update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.7268527430221366
+      value: 0.5094757094757095
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9616
-- Wer: 0.7269
+- Loss: 1.1240
+- Wer: 0.5095
 
 ## Model description
 
@@ -53,22 +53,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- num_epochs: 30
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.4788        | 1.34  | 400  | 1.8828          | 0.9834 |
-| 1.2166        | 2.69  | 800  | 0.9616          | 0.7269 |
+| 5.1179        | 3.12  | 400  | 1.3528          | 0.8758 |
+| 0.8834        | 6.25  | 800  | 0.9791          | 0.6978 |
+| 0.4513        | 9.38  | 1200 | 0.9412          | 0.6085 |
+| 0.291         | 12.5  | 1600 | 1.0826          | 0.5874 |
+| 0.2133        | 15.62 | 2000 | 1.0616          | 0.5589 |
+| 0.1653        | 18.75 | 2400 | 1.0475          | 0.5519 |
+| 0.1235        | 21.88 | 2800 | 1.0702          | 0.5293 |
+| 0.0927        | 25.0  | 3200 | 1.1390          | 0.5219 |
+| 0.0698        | 28.12 | 3600 | 1.1240          | 0.5095 |
 
 
 ### Framework versions