Hugging Face's logo

hadiqa123
/
XLS-R_53_english

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
1
hadiqa123 commited on
Commit
0d7d1fd
·
1 Parent(s): 52bd71c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -7
README.md CHANGED
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.8306
18
- - Wer: 0.6991
19
 
20
  ## Model description
21
 
@@ -48,11 +48,24 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
- | 6.1059 | 5.56 | 250 | 3.2801 | 1.0 |
52
- | 3.0169 | 11.11 | 500 | 3.1509 | 1.0 |
53
- | 2.9173 | 16.67 | 750 | 2.8107 | 1.0 |
54
- | 2.1179 | 22.22 | 1000 | 1.1816 | 0.8956 |
55
- | 1.0037 | 27.78 | 1250 | 0.8306 | 0.6991 |
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3430
18
+ - Wer: 0.3033
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Wer |
50
  |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 4.6589 | 1.65 | 500 | 3.1548 | 1.0 |
52
+ | 2.5363 | 3.3 | 1000 | 1.0250 | 0.8707 |
53
+ | 0.849 | 4.95 | 1500 | 0.3964 | 0.4636 |
54
+ | 0.4812 | 6.6 | 2000 | 0.3341 | 0.3907 |
55
+ | 0.3471 | 8.25 | 2500 | 0.3351 | 0.3659 |
56
+ | 0.2797 | 9.9 | 3000 | 0.3104 | 0.3475 |
57
+ | 0.2336 | 11.55 | 3500 | 0.3545 | 0.3419 |
58
+ | 0.2116 | 13.2 | 4000 | 0.3577 | 0.3353 |
59
+ | 0.1688 | 14.85 | 4500 | 0.3383 | 0.3302 |
60
+ | 0.1587 | 16.5 | 5000 | 0.3431 | 0.3235 |
61
+ | 0.1358 | 18.15 | 5500 | 0.3504 | 0.3209 |
62
+ | 0.1323 | 19.8 | 6000 | 0.3468 | 0.3191 |
63
+ | 0.115 | 21.45 | 6500 | 0.3331 | 0.3127 |
64
+ | 0.108 | 23.1 | 7000 | 0.3497 | 0.3099 |
65
+ | 0.0938 | 24.75 | 7500 | 0.3532 | 0.3091 |
66
+ | 0.0974 | 26.4 | 8000 | 0.3461 | 0.3086 |
67
+ | 0.0867 | 28.05 | 8500 | 0.3422 | 0.3054 |
68
+ | 0.0852 | 29.7 | 9000 | 0.3430 | 0.3033 |
69
 
70
 
71
  ### Framework versions