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: 0.1079
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 |
|---|---|---|---|
| 0.3137 | 0.5263 | 100 | 0.6400 |
| 0.1177 | 1.0526 | 200 | 0.4196 |
| 0.1026 | 1.5789 | 300 | 0.3100 |
| 0.08 | 2.1053 | 400 | 0.2444 |
| 0.0603 | 2.6316 | 500 | 0.2066 |
| 0.0605 | 3.1579 | 600 | 0.1611 |
| 0.0437 | 3.6842 | 700 | 0.1581 |
| 0.0368 | 4.2105 | 800 | 0.1296 |
| 0.0329 | 4.7368 | 900 | 0.1147 |
| 0.0254 | 5.2632 | 1000 | 0.1079 |
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
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.