update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.982200647249191
+      value: 0.9852897911150338
 ---
 
 <!-- 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-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0914
-- Accuracy: 0.9822
+- Loss: 0.0639
+- Accuracy: 0.9853
 
 ## Model description
 
@@ -67,11 +67,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7748        | 1.0   | 399  | 0.6609          | 0.9345   |
-| 0.2856        | 2.0   | 798  | 0.1977          | 0.9787   |
-| 0.2129        | 3.0   | 1197 | 0.1209          | 0.9793   |
-| 0.1998        | 4.0   | 1597 | 0.0959          | 0.9815   |
-| 0.1712        | 5.0   | 1995 | 0.0914          | 0.9822   |
+| 0.1557        | 1.0   | 399  | 0.0856          | 0.9826   |
+| 0.1589        | 2.0   | 798  | 0.0826          | 0.9818   |
+| 0.1461        | 3.0   | 1197 | 0.0714          | 0.9822   |
+| 0.0897        | 4.0   | 1597 | 0.0639          | 0.9853   |
+| 0.1179        | 5.0   | 1995 | 0.0623          | 0.9851   |
 
 
 ### Framework versions