Skip to content

vvestman/asdf

Repository files navigation

Artificial Speech Detection Framework (ASDF)

ASDF is a framework for training anti-spoofing neural networks for automatic speaker verification.

Main features

  • Multi-GPU training with DistributedDataParallel
  • Multi-GPU scoring of audio files of variable lengths

Installation

  1. Clone ASDF repository
    1. Navigate to a folder, where you want ASDF to be placed to
    2. git clone https://github.com/vvestman/asdf.git
    3. cd asdf

Use an environment such as the following:

  1. conda create -n asdf python=3.12
  2. conda activate asdf
  3. pip install -r requirements.txt

Running the Wav2Vec-AASIST recipe

Other instructions

About

Artificial Speech Detection Framework

Resources

License

MIT, MIT licenses found

Licenses found

MIT
LICENSE.txt
MIT
License_fairseq.txt

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages