update model card README.md

README.md

@@ -12,10 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-timit-demo-colab
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4652
-- Wer: 0.3380
+This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn) on the None dataset.
 
 ## Model description
 
@@ -34,27 +31,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.01
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 30
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.5427        | 4.0   | 500  | 1.7699          | 1.0055 |
-| 0.6664        | 8.0   | 1000 | 0.4907          | 0.4596 |
-| 0.2329        | 12.0  | 1500 | 0.4678          | 0.3875 |
-| 0.1341        | 16.0  | 2000 | 0.4284          | 0.3716 |
-| 0.0895        | 20.0  | 2500 | 0.4776          | 0.3565 |
-| 0.0633        | 24.0  | 3000 | 0.4691          | 0.3451 |
-| 0.0476        | 28.0  | 3500 | 0.4652          | 0.3380 |
 
 
 ### Framework versions