update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_10_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3157
-- Wer: 0.2980
+- Loss: 0.3076
+- Wer: 0.2971
 
 ## Model description
 
@@ -52,12 +52,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.9536        | 9.99  | 570  | 2.8267          | 1.0    |
-| 1.4237        | 19.99 | 1140 | 0.4130          | 0.4141 |
-| 0.7445        | 29.99 | 1710 | 0.3580          | 0.3569 |
-| 0.5797        | 39.99 | 2280 | 0.3324          | 0.3308 |
-| 0.5155        | 49.99 | 2850 | 0.3257          | 0.3047 |
-| 0.468         | 59.99 | 3420 | 0.3157          | 0.2980 |
+| 2.9436        | 9.99  | 570  | 2.7467          | 1.0    |
+| 1.0498        | 19.99 | 1140 | 0.3630          | 0.3965 |
+| 0.6789        | 29.99 | 1710 | 0.3396          | 0.3712 |
+| 0.5259        | 39.99 | 2280 | 0.3204          | 0.3241 |
+| 0.4701        | 49.99 | 2850 | 0.3118          | 0.3005 |
+| 0.4248        | 59.99 | 3420 | 0.3076          | 0.2971 |
 
 
 ### Framework versions