Whisper Small
This model is a fine-tuned version of openai/whisper-small on the Quechua Bible dataset. It achieves the following results on the evaluation set:
- Loss: 0.0002
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0765 | 12.5 | 500 | 0.0630 |
| 0.0413 | 25.0 | 1000 | 0.0294 |
| 0.0173 | 37.5 | 1500 | 0.0191 |
| 0.0161 | 50.0 | 2000 | 0.0116 |
| 0.0078 | 62.5 | 2500 | 0.0046 |
| 0.0071 | 75.0 | 3000 | 0.0039 |
| 0.0019 | 87.5 | 3500 | 0.0015 |
| 0.001 | 100.0 | 4000 | 0.0002 |
| 0.0007 | 112.5 | 4500 | 0.0002 |
| 0.0 | 125.0 | 5000 | 0.0002 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2