Whisper tiny Japenese
This model is a fine-tuned version of openai/whisper-tiny on the Japanese English dataset. It achieves the following results on the evaluation set:
- Loss: 0.4644
- Wer: 20.2381
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: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.25
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3531 | 0.5 | 402 | 0.5442 | 24.1698 |
| 0.4043 | 1.0 | 804 | 0.4825 | 21.3659 |
| 0.1580 | 1.5 | 1206 | 0.4743 | 20.9117 |
| 0.1118 | 2.0 | 1608 | 0.4644 | 20.2381 |
Framework versions
- Transformers 5.22.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3