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: 0.6119
- Rouge1: 44.2768
- Rouge2: 23.1307
- Rougel: 36.7378
- Rougelsum: 36.7159
- Gen Len: 72.18
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: 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 |
|---|---|---|---|---|---|---|---|---|
| 2.3982 | 1.0 | 959 | 2.0620 | 26.4298 | 5.9908 | 23.2899 | 23.3213 | 64.6 |
| 1.7265 | 2.0 | 1918 | 1.6701 | 27.8931 | 6.8526 | 24.1834 | 24.1954 | 65.1 |
| 1.4192 | 3.0 | 2877 | 1.3889 | 30.545 | 8.5986 | 26.1328 | 26.1093 | 63.72 |
| 1.215 | 4.0 | 3836 | 1.1685 | 32.7599 | 10.5476 | 27.2588 | 27.2407 | 66.01 |
| 1.0452 | 5.0 | 4795 | 0.9892 | 33.4751 | 11.1674 | 27.5111 | 27.4954 | 65.03 |
| 0.8959 | 6.0 | 5754 | 0.8506 | 35.995 | 13.1211 | 29.6986 | 29.745 | 67.8 |
| 0.7872 | 7.0 | 6713 | 0.7457 | 39.7262 | 16.9675 | 32.8461 | 32.8319 | 70.65 |
| 0.6891 | 8.0 | 7672 | 0.6733 | 41.6536 | 19.7787 | 34.6224 | 34.5889 | 67.49 |
| 0.6223 | 9.0 | 8631 | 0.6272 | 43.4958 | 21.9107 | 36.5012 | 36.4477 | 72.2 |
| 0.5763 | 10.0 | 9590 | 0.6119 | 44.2768 | 23.1307 | 36.7378 | 36.7159 | 72.18 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3