Hugging Face's logo

nrshoudi
/
wav2vec2-large-xls-r-300m-Arabic-phoneme-based-MDD-experiment2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
1
nrshoudi commited on
Commit
81f7181
•
1 Parent(s): e1126d8

Model save

Browse files
Files changed (2) hide show
  1. README.md +33 -33
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  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.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0380
21
- - Per: 0.0182
22
- - Wer: 0.0209
23
 
24
  ## Model description
25
 
@@ -53,36 +53,36 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Per | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
- | 2.3253 | 1.0 | 546 | 1.6463 | 0.9997 | 0.9990 |
57
- | 1.7194 | 2.0 | 1093 | 1.4798 | 0.9993 | 0.9985 |
58
- | 1.6318 | 3.0 | 1640 | 1.2181 | 0.9304 | 0.9399 |
59
- | 1.4017 | 4.0 | 2187 | 0.5801 | 0.2704 | 0.3889 |
60
- | 0.9203 | 5.0 | 2733 | 0.1995 | 0.1330 | 0.1439 |
61
- | 0.669 | 6.0 | 3280 | 0.1462 | 0.0867 | 0.0928 |
62
- | 0.5585 | 7.0 | 3827 | 0.0925 | 0.0739 | 0.0752 |
63
- | 0.4954 | 8.0 | 4374 | 0.0795 | 0.0601 | 0.0573 |
64
- | 0.4536 | 9.0 | 4920 | 0.0714 | 0.0498 | 0.0530 |
65
- | 0.4183 | 10.0 | 5467 | 0.0726 | 0.0652 | 0.0679 |
66
- | 0.3896 | 11.0 | 6014 | 0.0782 | 0.0566 | 0.0553 |
67
- | 0.3643 | 12.0 | 6561 | 0.0713 | 0.0502 | 0.0514 |
68
- | 0.3391 | 13.0 | 7107 | 0.0928 | 0.0693 | 0.0702 |
69
- | 0.3229 | 14.0 | 7654 | 0.0596 | 0.0503 | 0.0484 |
70
- | 0.3038 | 15.0 | 8201 | 0.0651 | 0.0531 | 0.0547 |
71
- | 0.2853 | 16.0 | 8748 | 0.0577 | 0.0483 | 0.0473 |
72
- | 0.2736 | 17.0 | 9294 | 0.0542 | 0.0463 | 0.0485 |
73
- | 0.2603 | 18.0 | 9841 | 0.0519 | 0.0327 | 0.0325 |
74
- | 0.2472 | 19.0 | 10388 | 0.0513 | 0.0336 | 0.0351 |
75
- | 0.2346 | 20.0 | 10935 | 0.0589 | 0.0281 | 0.0310 |
76
- | 0.2265 | 21.0 | 11481 | 0.0499 | 0.0285 | 0.0312 |
77
- | 0.214 | 22.0 | 12028 | 0.0485 | 0.0281 | 0.0342 |
78
- | 0.2045 | 23.0 | 12575 | 0.0479 | 0.0273 | 0.0295 |
79
- | 0.1917 | 24.0 | 13122 | 0.0457 | 0.0267 | 0.0286 |
80
- | 0.1814 | 25.0 | 13668 | 0.0423 | 0.0224 | 0.0265 |
81
- | 0.1769 | 26.0 | 14215 | 0.0442 | 0.0243 | 0.0264 |
82
- | 0.1682 | 27.0 | 14762 | 0.0396 | 0.0200 | 0.0235 |
83
- | 0.161 | 28.0 | 15309 | 0.0386 | 0.0190 | 0.0225 |
84
- | 0.1572 | 29.0 | 15855 | 0.0383 | 0.0186 | 0.0216 |
85
- | 0.1502 | 29.96 | 16380 | 0.0380 | 0.0182 | 0.0209 |
86
 
87
 
88
  ### Framework versions
 
17
 
18
  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.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0434
21
+ - Per: 0.0207
22
+ - Wer: 0.0212
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Per | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
+ | 2.4593 | 1.0 | 546 | 1.6587 | 0.9769 | 0.9819 |
57
+ | 1.7776 | 2.0 | 1093 | 1.5794 | 0.9995 | 0.9994 |
58
+ | 1.733 | 3.0 | 1640 | 1.5264 | 0.9998 | 0.9998 |
59
+ | 1.6734 | 4.0 | 2187 | 1.3536 | 0.9948 | 0.9831 |
60
+ | 1.5266 | 5.0 | 2733 | 0.8784 | 0.6903 | 0.7321 |
61
+ | 1.1705 | 6.0 | 3280 | 0.3408 | 0.2076 | 0.2568 |
62
+ | 0.8237 | 7.0 | 3827 | 0.1968 | 0.1045 | 0.1223 |
63
+ | 0.66 | 8.0 | 4374 | 0.1400 | 0.0756 | 0.0851 |
64
+ | 0.5747 | 9.0 | 4920 | 0.0954 | 0.0665 | 0.0659 |
65
+ | 0.5063 | 10.0 | 5467 | 0.0999 | 0.0645 | 0.0650 |
66
+ | 0.4641 | 11.0 | 6014 | 0.0800 | 0.0545 | 0.0572 |
67
+ | 0.4246 | 12.0 | 6561 | 0.0783 | 0.0512 | 0.0506 |
68
+ | 0.3957 | 13.0 | 7107 | 0.0780 | 0.0494 | 0.0516 |
69
+ | 0.3693 | 14.0 | 7654 | 0.0647 | 0.0393 | 0.0411 |
70
+ | 0.3517 | 15.0 | 8201 | 0.0597 | 0.0364 | 0.0370 |
71
+ | 0.3292 | 16.0 | 8748 | 0.0577 | 0.0356 | 0.0361 |
72
+ | 0.3079 | 17.0 | 9294 | 0.0573 | 0.0346 | 0.0362 |
73
+ | 0.2946 | 18.0 | 9841 | 0.0622 | 0.0350 | 0.0389 |
74
+ | 0.2735 | 19.0 | 10388 | 0.0525 | 0.0293 | 0.0300 |
75
+ | 0.2588 | 20.0 | 10935 | 0.0553 | 0.0254 | 0.0283 |
76
+ | 0.2477 | 21.0 | 11481 | 0.0479 | 0.0244 | 0.0259 |
77
+ | 0.2346 | 22.0 | 12028 | 0.0560 | 0.0280 | 0.0283 |
78
+ | 0.222 | 23.0 | 12575 | 0.0421 | 0.0242 | 0.0250 |
79
+ | 0.208 | 24.0 | 13122 | 0.0508 | 0.0240 | 0.0245 |
80
+ | 0.2002 | 25.0 | 13668 | 0.0435 | 0.0218 | 0.0223 |
81
+ | 0.1912 | 26.0 | 14215 | 0.0477 | 0.0225 | 0.0239 |
82
+ | 0.1823 | 27.0 | 14762 | 0.0414 | 0.0210 | 0.0214 |
83
+ | 0.1745 | 28.0 | 15309 | 0.0434 | 0.0212 | 0.0216 |
84
+ | 0.1703 | 29.0 | 15855 | 0.0427 | 0.0202 | 0.0212 |
85
+ | 0.163 | 29.96 | 16380 | 0.0434 | 0.0207 | 0.0212 |
86
 
87
 
88
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f900ed1b08cb3c12e46ee4e817d0c33c5dbadb574520c284d904203613a3e087
3
  size 1262053549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a41c24d83004cd6e57080b7e12e4d467f74437d3ef59bcd42b6c36e2936cba9
3
  size 1262053549