Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-large-v3-turbo-med-pl-lora-r16-decoder-only-lr5e-05-ep3-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: 1.6611
- Model Preparation Time: 0.0094
- Wer: 14.1952
- Cer: 4.3217
- Content Wer: 8.0298
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 | Content Wer |
|---|---|---|---|---|---|---|---|
| 1.6854 | 1.0 | 1514 | 1.6789 | 0.0094 | 15.3443 | 4.6216 | 8.6227 |
| 1.673 | 2.0 | 3028 | 1.6657 | 0.0094 | 14.5163 | 4.3504 | 8.1569 |
| 1.6675 | 3.0 | 4542 | 1.6611 | 0.0094 | 14.1952 | 4.3217 | 8.0298 |
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
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AleksanderObuchowski/whisper-large-v3-turbo-med-pl-lora-r16-decoder-only-lr5e-05-ep3-whisper_fair", dtype="auto")