Whisper Small Pashto
This model is a fine-tuned version of openai/whisper-small on the Open ASR dataset. It achieves the following results on the evaluation set:
- Loss: 0.7846
- Wer: 34.4754
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0112 | 17.8571 | 1000 | 0.6265 | 38.1462 |
| 0.0023 | 35.7143 | 2000 | 0.7230 | 35.0260 |
| 0.0006 | 53.5714 | 3000 | 0.7555 | 34.7201 |
| 0.0001 | 71.4286 | 4000 | 0.7708 | 34.9342 |
| 0.0001 | 89.2857 | 5000 | 0.7846 | 34.4754 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3