Whisper large v2 aphasia - Nuwan
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: 0.5667
- Wer Ortho: 32.9754
- Wer: 32.0758
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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.7049 | 0.0472 | 200 | 0.7395 | 41.4881 | 40.2489 |
| 0.606 | 0.0943 | 400 | 0.6397 | 33.2373 | 32.4595 |
| 0.5243 | 0.1415 | 600 | 0.6069 | 36.2108 | 35.3199 |
| 0.5454 | 0.1886 | 800 | 0.5835 | 34.2110 | 33.4666 |
| 0.5021 | 0.2358 | 1000 | 0.5667 | 32.9754 | 32.0758 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1