update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the librispeech_asr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2318
-- Wer: 1.5487
+- Loss: 3.5264
+- Wer: 1.7073
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.799         | 0.28  | 500  | 5.4513          | 1.9664 |
-| 4.808         | 0.56  | 1000 | 5.3161          | 1.9637 |
-| 4.8826        | 0.84  | 1500 | 5.1102          | 1.9787 |
-| 4.1926        | 1.12  | 2000 | 5.0165          | 1.9481 |
-| 4.3364        | 1.4   | 2500 | 4.9677          | 1.7883 |
-| 4.1573        | 1.68  | 3000 | 4.7702          | 1.9016 |
-| 3.9193        | 1.96  | 3500 | 4.5930          | 1.8681 |
-| 3.127         | 2.24  | 4000 | 4.3655          | 1.7748 |
-| 2.7945        | 2.52  | 4500 | 3.8526          | 1.6525 |
-| 2.1143        | 2.8   | 5000 | 3.2318          | 1.5487 |
+| 4.4032        | 0.28  | 500  | 4.6724          | 1.9406 |
+| 4.6417        | 0.56  | 1000 | 4.7143          | 1.8874 |
+| 4.5725        | 0.84  | 1500 | 4.6413          | 1.9451 |
+| 4.0178        | 1.12  | 2000 | 4.5470          | 1.8861 |
+| 3.9084        | 1.4   | 2500 | 4.4360          | 1.8881 |
+| 3.9297        | 1.68  | 3000 | 4.2814          | 1.8652 |
+| 3.707         | 1.96  | 3500 | 4.1035          | 1.8320 |
+| 3.1373        | 2.24  | 4000 | 3.9557          | 1.7762 |
+| 3.3152        | 2.52  | 4500 | 3.7737          | 1.7454 |
+| 2.9501        | 2.8   | 5000 | 3.5264          | 1.7073 |
 
 
 ### Framework versions