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: 0.5171
- Accuracy: 0.91
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 |
|---|---|---|---|---|
| 1.4157 | 1.0 | 113 | 1.1896 | 0.67 |
| 0.7796 | 2.0 | 226 | 0.7259 | 0.75 |
| 0.3832 | 3.0 | 339 | 0.5214 | 0.83 |
| 0.3417 | 4.0 | 452 | 0.4182 | 0.86 |
| 0.2349 | 5.0 | 565 | 0.9444 | 0.73 |
| 0.0056 | 6.0 | 678 | 0.4377 | 0.91 |
| 0.1083 | 7.0 | 791 | 0.5190 | 0.9 |
| 0.0022 | 8.0 | 904 | 0.5642 | 0.89 |
| 0.1358 | 9.0 | 1017 | 0.5125 | 0.91 |
| 0.0016 | 10.0 | 1130 | 0.5171 | 0.91 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3