slplab
/

wav2vec2-xls-r-300m_phone-mfa_korean

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

slplab commited on Dec 31, 2022

Commit

69a6b3f

•

1 Parent(s): 18f7f3d

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -44,12 +44,12 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.2
-- num_epochs: 20
 - mixed_precision_training: Native AMP
 ### Training results
-| Training Loss | Epoch | Step  | Validation Loss | Per    | Rate   |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
 | 5.1523        | 1.0   | 3362  | 0.6130          | 0.1649 | 0.0000 |
 | 0.512         | 2.0   | 6724  | 0.2874          | 0.0959 | 0.0000 |
@@ -64,6 +64,7 @@ The following hyperparameters were used during training:
 | 0.1584        | 11.0  | 36982 | 0.2526          | 0.0792 | 0.0001 |
 | 0.1483        | 12.0  | 40344 | 0.2517          | 0.0763 | 0.0001 |
 ### Framework versions

 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 20 (EarlyStopping: patience -5)
 - mixed_precision_training: Native AMP
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss | PER    | Rate   |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
 | 5.1523        | 1.0   | 3362  | 0.6130          | 0.1649 | 0.0000 |
 | 0.512         | 2.0   | 6724  | 0.2874          | 0.0959 | 0.0000 |
 | 0.1584        | 11.0  | 36982 | 0.2526          | 0.0792 | 0.0001 |
 | 0.1483        | 12.0  | 40344 | 0.2517          | 0.0763 | 0.0001 |
+Final Result: PER 3.88%
 ### Framework versions