VIT-ASVspoof5-MFCC-Synthetic-Voice-Detection
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.8475
- Accuracy: 0.6870
- F1: 0.7634
- Precision: 0.9260
- Recall: 0.6494
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0335 | 1.0 | 22795 | 1.1422 | 0.7655 | 0.8411 | 0.8892 | 0.7979 |
| 0.0104 | 2.0 | 45590 | 1.9972 | 0.6301 | 0.6979 | 0.9567 | 0.5493 |
| 0.0035 | 3.0 | 68385 | 2.8475 | 0.6870 | 0.7634 | 0.9260 | 0.6494 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu124
- Datasets 2.20.0
- Tokenizers 0.19.1