nezamisafa/whisper-v3-turbo-persian-v1.0
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3078
- Wer: 29.9382
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: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1113 | 1.0152 | 2000 | 0.4020 | 38.7338 |
| 0.0554 | 2.0305 | 4000 | 0.3469 | 35.0827 |
| 0.0204 | 3.0457 | 6000 | 0.3078 | 29.9382 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1