Hugging Face's logo

slplab
/
wav2vec2-xls-r-300m_phone-mfa_korean

Automatic Speech Recognition
Transformers
PyTorch
Korean
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
4
slplab commited on
Commit
c5231b4
•
1 Parent(s): 7471b79

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -18
README.md CHANGED
@@ -49,24 +49,9 @@ The following hyperparameters were used during training:
49
  - num_epochs: 20 (EarlyStopping: patience -5)
50
  - mixed_precision_training: Native AMP
51
 
52
- ### Training results
53
-
54
- | Training Loss | Epoch | Step | Validation Loss | PER | Rate |
55
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
56
- | 5.1523 | 1.0 | 3362 | 0.6130 | 0.1649 | 0.0000 |
57
- | 0.512 | 2.0 | 6724 | 0.2874 | 0.0959 | 0.0000 |
58
- | 0.3554 | 3.0 | 10086 | 0.2540 | 0.0868 | 0.0001 |
59
- | 0.2992 | 4.0 | 13448 | 0.2578 | 0.0749 | 0.0001 |
60
- | 0.2619 | 5.0 | 16810 | 0.2524 | 0.0808 | 0.0001 |
61
- | 0.2313 | 6.0 | 20172 | 0.2496 | 0.0738 | 0.0001 |
62
- | 0.2084 | 7.0 | 23534 | 0.2420 | 0.0523 | 0.0001 |
63
- | 0.1928 | 8.0 | 26896 | 0.2425 | 0.0523 | 0.0001 |
64
- | 0.1791 | 9.0 | 30258 | 0.2426 | 0.0748 | 0.0001 |
65
- | 0.1678 | 10.0 | 33620 | 0.2427 | 0.0752 | 0.0001 |
66
- | 0.1584 | 11.0 | 36982 | 0.2526 | 0.0792 | 0.0001 |
67
- | 0.1483 | 12.0 | 40344 | 0.2517 | 0.0763 | 0.0001 |
68
-
69
- Final Result: PER 3.88%
70
 
71
  ### Framework versions
72
 
 
49
  - num_epochs: 20 (EarlyStopping: patience -5)
50
  - mixed_precision_training: Native AMP
51
 
52
+ ### Evaluation Result
53
+
54
+ Phone Error Rate 3.88%
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
  ### Framework versions
57