This Inference Pipeline is from Mangio-Fork
Support V1 Model and V2 Model

Original Repository: Retrieval-based-Voice-Conversion-WebUI
Mangio-Fork Repository: RVC-Mangio-Fork-WebUI

• Youtube Audio Downloader
• Demucs (Voice Splitter) [Internet Required]
• TTS Support
• HuggingFace Spaces Inference [FREE TIER CPU]
  • Remove Youtube & Input Path
  • Remove Crepe Support due to gpu requirement

• New Multi RVC Inference ❗
• Model Downloader

Download Hubert Model

Install Requirement

pip install -r requirements.txt

Run WebUI

python app.py

Share gradio

python app.py --colab