whisper-tiny-medical
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5555
- Wer: 0.3282
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4277 | 1.0 | 204 | 0.6119 | 0.2787 |
| 0.3418 | 2.0 | 408 | 0.5642 | 0.2541 |
| 0.2761 | 3.0 | 612 | 0.5533 | 0.3720 |
| 0.1849 | 4.0 | 816 | 0.5534 | 0.3361 |
| 0.1760 | 5.0 | 1020 | 0.5555 | 0.3282 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.5.1+cu121
- Datasets 4.8.3
- Tokenizers 0.22.2