whisper-darija-stage1
This model is a fine-tuned version of ychafiqui/whisper-small-darija on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9841
- Wer: 68.6860
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3707 | 16.6809 | 100 | 2.3146 | 69.3987 |
| 0.0683 | 33.3404 | 200 | 2.6466 | 67.5724 |
| 0.0202 | 50.0 | 300 | 2.8124 | 69.0869 |
| 0.0046 | 66.6809 | 400 | 2.9300 | 68.3296 |
| 0.0008 | 83.3404 | 500 | 2.9841 | 68.6860 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2