Whisper Tiny Portuguese
This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_13_0 pt dataset. It achieves the following results on the evaluation set:
- Loss: 0.5191
- Wer: 28.9653
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-06
- train_batch_size: 256
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.4763 | 14.08 | 1000 | 0.5686 | 31.3114 |
| 0.3784 | 28.17 | 2000 | 0.5350 | 30.0693 |
| 0.3286 | 42.25 | 3000 | 0.5239 | 29.2413 |
| 0.3073 | 56.34 | 4000 | 0.5200 | 29.4138 |
| 0.2971 | 70.42 | 5000 | 0.5191 | 28.9653 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.15.1