Whisper tiny Potuguese
This model is a fine-tuned version of openai/whisper-tiny on the Portuguese English dataset. It achieves the following results on the evaluation set:
- Loss: 0.2603
- Wer: 10.9972
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.25
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3428 | 0.5005 | 543 | 0.3082 | 14.6692 |
| 0.2665 | 1.0009 | 1086 | 0.2744 | 11.0345 |
| 0.1130 | 1.5014 | 1629 | 0.2649 | 10.4007 |
| 0.1215 | 2.0 | 2170 | 0.2603 | 10.9972 |
Framework versions
- Transformers 5.22.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3