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-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7910
-- Wer: 31.4005
-- Cer: 9.9570
+- Loss: 0.5835
+- Wer: 24.8548
+- Cer: 8.2429
 
 ## Model description
 
@@ -38,13 +38,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 1
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 45000
+- training_steps: 35000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -86,16 +86,16 @@ The following hyperparameters were used during training:
 | 0.4863        | 35.99 | 33000 | 7.2441  | 0.5003          | 23.0542 |
 | 0.5007        | 37.08 | 34000 | 7.1545  | 0.4948          | 22.9234 |
 | 0.4519        | 38.17 | 35000 | 7.1257  | 0.4922          | 22.8248 |
-| 0.3674        | 39.26 | 36000 | 0.4754  | 22.6642         | 7.0104  |
-| 0.3481        | 40.35 | 37000 | 0.4679  | 22.6314         | 7.0311  |
-| 0.2992        | 41.44 | 38000 | 0.4622  | 22.2595         | 6.9465  |
-| 0.2505        | 42.53 | 39000 | 0.4641  | 22.1937         | 6.9198  |
-| 0.2477        | 43.62 | 40000 | 0.4678  | 22.8279         | 7.2008  |
-| 0.1994        | 44.71 | 41000 | 0.4689  | 22.3808         | 7.1179  |
-| 0.1865        | 45.8  | 42000 | 0.4717  | 22.5664         | 7.1351  |
-| 0.2307        | 46.89 | 43000 | 0.4754  | 22.3722         | 7.1364  |
-| 0.1705        | 47.98 | 44000 | 0.4759  | 22.3863         | 7.0830  |
-| 0.2007        | 49.07 | 45000 | 0.4767  | 22.4849         | 7.1187  |
+| 0.3674        | 39.26 | 36000 | 7.0104  | 0.4754          | 22.6642 |
+| 0.3481        | 40.35 | 37000 | 7.0311  | 0.4679          | 22.6314 |
+| 0.2992        | 41.44 | 38000 | 6.9465  | 0.4622          | 22.2595 |
+| 0.2505        | 42.53 | 39000 | 6.9198  | 0.4641          | 22.1937 |
+| 0.2477        | 43.62 | 40000 | 7.2008  | 0.4678          | 22.8279 |
+| 0.1994        | 44.71 | 41000 | 7.1179  | 0.4689          | 22.3808 |
+| 0.1865        | 45.8  | 42000 | 7.1351  | 0.4717          | 22.5664 |
+| 0.2307        | 46.89 | 43000 | 7.1364  | 0.4754          | 22.3722 |
+| 0.1705        | 47.98 | 44000 | 7.0830  | 0.4759          | 22.3863 |
+| 0.2007        | 49.07 | 45000 | 7.1187  | 0.4767          | 22.4849 |
 
 
 ### Framework versions