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 - GL dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7654
-- Wer: 0.5186
+- Loss: 0.1525
+- Wer: 0.1542
 
 ## Model description
 
@@ -46,16 +46,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 400
-- num_epochs: 10.0
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.0269        | 3.48  | 400  | 2.9771          | 1.0    |
-| 2.7902        | 6.96  | 800  | 2.4357          | 0.9989 |
+| 3.0067        | 4.35  | 500  | 2.9632          | 1.0    |
+| 1.4939        | 8.7   | 1000 | 0.5005          | 0.4157 |
+| 0.9982        | 13.04 | 1500 | 0.1967          | 0.1857 |
+| 0.8726        | 17.39 | 2000 | 0.1587          | 0.1564 |
 
 
 ### Framework versions