CoolFace
Apppublic

Smotto/Sing-For-Me

sourceHugging Faceopenrailupdated 3y agoView on Hugging Face
0likes
App README

<div align="center">

Multi-Model RVC Inference

Simplified RVC Inference for HuggingFace or Google Colab

![License](https://github.com/ArkanDash/Multi-Model-RVC-Inference/blob/master/LICENSE) ![Repository](https://github.com/ArkanDash/Multi-Model-RVC-Inference) </div>

Information

Please support the original RVC, without it, this inference wont be possible to make.<br /> ![Original RVC Repository](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)

Features
  • —Support V1 & V2 Model ✅
  • —Youtube Audio Downloader ✅
  • —Demucs (Voice Splitter) [Internet required for downloading model] ✅
  • —TTS Support ✅
  • —Microphone Support ✅
  • —HuggingFace Spaces Inference [FREE TIER CPU] ✅
  • —Remove Youtube & Input Path ✅
  • —Remove Crepe Support due to gpu requirement ✅

Installation

  1. 1.Install Requirement <br />
bash
pip install torch torchvision torchaudio

pip install -r requirements.txt
  1. 1.Install ffmpeg
  1. 1.Download Hubert Model <br />
  1. 1.[OPTIONAL] To use rmvpe pitch extraction, download this rvmpe.pt
  1. 1.Run WebUI <br />
bash
python app.py

Other Inference

![Advanced RVC Inference](https://github.com/ArkanDash/Multi-Model-RVC-Inference) Advanced RVC Inference