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-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4473
-- Wer: 0.3872
+- Loss: 0.4285
+- Wer: 0.3662
 
 ## Model description
 
@@ -50,13 +50,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.3125        | 4.03  | 500  | 0.5989          | 0.6027 |
-| 0.2534        | 8.06  | 1000 | 0.4623          | 0.4681 |
-| 0.1077        | 12.1  | 1500 | 0.4736          | 0.4244 |
-| 0.0648        | 16.13 | 2000 | 0.4592          | 0.4138 |
-| 0.0439        | 20.16 | 2500 | 0.4601          | 0.4027 |
-| 0.0294        | 24.19 | 3000 | 0.4564          | 0.3954 |
-| 0.02          | 28.22 | 3500 | 0.4473          | 0.3872 |
+| 2.1571        | 4.03  | 500  | 0.5235          | 0.5098 |
+| 0.2001        | 8.06  | 1000 | 0.4172          | 0.4375 |
+| 0.0968        | 12.1  | 1500 | 0.4562          | 0.4016 |
+| 0.0607        | 16.13 | 2000 | 0.4640          | 0.4050 |
+| 0.0409        | 20.16 | 2500 | 0.4688          | 0.3914 |
+| 0.0273        | 24.19 | 3000 | 0.4414          | 0.3763 |
+| 0.0181        | 28.22 | 3500 | 0.4285          | 0.3662 |
 
 
 ### Framework versions