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: 0.4311
-- Wer: 0.3357
+- Loss: 0.4473
+- Wer: 0.3380
 
 ## Model description
 
@@ -48,13 +48,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.6383        | 4.0   | 500  | 1.9206          | 1.0171 |
-| 0.8682        | 8.0   | 1000 | 0.4965          | 0.4851 |
-| 0.3047        | 12.0  | 1500 | 0.4051          | 0.3887 |
-| 0.1763        | 16.0  | 2000 | 0.4268          | 0.3692 |
-| 0.1305        | 20.0  | 2500 | 0.4363          | 0.3566 |
-| 0.11          | 24.0  | 3000 | 0.4250          | 0.3411 |
-| 0.0815        | 28.0  | 3500 | 0.4311          | 0.3357 |
+| 0.1048        | 4.0   | 500  | 0.4370          | 0.3475 |
+| 0.0871        | 8.0   | 1000 | 0.4489          | 0.3405 |
+| 0.0651        | 12.0  | 1500 | 0.4473          | 0.3380 |
+| 0.0703        | 16.0  | 2000 | 0.4473          | 0.3380 |
+| 0.0676        | 20.0  | 2500 | 0.4473          | 0.3380 |
+| 0.0714        | 24.0  | 3000 | 0.4473          | 0.3380 |
+| 0.0742        | 28.0  | 3500 | 0.4473          | 0.3380 |
 
 
 ### Framework versions