Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-turbo-med-pl-lora-r64-enc-dec-lr1e-04-ep10-whisper_bigos_all_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: 1.6294
- Model Preparation Time: 0.0195
- Wer: 13.1358
- Cer: 4.4202
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: 0.00015
- 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: 10
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
|---|---|---|---|---|---|---|
| 1.6622 | 1.0 | 1827 | 1.6592 | 0.0195 | 14.3273 | 4.6485 |
| 1.6308 | 2.0 | 3654 | 1.6327 | 0.0195 | 15.6547 | 5.9427 |
| 1.5969 | 3.0 | 5481 | 1.6261 | 0.0195 | 13.7836 | 4.9204 |
| 1.5804 | 4.0 | 7308 | 1.6246 | 0.0195 | 15.3276 | 6.4441 |
| 1.5597 | 5.0 | 9135 | 1.6237 | 0.0195 | 13.7538 | 5.1828 |
| 1.5464 | 6.0 | 10962 | 1.6223 | 0.0195 | 14.1510 | 5.2661 |
| 1.5367 | 7.0 | 12789 | 1.6246 | 0.0195 | 12.9595 | 4.2609 |
| 1.526 | 8.0 | 14616 | 1.6267 | 0.0195 | 13.5563 | 4.8519 |
| 1.5157 | 9.0 | 16443 | 1.6278 | 0.0195 | 13.2717 | 4.6086 |
| 1.5113 | 10.0 | 18270 | 1.6294 | 0.0195 | 13.1358 | 4.4202 |
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
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support