Hugging Face's logo

foxxy-hm
/
wav2vec2-base-finetune-vi-v5

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files Metrics Community
1
foxxy-hm commited on
Commit
0f71853
·
1 Parent(s): 87ee333

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -16
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
@@ -13,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # wav2vec2-base-finetune-vi-v5
15
 
16
- This model is a fine-tuned version of [foxxy-hm/wav2vec2-base-finetune-vi-v5](https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi-v5) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2484
19
- - Wer: 0.1527
20
 
21
  ## Model description
22
 
@@ -35,27 +36,39 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
- - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 1000
45
- - num_epochs: 4
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Wer |
50
- |:-------------:|:-----:|:----:|:---------------:|:------:|
51
- | 11.2332 | 0.49 | 500 | 3.4000 | 1.0 |
52
- | 1.4014 | 0.99 | 1000 | 0.3058 | 0.1825 |
53
- | 0.1614 | 1.48 | 1500 | 0.2742 | 0.1646 |
54
- | 0.1269 | 1.98 | 2000 | 0.2791 | 0.1628 |
55
- | 0.0991 | 2.47 | 2500 | 0.2642 | 0.1589 |
56
- | 0.0913 | 2.96 | 3000 | 0.2483 | 0.1555 |
57
- | 0.0833 | 3.46 | 3500 | 0.2528 | 0.1535 |
58
- | 0.0787 | 3.95 | 4000 | 0.2484 | 0.1527 |
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
+ license: cc-by-nc-4.0
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # wav2vec2-base-finetune-vi-v5
16
 
17
+ This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-large-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-large-vi) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2373
20
+ - Wer: 0.1681
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 16
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 20
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
+ | 20.4793 | 0.99 | 500 | 8.0023 | 1.0 |
53
+ | 4.5661 | 1.98 | 1000 | 3.4221 | 1.0 |
54
+ | 3.356 | 2.96 | 1500 | 3.2739 | 1.0 |
55
+ | 2.2533 | 3.95 | 2000 | 0.8992 | 0.4884 |
56
+ | 0.8412 | 4.94 | 2500 | 0.5181 | 0.3061 |
57
+ | 0.5738 | 5.93 | 3000 | 0.3986 | 0.2586 |
58
+ | 0.4608 | 6.92 | 3500 | 0.3545 | 0.2230 |
59
+ | 0.399 | 7.91 | 4000 | 0.3220 | 0.2003 |
60
+ | 0.341 | 8.89 | 4500 | 0.2936 | 0.1928 |
61
+ | 0.3094 | 9.88 | 5000 | 0.2727 | 0.1873 |
62
+ | 0.2834 | 10.87 | 5500 | 0.2721 | 0.1813 |
63
+ | 0.2761 | 11.86 | 6000 | 0.2704 | 0.1817 |
64
+ | 0.2505 | 12.85 | 6500 | 0.2597 | 0.1766 |
65
+ | 0.2472 | 13.83 | 7000 | 0.2460 | 0.1744 |
66
+ | 0.2335 | 14.82 | 7500 | 0.2486 | 0.1728 |
67
+ | 0.2183 | 15.81 | 8000 | 0.2430 | 0.1714 |
68
+ | 0.2153 | 16.8 | 8500 | 0.2433 | 0.1697 |
69
+ | 0.2029 | 17.79 | 9000 | 0.2408 | 0.1688 |
70
+ | 0.2094 | 18.77 | 9500 | 0.2349 | 0.1694 |
71
+ | 0.2045 | 19.76 | 10000 | 0.2373 | 0.1681 |
72
 
73
 
74
  ### Framework versions