update model card README.md

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-arabic](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-arabic) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4871
-- Wer: 0.5572
+- Loss: 0.7583
+- Wer: 0.8093
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 3e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.8457        | 6.06  | 400  | 0.4179          | 0.5728 |
-| 0.2906        | 12.12 | 800  | 0.4657          | 0.5852 |
-| 0.2018        | 18.18 | 1200 | 0.4544          | 0.5638 |
-| 0.1433        | 24.24 | 1600 | 0.4871          | 0.5572 |
+| 9.6354        | 6.06  | 400  | 3.0334          | 1.0    |
+| 1.6084        | 12.12 | 800  | 0.9223          | 0.8384 |
+| 0.3271        | 18.18 | 1200 | 0.8134          | 0.8119 |
+| 0.2483        | 24.24 | 1600 | 0.7583          | 0.8093 |
 
 
 ### Framework versions