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: 2.1711
-- Wer: 1.0
+- Loss: 0.7467
+- Wer: 0.7530
 
 ## Model description
 
@@ -45,13 +45,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 6.984         | 0.74  | 100  | 3.5836          | 1.0 |
-| 3.1598        | 1.47  | 200  | 3.3123          | 1.0 |
-| 3.0569        | 2.21  | 300  | 3.1985          | 1.0 |
-| 3.0107        | 2.94  | 400  | 3.1421          | 1.0 |
-| 2.76          | 3.68  | 500  | 2.1711          | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.5472        | 0.74  | 100  | 1.1651          | 0.9010 |
+| 1.2501        | 1.47  | 200  | 0.9557          | 0.8303 |
+| 1.0422        | 2.21  | 300  | 0.8295          | 0.7948 |
+| 0.9174        | 2.94  | 400  | 0.7508          | 0.7637 |
+| 0.8191        | 3.68  | 500  | 0.7467          | 0.7530 |
 
 
 ### Framework versions