nacielo
/

whispherMusic

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7159
-- Rouge1: 51.0246
-- Rouge2: 28.8904
-- Rougel: 41.9694
-- Rougelsum: 41.9864
-- Gen Len: 57.62
 ## Model description
@@ -41,23 +41,28 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 2.3604        | 1.0   | 1361 | 1.8562          | 29.3488 | 8.9477  | 21.7546 | 21.8458   | 49.94   |
-| 1.8249        | 2.0   | 2722 | 1.4736          | 35.8525 | 12.9644 | 26.8468 | 26.8883   | 53.59   |
-| 1.4928        | 3.0   | 4083 | 1.1557          | 36.0664 | 11.6796 | 26.6999 | 26.7209   | 65.05   |
-| 1.149         | 4.0   | 5444 | 0.8567          | 45.1488 | 21.9847 | 35.4935 | 35.6169   | 56.51   |
-| 0.862         | 5.0   | 6805 | 0.7159          | 51.0246 | 28.8904 | 41.9694 | 41.9864   | 57.62   |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4596
+- Rouge1: 67.0305
+- Rouge2: 49.4145
+- Rougel: 59.4632
+- Rougelsum: 59.5132
+- Gen Len: 47.98
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.5281        | 1.0   | 983  | 1.7656          | 47.2738 | 19.609  | 35.166  | 35.1418   | 39.81   |
+| 1.8844        | 2.0   | 1966 | 1.4416          | 48.4369 | 22.034  | 36.3312 | 36.3541   | 41.88   |
+| 1.6071        | 3.0   | 2949 | 1.2060          | 49.7668 | 24.7504 | 38.8626 | 38.8523   | 37.8    |
+| 1.3867        | 4.0   | 3932 | 1.0056          | 52.8821 | 28.115  | 40.5389 | 40.5263   | 44.19   |
+| 1.1964        | 5.0   | 4915 | 0.8299          | 56.3235 | 32.1936 | 44.4629 | 44.3334   | 44.24   |
+| 1.0301        | 6.0   | 5898 | 0.6930          | 59.6505 | 36.3548 | 48.4558 | 48.3634   | 44.14   |
+| 0.904         | 7.0   | 6881 | 0.5916          | 61.3377 | 40.3586 | 50.8339 | 50.7188   | 46.15   |
+| 0.7985        | 8.0   | 7864 | 0.5157          | 64.7817 | 45.3792 | 56.0262 | 55.9178   | 47.7    |
+| 0.7125        | 9.0   | 8847 | 0.4722          | 66.0546 | 47.0456 | 57.422  | 57.37     | 48.35   |
+| 0.6514        | 10.0  | 9830 | 0.4596          | 67.0305 | 49.4145 | 59.4632 | 59.5132   | 47.98   |
 ### Framework versions