whisper-small-ptbr-mupe-final3
This model is a fine-tuned version of lejonck/whisper-small-ptbr-mupe-final1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2697
- Wer: 0.3986
- Cer: 0.6141
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: 2
- seed: 42
- 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: 100
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.326 | 1.0 | 375 | 0.9581 | 0.4462 | 0.6216 |
| 0.1473 | 2.0 | 750 | 1.0390 | 0.4458 | 0.6259 |
| 0.0431 | 3.0 | 1125 | 1.0292 | 0.4306 | 0.6188 |
| 0.0197 | 4.0 | 1500 | 1.0942 | 0.4406 | 0.6191 |
| 0.0199 | 5.0 | 1875 | 1.1880 | 0.4438 | 0.6196 |
| 0.0021 | 6.0 | 2250 | 1.1897 | 0.4066 | 0.6139 |
| 0.0012 | 7.0 | 2625 | 1.2027 | 0.4182 | 0.6149 |
| 0.0007 | 8.0 | 3000 | 1.2243 | 0.4042 | 0.6122 |
| 0.0006 | 9.0 | 3375 | 1.2533 | 0.4194 | 0.6168 |
| 0.0004 | 10.0 | 3750 | 1.2620 | 0.3998 | 0.6141 |
| 0.0006 | 11.0 | 4125 | 1.2550 | 0.4126 | 0.6145 |
| 0.0004 | 12.0 | 4500 | 1.2486 | 0.3966 | 0.6115 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support