deepfake-audio-detector-v8
This model is a fine-tuned version of Heem2/Deepfake-audio-detection on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6630
- Accuracy: 0.6005
- Precision: 0.5741
- Recall: 0.7784
- F1: 0.6608
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 194 | 0.6786 | 0.5477 | 0.5256 | 0.9794 | 0.6841 |
| No log | 2.0 | 388 | 0.6643 | 0.6018 | 0.5714 | 0.8144 | 0.6716 |
| 0.7328 | 3.0 | 582 | 0.6601 | 0.6005 | 0.5741 | 0.7784 | 0.6608 |
| 0.7328 | 4.0 | 776 | 0.6683 | 0.6031 | 0.5730 | 0.8093 | 0.6709 |
| 0.7328 | 5.0 | 970 | 0.6630 | 0.6005 | 0.5741 | 0.7784 | 0.6608 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1