whisper-small-en-VB
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6560
- Wer Ortho: 11.0424
- Wer: 7.8659
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: 16
- seed: 42
- optimizer: Use 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: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0373 | 3.9683 | 250 | 0.5479 | 11.1283 | 8.2365 |
| 0.001 | 7.9365 | 500 | 0.6287 | 11.0939 | 7.6638 |
| 0.0003 | 11.9048 | 750 | 0.6504 | 11.0424 | 7.8659 |
| 0.0003 | 15.8730 | 1000 | 0.6560 | 11.0424 | 7.8659 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.0