update model card README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: Model_G_S_Berita_Wav2Vec2
   results: []
@@ -13,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0238
-- Wer: 0.0266
-- Cer: 0.0049
+- Loss: 0.0239
+- Wer: 0.0350
+- Cer: 0.0055
 
 ## Model description
 
@@ -44,19 +46,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 30
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.3377        | 12.5  | 400  | 0.0482          | 0.0748 | 0.0118 |
-| 0.0269        | 25.0  | 800  | 0.0238          | 0.0266 | 0.0049 |
+| 0.3535        | 12.5  | 400  | 0.0680          | 0.0888 | 0.0139 |
+| 0.0269        | 25.0  | 800  | 0.0239          | 0.0350 | 0.0055 |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
-- Pytorch 1.10.0+cu113
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu117
 - Datasets 1.18.3
-- Tokenizers 0.10.3
+- Tokenizers 0.13.3