Skip to content

Latest commit

 

History

History
13 lines (9 loc) · 1.15 KB

README.md

File metadata and controls

13 lines (9 loc) · 1.15 KB

Speaker Anonymization Models

This collection of models are meant to be used with the evaluation framework spkanon_eval. The additional dependencies are defines in the corresponding build files in the build folder. The config and components of each model can be found under the model's folder.

Information and evaluation results for each model can be found in the docs folder.

Current models

  • STT-TTS with Whisper & FastPitch: does not require any further installation. Read more about this pipeline here.
  • StarGANv2-VC: install it with build/stargan.sh. Read more about this pipeline here.
  • Soft-VC: install it with build/softvc.sh does not require any further installation. Read more about this pipeline here.
  • kNN-VC: You only need the WavLM and HifiGAN checkpoints to run this model. Read more about this pipeline here.
  • Bark-VC: requires the installation of Coqui TTS. Read more about this pipeline here.