whisper-small-arbyeg_on
This model is a fine-tuned version of EYEDOL/whisper-small-arbyeg on the arabic_mozilla_dataset_clean dataset. It achieves the following results on the evaluation set:
- Loss: 0.2651
- Wer: 46.8761
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: 32
- 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: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9316 | 0.7205 | 1000 | 0.3003 | 48.2201 |
| 0.4708 | 1.4409 | 2000 | 0.2651 | 46.8761 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.9.0+cu126
- Datasets 4.6.1
- Tokenizers 0.22.2