update model card README.md

README.md

@@ -4,6 +4,8 @@ tags:
 - generated_from_trainer
 datasets:
 - superb
+metrics:
+- accuracy
 model-index:
 - name: wav2vec2-base-finetuned-ks
   results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-base-finetuned-ks
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0894
+- Accuracy: 0.9828
 
 ## Model description
 
@@ -44,6 +49,17 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch | Step | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| 0.5003        | 1.0   | 399  | 0.9643   | 0.4284          |
+| 0.1868        | 2.0   | 798  | 0.9748   | 0.1628          |
+| 0.1413        | 3.0   | 1197 | 0.9796   | 0.1128          |
+| 0.0965        | 4.0   | 1596 | 0.0950   | 0.9826          |
+| 0.0915        | 5.0   | 1995 | 0.0894   | 0.9828          |
+
+
 ### Framework versions
 
 - Transformers 4.11.3