whisper-large-v2-medical-6
This model is a fine-tuned version of openai/whisper-large-v2 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1435
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-06
- train_batch_size: 64
- eval_batch_size: 64
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.26 | 20 | 0.6876 |
| 1.0862 | 0.51 | 40 | 0.4528 |
| 0.4702 | 0.77 | 60 | 0.3280 |
| 0.311 | 1.03 | 80 | 0.2105 |
| 0.145 | 1.28 | 100 | 0.1609 |
| 0.145 | 1.54 | 120 | 0.1526 |
| 0.1185 | 1.79 | 140 | 0.1483 |
| 0.1195 | 2.05 | 160 | 0.1449 |
| 0.092 | 2.31 | 180 | 0.1449 |
| 0.0829 | 2.56 | 200 | 0.1441 |
| 0.0829 | 2.82 | 220 | 0.1435 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.4.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2