update model card README.md

README.md

@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0215
-- Wer: 0.9819
+- Loss: 3.0755
+- Wer: 1.0
 
 ## Model description
 
@@ -40,22 +40,19 @@ 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: 1000
-- num_epochs: 30
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.7978        | 3.45  | 500  | 3.0688          | 0.9819 |
-| 3.1832        | 6.9   | 1000 | 3.0315          | 0.9819 |
-| 3.1158        | 10.34 | 1500 | 3.0514          | 0.9819 |
-| 3.0776        | 13.79 | 2000 | 2.9971          | 0.9819 |
-| 3.0614        | 17.24 | 2500 | 3.0837          | 0.9819 |
-| 3.0724        | 20.69 | 3000 | 3.0462          | 0.9819 |
-| 3.0499        | 24.14 | 3500 | 3.0444          | 0.9819 |
-| 3.0592        | 27.59 | 4000 | 3.0215          | 0.9819 |
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| 8.0894        | 0.34  | 50   | 3.8065          | 1.0 |
+| 3.2971        | 0.69  | 100  | 3.0704          | 1.0 |
+| 3.1262        | 1.03  | 150  | 3.0153          | 1.0 |
+| 2.9925        | 1.38  | 200  | 3.0094          | 1.0 |
+| 3.2159        | 1.72  | 250  | 3.0755          | 1.0 |
 
 
 ### Framework versions