Whisper Small for Hre - NT Viet
This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.9195
- Wer Ortho: 88.8889
- Wer: 88.8889
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0674 | 50.0 | 100 | 1.9195 | 88.8889 | 88.8889 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.1