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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Wer: 0.9958
+- Loss: 0.6432
+- Wer: 0.6298
 
 ## Model description
 
@@ -50,9 +50,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 7.8995        | 0.5   | 500  | 14.0702         | 0.9960 |
-| 8.3344        | 1.01  | 1000 | 14.0704         | 0.9961 |
-| 0.0           | 1.51  | 1500 | nan             | 0.9958 |
+| 3.6199        | 0.25  | 250  | 3.6163          | 1.0    |
+| 3.0927        | 0.5   | 500  | 3.5932          | 1.0    |
+| 3.0837        | 0.76  | 750  | 3.2418          | 1.0    |
+| 2.2385        | 1.01  | 1000 | 1.2621          | 0.9855 |
+| 1.743         | 1.26  | 1250 | 1.0830          | 0.9442 |
+| 1.6661        | 1.51  | 1500 | 0.7926          | 0.8051 |
+| 1.5661        | 1.77  | 1750 | 0.6432          | 0.6298 |
 
 
 ### Framework versions