whisper-base-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-base on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5877
- Accuracy: 0.88
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1813 | 1.0 | 113 | 1.1224 | 0.62 |
| 0.6839 | 2.0 | 226 | 0.7112 | 0.78 |
| 0.4336 | 3.0 | 339 | 0.6312 | 0.8 |
| 0.1472 | 4.0 | 452 | 0.5366 | 0.83 |
| 0.1193 | 5.0 | 565 | 0.7973 | 0.8 |
| 0.008 | 6.0 | 678 | 0.5044 | 0.87 |
| 0.1485 | 7.0 | 791 | 0.7054 | 0.86 |
| 0.0155 | 8.0 | 904 | 0.6145 | 0.87 |
| 0.1364 | 9.0 | 1017 | 0.6034 | 0.88 |
| 0.0017 | 10.0 | 1130 | 0.5877 | 0.88 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3