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-ep7-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: 1.6234
- Model Preparation Time: 0.0193
- Wer: 12.7323
- Cer: 4.1336
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: 7
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
|---|---|---|---|---|---|---|
| 1.6566 | 1.0 | 1827 | 1.6525 | 0.0193 | 14.1404 | 4.7709 |
| 1.6252 | 2.0 | 3654 | 1.6308 | 0.0193 | 15.4274 | 5.7174 |
| 1.5922 | 3.0 | 5481 | 1.6232 | 0.0193 | 13.0020 | 4.2626 |
| 1.5749 | 4.0 | 7308 | 1.6244 | 0.0193 | 13.2548 | 4.6086 |
| 1.5544 | 5.0 | 9135 | 1.6202 | 0.0193 | 13.1953 | 4.5530 |
| 1.5415 | 6.0 | 10962 | 1.6213 | 0.0193 | 13.1146 | 4.4049 |
| 1.5334 | 7.0 | 12789 | 1.6234 | 0.0193 | 12.7323 | 4.1336 |
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