Hugging Face's logo

scasutt
/
wav2vec2-large-xlsr-53_toy_train_data_augment_0.1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
scasutt commited on
Commit
c39376a
·
1 Parent(s): 2e67b8f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
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: 0.4808
18
- - Wer: 0.4983
19
 
20
  ## Model description
21
 
@@ -49,25 +49,25 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
- | 3.4085 | 1.05 | 250 | 3.4285 | 0.9954 |
53
- | 3.0869 | 2.1 | 500 | 3.4855 | 0.9954 |
54
- | 3.0654 | 3.15 | 750 | 3.3135 | 0.9954 |
55
- | 2.5647 | 4.2 | 1000 | 1.4535 | 0.9291 |
56
- | 1.641 | 5.25 | 1250 | 0.8070 | 0.7470 |
57
- | 1.3116 | 6.3 | 1500 | 0.6627 | 0.6804 |
58
- | 1.2153 | 7.35 | 1750 | 0.5830 | 0.6281 |
59
- | 1.1038 | 8.4 | 2000 | 0.5565 | 0.5924 |
60
- | 1.0305 | 9.45 | 2250 | 0.5242 | 0.5756 |
61
- | 0.9547 | 10.5 | 2500 | 0.5270 | 0.5640 |
62
- | 0.8927 | 11.55 | 2750 | 0.5252 | 0.5474 |
63
- | 0.8508 | 12.6 | 3000 | 0.5046 | 0.5291 |
64
- | 0.8474 | 13.65 | 3250 | 0.4855 | 0.5281 |
65
- | 0.8313 | 14.7 | 3500 | 0.4760 | 0.5135 |
66
- | 0.832 | 15.75 | 3750 | 0.4845 | 0.5111 |
67
- | 0.7604 | 16.81 | 4000 | 0.4838 | 0.5080 |
68
- | 0.7834 | 17.86 | 4250 | 0.4911 | 0.5088 |
69
- | 0.7478 | 18.91 | 4500 | 0.4828 | 0.4999 |
70
- | 0.7049 | 19.96 | 4750 | 0.4808 | 0.4983 |
71
 
72
 
73
  ### 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: 0.4658
18
+ - Wer: 0.5037
19
 
20
  ## Model description
21
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 3.447 | 1.05 | 250 | 3.3799 | 1.0 |
53
+ | 3.089 | 2.1 | 500 | 3.4868 | 1.0 |
54
+ | 3.063 | 3.15 | 750 | 3.3155 | 1.0 |
55
+ | 2.4008 | 4.2 | 1000 | 1.2934 | 0.8919 |
56
+ | 1.618 | 5.25 | 1250 | 0.7847 | 0.7338 |
57
+ | 1.3038 | 6.3 | 1500 | 0.6459 | 0.6712 |
58
+ | 1.2074 | 7.35 | 1750 | 0.5705 | 0.6269 |
59
+ | 1.1062 | 8.4 | 2000 | 0.5267 | 0.5843 |
60
+ | 1.026 | 9.45 | 2250 | 0.5108 | 0.5683 |
61
+ | 0.9505 | 10.5 | 2500 | 0.5066 | 0.5568 |
62
+ | 0.893 | 11.55 | 2750 | 0.5161 | 0.5532 |
63
+ | 0.8535 | 12.6 | 3000 | 0.4994 | 0.5341 |
64
+ | 0.8462 | 13.65 | 3250 | 0.4626 | 0.5262 |
65
+ | 0.8334 | 14.7 | 3500 | 0.4593 | 0.5197 |
66
+ | 0.842 | 15.75 | 3750 | 0.4651 | 0.5126 |
67
+ | 0.7678 | 16.81 | 4000 | 0.4687 | 0.5120 |
68
+ | 0.7873 | 17.86 | 4250 | 0.4716 | 0.5070 |
69
+ | 0.7486 | 18.91 | 4500 | 0.4657 | 0.5033 |
70
+ | 0.7073 | 19.96 | 4750 | 0.4658 | 0.5037 |
71
 
72
 
73
  ### Framework versions