update model card README.md

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6150
-- Wer: 20.4979
-- Cer: 8.9847
+- Loss: 0.7427
+- Wer: 19.3902
+- Cer: 8.7285
 
 ## Model description
 
@@ -37,10 +37,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
+- learning_rate: 1e-05
 - train_batch_size: 32
-- eval_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -51,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
-| 0.1041        | 0.2   | 1000 | 0.5133          | 22.6146 | 9.7131 |
-| 0.074         | 1.11  | 2000 | 0.5532          | 21.6166 | 9.4196 |
-| 0.0796        | 2.02  | 3000 | 0.6025          | 21.3314 | 9.2435 |
-| 0.0422        | 2.22  | 4000 | 0.6029          | 20.7392 | 9.0274 |
-| 0.0517        | 3.13  | 5000 | 0.6150          | 20.4979 | 8.9847 |
+| 0.0471        | 1.05  | 1000 | 0.5961          | 20.2895 | 8.9820 |
+| 0.0194        | 2.11  | 2000 | 1.0999          | 22.6146 | 9.7105 |
+| 0.002         | 4.02  | 3000 | 0.7289          | 20.2018 | 8.8379 |
+| 0.0006        | 5.07  | 4000 | 0.7791          | 19.3683 | 8.4376 |
+| 0.0003        | 6.13  | 5000 | 0.7427          | 19.3902 | 8.7285 |
 
 
 ### Framework versions