metadata
library_name: transformers
license: apache-2.0
base_model: Heem2/Deepfake-audio-detection
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: deepfake-audio-detector-v12
results: []
deepfake-audio-detector-v12
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: 0.8698
- Accuracy: 0.9072
- Precision: 0.8756
- Recall: 0.9492
- F1: 0.9109
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: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.4229 | 1.0 | 571 | 0.3528 | 0.8669 | 0.8223 | 0.9361 | 0.8755 |
0.1973 | 2.0 | 1142 | 0.5274 | 0.9076 | 0.8781 | 0.9466 | 0.9111 |
0.2161 | 3.0 | 1713 | 0.8698 | 0.9072 | 0.8756 | 0.9492 | 0.9109 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2