whisper-medium-aug-05-june
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0721
- Wer: 78.5554
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1867 | 1.0 | 2847 | 0.0867 | 78.8824 |
| 0.0689 | 2.0 | 5694 | 0.0720 | 75.8348 |
| 0.0485 | 3.0 | 8541 | 0.0706 | 77.7656 |
| 0.0362 | 4.0 | 11388 | 0.0690 | 77.5133 |
| 0.0274 | 5.0 | 14235 | 0.0721 | 78.5554 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1