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: 0.7159
- Rouge1: 51.0246
- Rouge2: 28.8904
- Rougel: 41.9694
- Rougelsum: 41.9864
- Gen Len: 57.62
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 |
|---|---|---|---|---|---|---|---|---|
| 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
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3