update model card README.md

README.md

@@ -11,15 +11,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-en-in
 
-This model is a fine-tuned version of [beinghorizontal/wav2vec2-base-en-in](https://huggingface.co/beinghorizontal/wav2vec2-base-en-in) on the None dataset.
+This model is a fine-tuned version of [beinghorizontal/wav2vec2-base-en-in](https://huggingface.co/beinghorizontal/wav2vec2-base-en-in) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4400
-- eval_wer: 0.2424
-- eval_runtime: 28.5705
-- eval_samples_per_second: 8.365
-- eval_steps_per_second: 1.05
-- epoch: 27.78
-- step: 2500
+- Loss: 3.0056
+- Wer: 0.9997
 
 ## Model description
 
@@ -45,9 +40,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 100
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 29.5423       | 0.63  | 200  | 3.1266          | 0.9997 |
+| 3.1063        | 1.26  | 400  | 3.0490          | 0.9997 |
+| 3.0009        | 1.89  | 600  | 3.0056          | 0.9997 |
+
+
 ### Framework versions
 
 - Transformers 4.17.0