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_V2
results: []
deepfake-audio-detector_V2
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: 0.0708
- Accuracy: 0.9961
- Precision: 0.9949
- Recall: 0.9974
- F1: 0.9961
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4204 | 1.0 | 388 | 0.5132 | 0.9691 | 0.9483 | 0.9923 | 0.9698 |
| 0.5578 | 2.0 | 776 | 0.3286 | 0.9794 | 0.9697 | 0.9897 | 0.9796 |
| 0.2106 | 3.0 | 1164 | 0.1348 | 0.9923 | 0.9923 | 0.9923 | 0.9923 |
| 0.2262 | 4.0 | 1552 | 0.0624 | 0.9961 | 0.9923 | 1.0 | 0.9961 |
| 0.0 | 4.9884 | 1935 | 0.0708 | 0.9961 | 0.9949 | 0.9974 | 0.9961 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1