | 0.0161 | 25.0 | 1275 | 0.0024 | 0.0320 | 0.0127 |
81
+ | 0.0156 | 26.0 | 1326 | 0.0027 | 0.0565 | 0.0244 |
82
+ | 0.0122 | 27.0 | 1377 | 0.0036 | 0.0587 | 0.0260 |
83
+ | 0.0105 | 28.0 | 1428 | 0.0026 | 0.0494 | 0.0216 |
84
+ | 0.0114 | 29.0 | 1479 | 0.0028 | 0.0613 | 0.0283 |
85
+ | 0.0087 | 30.0 | 1530 | 0.0028 | 0.0691 | 0.0318 |
86
 
87
 
88
  ### Framework versions