Whisper Small vn - pbl4
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: 0.7314
- Wer: 27.8210
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 |
|---|---|---|---|---|
| 0.0252 | 5.7471 | 1000 | 0.6066 | 28.1171 |
| 0.0006 | 11.4943 | 2000 | 0.6882 | 27.6017 |
| 0.0003 | 17.2414 | 3000 | 0.7211 | 27.9088 |
| 0.0002 | 22.9885 | 4000 | 0.7314 | 27.8210 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.0
- Datasets 3.2.0
- Tokenizers 0.21.0