Whisper large v2 aphasia - 2000
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5148
- Wer Ortho: 27.2934
- Wer: 26.6452
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.62 | 0.0943 | 400 | 0.6506 | 35.1514 | 34.0594 |
| 0.5504 | 0.1886 | 800 | 0.5892 | 33.9968 | 33.1434 |
| 0.4954 | 0.2830 | 1200 | 0.5583 | 28.8726 | 28.1999 |
| 0.562 | 0.3773 | 1600 | 0.5348 | 28.7116 | 28.1011 |
| 0.479 | 0.4716 | 2000 | 0.5148 | 27.2934 | 26.6452 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1