Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-turbo-med-pl-lora-decoder-only
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7147
- Model Preparation Time: 0.0121
- Wer: 19.9336
- Cer: 8.4978
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: 5e-05
- train_batch_size: 16
- 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_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
|---|---|---|---|---|---|---|
| 1.7811 | 1.0 | 2227 | 1.7378 | 0.0121 | 21.4499 | 9.5474 |
| 1.7453 | 2.0 | 4454 | 1.7207 | 0.0121 | 20.7634 | 9.2218 |
| 1.7313 | 3.0 | 6681 | 1.7147 | 0.0121 | 19.9336 | 8.4978 |
Framework versions
- PEFT 0.18.1
- Transformers 4.57.6
- Pytorch 2.8.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support