whisper-small-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-small on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4130
- Accuracy: 0.92
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- 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 |
|---|---|---|---|---|
| 1.3174 | 1.0 | 45 | 1.1768 | 0.61 |
| 0.687 | 2.0 | 90 | 0.7042 | 0.8 |
| 0.4524 | 3.0 | 135 | 0.4748 | 0.85 |
| 0.197 | 4.0 | 180 | 0.4230 | 0.89 |
| 0.2199 | 5.0 | 225 | 0.4980 | 0.88 |
| 0.113 | 6.0 | 270 | 0.3381 | 0.91 |
| 0.0054 | 7.0 | 315 | 0.3697 | 0.92 |
| 0.004 | 8.0 | 360 | 0.2930 | 0.94 |
| 0.0632 | 9.0 | 405 | 0.4574 | 0.92 |
| 0.0029 | 10.0 | 450 | 0.4130 | 0.92 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.