whisper-lora-640
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3484
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 50
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|---|---|---|---|---|---|
| 1.4182 | 0.5674 | 10 | 0.1771 | 1.3644 | 0.3574 |
| 1.3081 | 1.1135 | 20 | 0.1771 | 1.3655 | 0.3574 |
| 1.4107 | 1.6809 | 30 | 0.1771 | 1.3661 | 0.3574 |
| 1.4016 | 2.2837 | 40 | 0.1813 | 1.3622 | 0.3688 |
| 1.3979 | 2.7943 | 50 | 0.1820 | 1.3586 | 0.3688 |
| 1.4308 | 3.3972 | 60 | 1.3539 | ||
| 1.3849 | 3.9645 | 70 | 1.3514 | ||
| 1.2477 | 4.5106 | 80 | 1.3484 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.7.1+cu118
- Datasets 3.1.0
- Tokenizers 0.21.2
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Jeff13680/whisper-lora-640
Base model
openai/whisper-large-v3