update model card README.md

README.md

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4313
-- Wer: 0.3407
+- Loss: 0.4180
+- Wer: 0.3364
 
 ## Model description
 
@@ -48,13 +48,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.7189        | 4.0   | 500  | 2.7870          | 1.0    |
-| 1.0919        | 8.0   | 1000 | 0.5166          | 0.4745 |
-| 0.3253        | 12.0  | 1500 | 0.4438          | 0.4012 |
-| 0.1814        | 16.0  | 2000 | 0.4103          | 0.3662 |
-| 0.1338        | 20.0  | 2500 | 0.4436          | 0.3581 |
-| 0.1107        | 24.0  | 3000 | 0.4406          | 0.3481 |
-| 0.0849        | 28.0  | 3500 | 0.4313          | 0.3407 |
+| 3.7066        | 4.0   | 500  | 2.1242          | 1.0273 |
+| 0.9081        | 8.0   | 1000 | 0.4490          | 0.4506 |
+| 0.2949        | 12.0  | 1500 | 0.4029          | 0.3882 |
+| 0.1693        | 16.0  | 2000 | 0.4160          | 0.3655 |
+| 0.1286        | 20.0  | 2500 | 0.4418          | 0.3519 |
+| 0.1067        | 24.0  | 3000 | 0.4464          | 0.3422 |
+| 0.0808        | 28.0  | 3500 | 0.4180          | 0.3364 |
 
 
 ### Framework versions