whisper_large_v3_phase4_2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7026
- Cer: 16.6966
- Wer: 28.1219
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: 5e-06
- 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 |
|---|---|---|---|---|---|
| 0.0235 | 1.0 | 1056 | 0.7088 | 16.8665 | 28.2810 |
| 0.0269 | 2.0 | 2112 | 0.7037 | 17.1738 | 28.8062 |
| 0.0259 | 3.0 | 3168 | 0.7019 | 17.0483 | 28.6600 |
| 0.023 | 4.0 | 4224 | 0.7056 | 16.8582 | 28.3430 |
| 0.0205 | 5.0 | 5280 | 0.7026 | 16.6966 | 28.1219 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.21.4
- Downloads last month
- 2