Zolfa-raghadomar
This model is a fine-tuned version of tarteel-ai/whisper-base-ar-quran on the Zolfa Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0157
- Wer: 5.2632
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0155 | 2.8571 | 100 | 0.0156 | 5.2632 |
| 0.0037 | 5.7143 | 200 | 0.0199 | 5.2632 |
| 0.0011 | 8.5714 | 300 | 0.0175 | 5.2632 |
| 0.0006 | 11.4286 | 400 | 0.0123 | 5.2632 |
| 0.0003 | 14.2857 | 500 | 0.0187 | 5.2632 |
| 0.0001 | 17.1429 | 600 | 0.0126 | 5.2632 |
| 0.0001 | 20.0 | 700 | 0.0159 | 5.2632 |
| 0.0002 | 22.8571 | 800 | 0.0137 | 5.2632 |
| 0.0001 | 25.7143 | 900 | 0.0149 | 5.2632 |
| 0.0001 | 28.5714 | 1000 | 0.0157 | 5.2632 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1