Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-turbo-med-pl-lora-r128-enc-dec-lr2e-04-ep5-whisper_bigos10k_fair
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: 1.6146
- Model Preparation Time: 0.02
- Wer: 12.7365
- Cer: 4.4142
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: 0.0002
- 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: 5
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
|---|---|---|---|---|---|---|
| 1.6514 | 1.0 | 1827 | 1.6449 | 0.02 | 13.4480 | 4.2912 |
| 1.6125 | 2.0 | 3654 | 1.6276 | 0.02 | 13.2930 | 4.7269 |
| 1.5725 | 3.0 | 5481 | 1.6170 | 0.02 | 13.3694 | 4.9395 |
| 1.5464 | 4.0 | 7308 | 1.6168 | 0.02 | 12.8406 | 4.4764 |
| 1.5212 | 5.0 | 9135 | 1.6146 | 0.02 | 12.7365 | 4.4142 |
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
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support