AST-ASVspoof5-Synthetic-Voice-Detection
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.2821
- Accuracy: 0.8333
- F1: 0.8892
- Precision: 0.9209
- Recall: 0.8595
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 |
|---|---|---|---|---|---|---|---|
| 0.0042 | 1.0 | 22795 | 1.6954 | 0.8470 | 0.8942 | 0.9672 | 0.8314 |
| 0.0 | 2.0 | 45590 | 1.5632 | 0.8489 | 0.9014 | 0.9157 | 0.8875 |
| 0.0 | 3.0 | 68385 | 2.2821 | 0.8333 | 0.8892 | 0.9209 | 0.8595 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1