metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: whisper-tiny-finetuned-gtzan
results: []
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: 0.4342
- 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 1.7087 | 0.99 | 56 | 1.6682 | 0.53 |
| 1.0139 | 2.0 | 113 | 1.1272 | 0.64 |
| 0.8057 | 2.99 | 169 | 0.7579 | 0.79 |
| 0.393 | 4.0 | 226 | 0.5791 | 0.86 |
| 0.3414 | 4.99 | 282 | 0.5055 | 0.86 |
| 0.1083 | 6.0 | 339 | 0.4109 | 0.9 |
| 0.0783 | 6.99 | 395 | 0.4297 | 0.87 |
| 0.0998 | 8.0 | 452 | 0.4627 | 0.87 |
| 0.0119 | 8.99 | 508 | 0.4410 | 0.87 |
| 0.0095 | 9.91 | 560 | 0.4342 | 0.87 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3