Whisper Tiny Japanese Combine 4k - Chee Li
This model is a fine-tuned version of openai/whisper-tiny on the Meta JSON Japanese Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.6167
- Wer: 374.3034
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 |
|---|---|---|---|---|
| 2.5437 | 3.8911 | 1000 | 2.4311 | 494.4272 |
| 2.0028 | 7.7821 | 2000 | 2.0321 | 427.0898 |
| 1.5918 | 11.6732 | 3000 | 1.7293 | 395.9752 |
| 1.4102 | 15.5642 | 4000 | 1.6167 | 374.3034 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.1
- Downloads last month
- 13
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for CheeLi03/whisper-tiny-ja-puct-combine-4k
Base model
openai/whisper-tiny