whisper-tiny-finetuned-gtzan-finetuned-gtzan
This model is a fine-tuned version of ditwoo/whisper-tiny-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6948
- Accuracy: 0.87
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.99,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0665 | 1.0 | 15 | 0.5896 | 0.88 |
| 0.0432 | 2.0 | 30 | 0.9979 | 0.8 |
| 0.0509 | 3.0 | 45 | 1.1608 | 0.8 |
| 0.0645 | 4.0 | 60 | 0.5176 | 0.91 |
| 0.0613 | 5.0 | 75 | 0.8058 | 0.86 |
| 0.0205 | 6.0 | 90 | 0.7243 | 0.85 |
| 0.0067 | 6.5614 | 98 | 0.6948 | 0.87 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0