nrshoudi commited on
Commit
9f95039
1 Parent(s): 97646f8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -34
README.md CHANGED
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # wav2vec2-large-xls-r-300m-Arabic-colab
16
 
17
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on a local dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0001
20
- - Wer: 0.0703
21
- - Cer: 0.0310
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
- | 0.1001 | 1.0 | 51 | 0.0159 | 0.0647 | 0.0295 |
57
- | 0.0576 | 2.0 | 102 | 0.0109 | 0.0819 | 0.0408 |
58
- | 0.0598 | 3.0 | 153 | 0.0096 | 0.1153 | 0.0541 |
59
- | 0.0636 | 4.0 | 204 | 0.0099 | 0.0594 | 0.0239 |
60
- | 0.0642 | 5.0 | 255 | 0.0107 | 0.1043 | 0.0447 |
61
- | 0.0551 | 6.0 | 306 | 0.0106 | 0.0575 | 0.0208 |
62
- | 0.0543 | 7.0 | 357 | 0.0078 | 0.0157 | 0.0042 |
63
- | 0.0516 | 8.0 | 408 | 0.0068 | 0.1144 | 0.0533 |
64
- | 0.0454 | 9.0 | 459 | 0.0054 | 0.1058 | 0.0547 |
65
- | 0.0308 | 10.0 | 510 | 0.0041 | 0.0742 | 0.0364 |
66
- | 0.0296 | 11.0 | 561 | 0.0042 | 0.1146 | 0.0540 |
67
- | 0.0252 | 12.0 | 612 | 0.0028 | 0.0971 | 0.0453 |
68
- | 0.0236 | 13.0 | 663 | 0.0026 | 0.0803 | 0.0359 |
69
- | 0.0238 | 14.0 | 714 | 0.0023 | 0.0783 | 0.0334 |
70
- | 0.0185 | 15.0 | 765 | 0.0023 | 0.0654 | 0.0272 |
71
- | 0.0185 | 16.0 | 816 | 0.0023 | 0.0522 | 0.0182 |
72
- | 0.0159 | 17.0 | 867 | 0.0012 | 0.0396 | 0.0130 |
73
- | 0.0161 | 18.0 | 918 | 0.0020 | 0.0580 | 0.0216 |
74
- | 0.0142 | 19.0 | 969 | 0.0010 | 0.0168 | 0.0037 |
75
- | 0.0164 | 20.0 | 1020 | 0.0009 | 0.0511 | 0.0221 |
76
- | 0.011 | 21.0 | 1071 | 0.0006 | 0.0192 | 0.0054 |
77
- | 0.0087 | 22.0 | 1122 | 0.0004 | 0.0198 | 0.0058 |
78
- | 0.0083 | 23.0 | 1173 | 0.0004 | 0.0251 | 0.0093 |
79
- | 0.0085 | 24.0 | 1224 | 0.0004 | 0.0677 | 0.0314 |
80
- | 0.0054 | 25.0 | 1275 | 0.0003 | 0.0587 | 0.0250 |
81
- | 0.0057 | 26.0 | 1326 | 0.0002 | 0.0435 | 0.0172 |
82
- | 0.007 | 27.0 | 1377 | 0.0005 | 0.0696 | 0.0305 |
83
- | 0.007 | 28.0 | 1428 | 0.0003 | 0.0673 | 0.0294 |
84
- | 0.0059 | 29.0 | 1479 | 0.0001 | 0.0688 | 0.0301 |
85
- | 0.0045 | 30.0 | 1530 | 0.0001 | 0.0703 | 0.0310 |
86
 
87
 
88
  ### Framework versions
 
14
 
15
  # wav2vec2-large-xls-r-300m-Arabic-colab
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: 0.0016
20
+ - Wer: 0.0180
21
+ - Cer: 0.0050
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
56
+ | 17.4389 | 1.0 | 51 | 5.2001 | 1.0 | 1.0 |
57
+ | 3.9365 | 2.0 | 102 | 3.1379 | 1.0 | 1.0 |
58
+ | 3.1693 | 3.0 | 153 | 3.1153 | 1.0 | 1.0 |
59
+ | 3.1436 | 4.0 | 204 | 3.0695 | 1.0 | 1.0 |
60
+ | 3.0914 | 5.0 | 255 | 2.9734 | 1.0 | 1.0 |
61
+ | 2.9509 | 6.0 | 306 | 2.7532 | 1.0 | 1.0 |
62
+ | 2.4865 | 7.0 | 357 | 1.8412 | 1.0 | 0.9310 |
63
+ | 1.2609 | 8.0 | 408 | 0.3920 | 0.5536 | 0.1712 |
64
+ | 0.4001 | 9.0 | 459 | 0.0803 | 0.1065 | 0.0262 |
65
+ | 0.1689 | 10.0 | 510 | 0.0340 | 0.0469 | 0.0119 |
66
+ | 0.1134 | 11.0 | 561 | 0.0240 | 0.0510 | 0.0150 |
67
+ | 0.0756 | 12.0 | 612 | 0.0140 | 0.0355 | 0.0106 |
68
+ | 0.0612 | 13.0 | 663 | 0.0098 | 0.0289 | 0.0086 |
69
+ | 0.0472 | 14.0 | 714 | 0.0087 | 0.0245 | 0.0066 |
70
+ | 0.0443 | 15.0 | 765 | 0.0075 | 0.0242 | 0.0066 |
71
+ | 0.0404 | 16.0 | 816 | 0.0072 | 0.0275 | 0.0079 |
72
+ | 0.0329 | 17.0 | 867 | 0.0056 | 0.0146 | 0.0040 |
73
+ | 0.0322 | 18.0 | 918 | 0.0058 | 0.0165 | 0.0044 |
74
+ | 0.0277 | 19.0 | 969 | 0.0056 | 0.0226 | 0.0063 |
75
+ | 0.0247 | 20.0 | 1020 | 0.0040 | 0.0180 | 0.0045 |
76
+ | 0.0234 | 21.0 | 1071 | 0.0050 | 0.0179 | 0.0052 |
77
+ | 0.0186 | 22.0 | 1122 | 0.0034 | 0.0138 | 0.0037 |
78
+ | 0.0178 | 23.0 | 1173 | 0.0032 | 0.0139 | 0.0039 |
79
+ | 0.0163 | 24.0 | 1224 | 0.0025 | 0.0158 | 0.0042 |
80
+ | 0.0165 | 25.0 | 1275 | 0.0023 | 0.0163 | 0.0043 |
81
+ | 0.0138 | 26.0 | 1326 | 0.0019 | 0.0141 | 0.0036 |
82
+ | 0.0145 | 27.0 | 1377 | 0.0019 | 0.0183 | 0.0047 |
83
+ | 0.0128 | 28.0 | 1428 | 0.0019 | 0.0178 | 0.0048 |
84
+ | 0.012 | 29.0 | 1479 | 0.0017 | 0.0177 | 0.0048 |
85
+ | 0.0121 | 30.0 | 1530 | 0.0016 | 0.0180 | 0.0050 |
86
 
87
 
88
  ### Framework versions