whisper-darija-v2
This model is a fine-tuned version of ilyaslbern7347/whisper-darija-final on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1471
- Wer: 7.8431
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: 4
- total_train_batch_size: 16
- 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: 25
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0969 | 3.5926 | 50 | 0.1945 | 11.1111 |
| 0.0329 | 7.1481 | 100 | 0.1680 | 8.4967 |
| 0.0037 | 10.7407 | 150 | 0.1405 | 6.5359 |
| 0.0002 | 14.2963 | 200 | 0.1471 | 7.8431 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2