whisper-large-v3-turbo-fa-c13-avs
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2687
- Wer: 27.9267
Model description
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 |
|---|---|---|---|---|
| 0.2167 | 0.4160 | 1000 | 0.4101 | 39.1360 |
| 0.1643 | 0.8319 | 2000 | 0.3560 | 34.6257 |
| 0.0874 | 1.2479 | 3000 | 0.3249 | 32.9962 |
| 0.0873 | 1.6639 | 4000 | 0.2836 | 29.3890 |
| 0.0421 | 2.0799 | 5000 | 0.2687 | 27.9267 |
Framework versions
- Transformers 4.52.1
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
Notes
- Amir Nezami safa
- Vahid Mahmodiyan
- Shahab Salehi