Whisper Small - Egyptian Arabic
This model is a fine-tuned version of openai/whisper-small on the Egyptian Arabic Speech Recognition dataset. It achieves the following results on the evaluation set:
- Loss: 0.9560
- Wer: 41.6677
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: Use OptimizerNames.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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0518 | 7.6336 | 1000 | 0.7113 | 42.9166 |
| 0.004 | 15.2672 | 2000 | 0.8712 | 41.2157 |
| 0.001 | 22.9008 | 3000 | 0.9327 | 42.0245 |
| 0.0006 | 30.5344 | 4000 | 0.9560 | 41.6677 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1.post303
- Datasets 3.1.0
- Tokenizers 0.20.3