The Beginner's Guide to Diff-SVC
  • Project Overview
  • Setting Up
    • Requirements
    • Setting up the Environment
  • Start
    • Dataset Preparation
    • Preprocessing
    • Training
    • Inference
  • See also
  • Appendix
  • Resource List
Powered by GitBook
On this page
  • Community Resource
  • [Guide] DIFF-SVC FOR VOCAL SYNTH USERS
  • [Online Inference Tool] DIFF-SVC Render
  • [Local Inference Tool] MoeTTS
  • Related Projects
  • Diff-SVC (OpenVPI's fork)
  • Fish Diffusion
  • SoftVC VITS Singing Voice Conversion (sovits 3.0)
  • Glossary

Was this helpful?

Resource List

Diff-SVC Discord server invite: https://discord.gg/3CtFhTsvuG Please read and follow the guide carefully before asking questions in the Discord server.

And please ask questions effectively if you do. (Describe what you tried and what issues you encountered with error messages/screenshots)

Community Resource

[Guide] DIFF-SVC FOR VOCAL SYNTH USERS

  • A very detailed guide for using Google Colab or a local machine to train and infer Diff-SVC models.

  • Author: julieraptor

  • Link: https://docs.google.com/document/d/1nA3PfQ-BooUpjCYErU-BHYvg2_NazAYJ0mvvmcjG40o

[Online Inference Tool] DIFF-SVC Render

  • (*Usage Request needed)

  • Huggingface cloud inference tool, without the need to set up an environment

  • Author: Kangarroar

  • Link: https://huggingface.co/spaces/DIFF-SVCModel/Inference

[Local Inference Tool] MoeTTS

  • (*Interface in Chinese)

  • A GUI tool that supports Diff-SVC and multiple TTS models.

  • Author: luoyi

  • Link: https://github.com/luoyily/MoeTTS

Related Projects

If you followed this guide carefully and know how to troubleshoot using search engines, you should be able to run some of the related projects below if you are interested.

Diff-SVC (OpenVPI's fork)

  • A refactored Diff-SVC with multi-speaker support, additional utility scripts, and more.

  • Author: OpenVPI

  • Github: https://github.com/openvpi/diff-svc

Fish Diffusion

  • An "easy to understand TTS / SVS / SVC framework" refactored on Diff-SVC/DiffSinger. With multi-speaker, multi-devices and half-precision training support, and more.

  • Author: Lengyue

  • Github: https://github.com/fishaudio/fish-diffusion

SoftVC VITS Singing Voice Conversion (sovits 3.0)

  • An SVC project based on VITS and soft-vc. Performs better on low-quality datasets, and inference faster in general than Diff-SVC.

  • Author: rcell

  • Github: https://github.com/innnky/so-vits-svc

Glossary

Search online or check the links below if you have difficulty understanding some terms in this guide.

PreviousAppendix

Last updated 2 years ago

Was this helpful?

LogoMachine Learning Glossary  |  Google DevelopersGoogle Developers
LogoGlossary — ML Glossary documentation