whisper-medium-v3
This model is a fine-tuned version of GogetaBlueMUI/whisper-medium-ur-v2-resumed on the jalandhary_asr dataset. It achieves the following results on the evaluation set:
- Loss: 0.1647
- Wer: 22.1497
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: 8
- eval_batch_size: 8
- 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: 110
- training_steps: 1050
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1884 | 0.3401 | 350 | 0.1993 | 24.2099 |
| 0.187 | 0.6803 | 700 | 0.1758 | 23.0122 |
| 0.1198 | 1.0204 | 1050 | 0.1647 | 22.1497 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.4.1
- Tokenizers 0.21.0