whisper_large_v3_phase4
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7061
- Cer: 16.9310
- Wer: 28.4880
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 0.0294 | 1.0 | 1056 | 0.7207 | 17.4849 | 29.4378 |
| 0.0421 | 2.0 | 2112 | 0.7178 | 17.8911 | 30.1385 |
| 0.0362 | 3.0 | 3168 | 0.7091 | 17.5893 | 29.4916 |
| 0.029 | 4.0 | 4224 | 0.7099 | 17.1988 | 28.8085 |
| 0.0228 | 5.0 | 5280 | 0.7061 | 16.9310 | 28.4880 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.21.4
- Downloads last month
- 21