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
b34ee4f
•
1 Parent(s): 8fff203

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -33,7 +33,7 @@ Evaluation Data
33
  - Num. of Samples: 6,000
34
  - Audio Length: 12 Hours
35
 
36
- ### Training Hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
48
  - num_epochs: 20 (EarlyStopping: patience: 5 epochs max)
49
  - mixed_precision_training: Native AMP
50
 
51
- ### Evaluation Result
52
 
53
  Phone Error Rate 3.88%
54
 
55
- ### Output Examples
56
  ![output_examples](./output_examples.png)
57
 
58
- ### MFA-IPA Phoneset Tables
59
 
60
  # Vowels
61
  ![mfa_ipa_chart_vowels](./mfa_ipa_chart_vowels.png)
@@ -63,7 +63,7 @@ Phone Error Rate 3.88%
63
  # Consonants
64
  ![mfa_ipa_chart_consonants](./mfa_ipa_chart_consonants.png)
65
 
66
- ### Framework versions
67
 
68
  - Transformers 4.21.3
69
  - Pytorch 1.12.1
 
33
  - Num. of Samples: 6,000
34
  - Audio Length: 12 Hours
35
 
36
+ ## Training Hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
 
48
  - num_epochs: 20 (EarlyStopping: patience: 5 epochs max)
49
  - mixed_precision_training: Native AMP
50
 
51
+ ## Evaluation Result
52
 
53
  Phone Error Rate 3.88%
54
 
55
+ ## Output Examples
56
  ![output_examples](./output_examples.png)
57
 
58
+ ## MFA-IPA Phoneset Tables
59
 
60
  # Vowels
61
  ![mfa_ipa_chart_vowels](./mfa_ipa_chart_vowels.png)
 
63
  # Consonants
64
  ![mfa_ipa_chart_consonants](./mfa_ipa_chart_consonants.png)
65
 
66
+ ## Framework versions
67
 
68
  - Transformers 4.21.3
69
  - Pytorch 1.12.1