metadata
license: apache-2.0
base_model: openai/whisper-base.en
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: whispherMusic
results: []
whispherMusic
This model is a fine-tuned version of openai/whisper-base.en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1914
- Rouge1: 30.2379
- Rouge2: 8.3781
- Rougel: 25.6302
- Rougelsum: 25.6217
- Gen Len: 63.09
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
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 |
|---|---|---|---|---|---|---|---|---|
| 3.0989 | 1.0 | 959 | 2.7267 | 22.3544 | 3.7732 | 21.0972 | 21.1155 | 58.46 |
| 2.2959 | 2.0 | 1918 | 2.1774 | 23.3309 | 3.946 | 21.5505 | 21.497 | 61.0 |
| 1.8902 | 3.0 | 2877 | 1.7126 | 26.1869 | 5.372 | 23.7001 | 23.6849 | 61.0 |
| 1.5533 | 4.0 | 3836 | 1.3554 | 29.4291 | 7.42 | 25.1978 | 25.1515 | 62.55 |
| 1.2635 | 5.0 | 4795 | 1.1914 | 30.2379 | 8.3781 | 25.6302 | 25.6217 | 63.09 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3