Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Turbo ko
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the custom dataset. It achieves the following results on the evaluation set:
- Loss: 0.1062
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: 0.001
- train_batch_size: 64
- eval_batch_size: 256
- 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: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3114 | 0.5348 | 100 | 0.6054 |
| 0.1095 | 1.0695 | 200 | 0.3744 |
| 0.0973 | 1.6043 | 300 | 0.3110 |
| 0.0766 | 2.1390 | 400 | 0.2473 |
| 0.0628 | 2.6738 | 500 | 0.1919 |
| 0.0533 | 3.2086 | 600 | 0.1704 |
| 0.0462 | 3.7433 | 700 | 0.1590 |
| 0.0329 | 4.2781 | 800 | 0.1363 |
| 0.0282 | 4.8128 | 900 | 0.1258 |
| 0.0294 | 5.3476 | 1000 | 0.1062 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 0