update model card README.md

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
-- google_colab
 datasets:
 - common_voice
 model-index:
@@ -17,8 +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 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3596
-- Wer: 0.3242
+- Loss: 0.3864
+- Wer: 0.3570
 
 ## Model description
 
@@ -53,19 +52,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.7652        | 3.67  | 400  | 0.6255          | 0.6933 |
-| 0.3716        | 7.34  | 800  | 0.4058          | 0.4563 |
-| 0.1779        | 11.01 | 1200 | 0.4128          | 0.4080 |
-| 0.1226        | 14.68 | 1600 | 0.3998          | 0.3941 |
-| 0.0927        | 18.35 | 2000 | 0.4084          | 0.3713 |
-| 0.0737        | 22.02 | 2400 | 0.3949          | 0.3520 |
-| 0.0581        | 25.69 | 2800 | 0.3698          | 0.3311 |
-| 0.0453        | 29.36 | 3200 | 0.3596          | 0.3242 |
+| 3.8302        | 3.67  | 400  | 0.6702          | 0.6903 |
+| 0.4098        | 7.34  | 800  | 0.4574          | 0.4939 |
+| 0.1908        | 11.01 | 1200 | 0.4350          | 0.4557 |
+| 0.1279        | 14.68 | 1600 | 0.4204          | 0.4213 |
+| 0.0966        | 18.35 | 2000 | 0.4238          | 0.3991 |
+| 0.0782        | 22.02 | 2400 | 0.3822          | 0.3906 |
+| 0.0613        | 25.69 | 2800 | 0.3982          | 0.3714 |
+| 0.0477        | 29.36 | 3200 | 0.3864          | 0.3570 |
 
 
 ### Framework versions
 
 - Transformers 4.11.3
-- Pytorch 1.10.0+cu111
-- Datasets 1.13.3
+- Pytorch 1.10.0+cu113
+- Datasets 1.18.3
 - Tokenizers 0.10.3