Whisper Small-nan
This model is a fine-tuned version of openai/whisper-small on the Common Voice 15, 16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7181
- Cer: 29.5966
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 | Cer |
|---|---|---|---|---|
| 0.2916 | 1.5552 | 1000 | 0.6323 | 31.6827 |
| 0.0274 | 3.1104 | 2000 | 0.6579 | 29.3462 |
| 0.0063 | 4.6656 | 3000 | 0.6931 | 29.0304 |
| 0.0018 | 6.2208 | 4000 | 0.7181 | 29.5966 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0