Update README.md

README.md

@@ -18,7 +18,7 @@ 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: 5.3456
-- Accuracy: 57.4
+- Accuracy: 34.4
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 5.923         | 0.94  | 12   | 5.9648          | 43.3      |
-| 5.6846        | 1.96  | 25   | 5.6787          | 45.5      |
-| 5.4614        | 2.98  | 38   | 5.4862          | 51.3      |
-| 5.1691        | 4.0   | 51   | 5.3746          | 51.2      |
-| 5.1066        | 4.71  | 60   | 5.3456          | 57.4      |
+| 5.923         | 0.94  | 12   | 5.9648          | 23.3      |
+| 5.6846        | 1.96  | 25   | 5.6787          | 28.5      |
+| 5.4614        | 2.98  | 38   | 5.4862          | 31.3      |
+| 5.1691        | 4.0   | 51   | 5.3746          | 31.2      |
+| 5.1066        | 4.71  | 60   | 5.3456          | 34.4      |
 
 
 ### Framework versions