update model card README.md

README.md

@@ -20,8 +20,8 @@ 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 MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5885
-- Wer: 0.5899
+- Loss: 0.5620
+- Wer: 0.5651
 
 ## Model description
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 750
+- lr_scheduler_warmup_steps: 2000
 - num_epochs: 100.0
 - mixed_precision_training: Native AMP
 
@@ -56,13 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 7.5798        | 13.64 | 300  | 3.4349          | 1.0    |
-| 3.1252        | 27.27 | 600  | 3.0706          | 1.0    |
-| 2.2546        | 40.91 | 900  | 0.8427          | 0.7763 |
-| 0.7564        | 54.55 | 1200 | 0.6129          | 0.6376 |
-| 0.5239        | 68.18 | 1500 | 0.5769          | 0.6037 |
-| 0.438         | 81.82 | 1800 | 0.5938          | 0.5915 |
-| 0.3945        | 95.45 | 2100 | 0.5869          | 0.5861 |
+| 9.6445        | 13.64 | 300  | 4.3963          | 1.0    |
+| 3.6459        | 27.27 | 600  | 3.2267          | 1.0    |
+| 3.0978        | 40.91 | 900  | 3.0927          | 1.0    |
+| 2.8357        | 54.55 | 1200 | 2.1462          | 1.0029 |
+| 1.2723        | 68.18 | 1500 | 0.6747          | 0.6996 |
+| 0.6528        | 81.82 | 1800 | 0.5928          | 0.6422 |
+| 0.4905        | 95.45 | 2100 | 0.5587          | 0.5681 |
 
 
 ### Framework versions