Whisper Base Portuguese
This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_13_0 pt dataset. It achieves the following results on the evaluation set:
- Loss: 0.3815
- Wer: 19.2899
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: 128
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.3261 | 7.04 | 1000 | 0.4097 | 20.6766 |
| 0.2632 | 14.08 | 2000 | 0.3884 | 19.5101 |
| 0.2241 | 21.13 | 3000 | 0.3827 | 19.4690 |
| 0.2048 | 28.17 | 4000 | 0.3815 | 19.2899 |
| 0.1956 | 35.21 | 5000 | 0.3815 | 19.4033 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.15.1