Whisper Small zhIII_v2
This model is a fine-tuned version of openai/whisper-small on the sample dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Cer: 0.0
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: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.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: 5
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0076 | 2.7778 | 100 | 0.0015 | 30.9760 |
| 0.0001 | 5.5556 | 200 | 0.0001 | 0.0 |
| 0.0001 | 8.3333 | 300 | 0.0001 | 0.0 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0