metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: whisper-tiny-finetuned-gtzan-finetuned-gtzan
results: []
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: 0.7520
- 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: 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 |
|---|---|---|---|---|
| 0.2831 | 1.0 | 113 | 1.6496 | 0.74 |
| 0.6095 | 2.0 | 226 | 1.0397 | 0.77 |
| 0.0629 | 3.0 | 339 | 0.8188 | 0.86 |
| 0.0006 | 4.0 | 452 | 0.7378 | 0.88 |
| 0.0123 | 5.0 | 565 | 0.7285 | 0.9 |
| 0.0002 | 6.0 | 678 | 0.9172 | 0.86 |
| 0.0002 | 7.0 | 791 | 0.8244 | 0.89 |
| 0.0002 | 8.0 | 904 | 0.7630 | 0.9 |
| 0.169 | 9.0 | 1017 | 0.7572 | 0.89 |
| 0.0002 | 10.0 | 1130 | 0.7520 | 0.9 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3