Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-turbo-med-pl-lora-r64-enc-dec-lr2e-04-ep7-whisper_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: 1.6259
- Model Preparation Time: 0.0224
- Wer: 13.2654
- Cer: 4.3688
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: 7
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer | Cer |
|---|---|---|---|---|---|---|
| 1.6487 | 1.0 | 1514 | 1.6520 | 0.0224 | 14.1956 | 4.9002 |
| 1.6136 | 2.0 | 3028 | 1.6329 | 0.0224 | 15.4911 | 7.5859 |
| 1.591 | 3.0 | 4542 | 1.6263 | 0.0224 | 14.7754 | 5.5331 |
| 1.573 | 4.0 | 6056 | 1.6255 | 0.0224 | 13.8919 | 4.8834 |
| 1.5422 | 5.0 | 7570 | 1.6231 | 0.0224 | 13.0848 | 4.5169 |
| 1.5296 | 6.0 | 9084 | 1.6248 | 0.0224 | 12.9383 | 4.2629 |
| 1.5225 | 7.0 | 10598 | 1.6259 | 0.0224 | 13.2654 | 4.3688 |
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