Whisper 50 Syllable - Albertus Pekerti
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0092
- Wer: 1.6693
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: 16
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.0226 | 0.2286 | 1000 | 0.0252 | 3.9549 |
| 0.0163 | 0.4572 | 2000 | 0.0153 | 2.3860 |
| 0.0107 | 0.6859 | 3000 | 0.0149 | 2.1993 |
| 0.0127 | 0.9145 | 4000 | 0.0115 | 1.9317 |
| 0.0071 | 1.1431 | 5000 | 0.0092 | 1.6693 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2