update model card README.md

README.md

@@ -1,11 +1,7 @@
 ---
 license: apache-2.0
-language:
-- pa
-- pa-IN
 tags:
 - generated_from_trainer
-- robust-speech-event
 datasets:
 - common_voice
 model-index:
@@ -20,8 +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: 2.7000
-- Wer: 0.9270
+- Loss: 1.7013
+- Wer: 0.8296
 
 ## Model description
 
@@ -40,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.000705
+- learning_rate: 0.0003
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -56,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 7.2796        | 24.97  | 400  | 3.4982          | 1.0    |
-| 3.5042        | 49.97  | 800  | 3.2698          | 1.0    |
-| 2.3524        | 74.97  | 1200 | 2.1014          | 0.9568 |
-| 1.1559        | 99.97  | 1600 | 2.3723          | 0.9281 |
-| 0.8267        | 124.97 | 2000 | 2.7000          | 0.9270 |
+| 8.4457        | 24.97  | 400  | 3.4891          | 1.0    |
+| 3.5215        | 49.97  | 800  | 3.3485          | 1.0    |
+| 2.5781        | 74.97  | 1200 | 1.7638          | 0.9209 |
+| 1.1329        | 99.97  | 1600 | 1.6719          | 0.8539 |
+| 0.8132        | 124.97 | 2000 | 1.7013          | 0.8296 |
 
 
 ### Framework versions