Bisher/wav2vec2_ASV_deepfake_audio_detection_DF_finetune_modified_test_1

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

wav2vec2ASVdeepfakeaudiodetectionDFfinetunemodifiedtest_1

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.4676
• —eval_accuracy: 0.945
• —eval_precision: 0.9440
• —eval_recall: 0.945
• —eval_f1: 0.9444
• —eval_TP: 16
• —eval_TN: 173
• —eval_FN: 6
• —eval_FP: 5
• —eval_EER: 0.1573
• —evalmintDCF: 0.0364
• —evalaucroc: 0.8601
• —eval_runtime: 66.2088
• —evalsamplesper_second: 3.021
• —evalstepsper_second: 3.021
• —epoch: 0.2
• —step: 5

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
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 2
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.44.0
• —Pytorch 2.4.0+cpu
• —Datasets 2.21.0
• —Tokenizers 0.19.1