whisper-es-pr-pe-lora-unsloth-large-turbo-v10
This model is a fine-tuned version of unsloth/whisper-large-v3-turbo on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.0875
- Wer: 0.0472
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0745 | 0.3333 | 400 | 0.0888 | 0.0553 |
| 0.0511 | 1.0983 | 800 | 0.0874 | 0.0476 |
| 0.047 | 1.4317 | 1200 | 0.0875 | 0.0472 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1