# Multi-Model RVC Inference ### Simplified RVC Inference for HuggingFace or Google Colab [![License](https://img.shields.io/github/license/arkandash/Multi-Model-RVC-Inference?style=for-the-badge)](https://github.com/ArkanDash/Multi-Model-RVC-Inference/blob/master/LICENSE) [![Repository](https://img.shields.io/badge/Github-Multi%20Model%20RVC%20Inference-blue?style=for-the-badge&logo=github)](https://github.com/ArkanDash/Multi-Model-RVC-Inference)
### Information Please support the original RVC, without it, this inference wont be possible to make.
[![Original RVC Repository](https://img.shields.io/badge/Github-Original%20RVC%20Repository-blue?style=for-the-badge&logo=github)](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. Install Requirement
```bash pip install torch torchvision torchaudio pip install -r requirements.txt ``` 2. Install [ffmpeg](https://ffmpeg.org/) 3. Download [Hubert Model](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/hubert_base.pt)
4. [OPTIONAL] To use rmvpe pitch extraction, download this [rvmpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt) 5. Run WebUI
```bash python app.py ``` ### [How to use](docs/HOW_TO_USE.md) ### [Command Line Arguments](docs/COMMAND_LINE_ARGUMENTS.md) # Other Inference [![Advanced RVC Inference](https://img.shields.io/badge/Github-Advanced_RVC_Inference-blue?style=for-the-badge&logo=github)](https://github.com/ArkanDash/Advanced-RVC-Inference)