update model card README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # HO_ASR-Model_KIIT2025
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
+This model is a fine-tuned version of [/content/HO_ASR-Model_KIIT2025/checkpoint-6250/](https://huggingface.co//content/HO_ASR-Model_KIIT2025/checkpoint-6250/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6844
-- Wer: 0.5516
+- Loss: 0.7268
+- Wer: 0.5447
 
 ## Model description
 
@@ -45,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 250
-- num_epochs: 50
+- num_epochs: 75
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -77,6 +76,18 @@ The following hyperparameters were used during training:
 | 0.0591        | 46.0  | 5750 | 0.6809          | 0.5535 |
 | 0.0585        | 48.0  | 6000 | 0.6786          | 0.5512 |
 | 0.0555        | 50.0  | 6250 | 0.6844          | 0.5516 |
+| 0.0681        | 52.0  | 6500 | 0.6603          | 0.5562 |
+| 0.0699        | 54.0  | 6750 | 0.6837          | 0.5565 |
+| 0.0641        | 56.0  | 7000 | 0.6792          | 0.5509 |
+| 0.0612        | 58.0  | 7250 | 0.6765          | 0.5508 |
+| 0.0593        | 60.0  | 7500 | 0.6780          | 0.5530 |
+| 0.0525        | 62.0  | 7750 | 0.6947          | 0.5460 |
+| 0.0491        | 64.0  | 8000 | 0.7007          | 0.5504 |
+| 0.0482        | 66.0  | 8250 | 0.7215          | 0.5572 |
+| 0.0478        | 68.0  | 8500 | 0.7178          | 0.5444 |
+| 0.0434        | 70.0  | 8750 | 0.7283          | 0.5465 |
+| 0.042         | 72.0  | 9000 | 0.7203          | 0.5462 |
+| 0.0402        | 74.0  | 9250 | 0.7268          | 0.5447 |
 
 
 ### Framework versions