whisper-tiny-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-tiny on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4981
- Accuracy: 0.9
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: 32
- eval_batch_size: 32
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.1058 | 1.0 | 29 | 1.8465 | 0.42 |
1.3479 | 2.0 | 58 | 1.1915 | 0.66 |
0.7793 | 3.0 | 87 | 0.8178 | 0.81 |
0.5603 | 4.0 | 116 | 0.7727 | 0.78 |
0.404 | 5.0 | 145 | 0.6454 | 0.82 |
0.3251 | 6.0 | 174 | 0.5526 | 0.86 |
0.3089 | 7.0 | 203 | 0.5551 | 0.86 |
0.1296 | 8.0 | 232 | 0.5292 | 0.86 |
0.0966 | 9.0 | 261 | 0.5025 | 0.86 |
0.0761 | 10.0 | 290 | 0.4981 | 0.9 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0a0+81ea7a4
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 47