Whisper Tiny Id - NT
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5240
- Wer: 36.4901
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: Use 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5362 | 1.9305 | 1000 | 0.5487 | 38.4995 |
| 0.2847 | 3.8610 | 2000 | 0.5154 | 36.7087 |
| 0.1703 | 5.7915 | 3000 | 0.5183 | 36.3412 |
| 0.1217 | 7.7220 | 4000 | 0.5240 | 36.4901 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0