ArkanDash/Advanced-RVC-Inference

# Advanced RVC Inference [![Colab](https://img.shields.io/badge/Colab-Advanced%20RVC%20Inference-blue?style=for-the-badge&logo=googlecolab)](https://colab.research.google.com/github/ArkanDash/Advanced-RVC-Inference/blob/master/Advanced-RVC.ipynb)

Information

Advanced RVC Inference presents itself as a state-of-the-art web UI crafted to streamline rapid and effortless inference. This comprehensive toolset encompasses a model downloader, a voice splitter, and the added efficiency of batch inference.

Please support the original RVC. This inference won't be possible to make without it.

Features

Support V1 & V2 Model ✅
Youtube Audio Downloader ✅
Demucs (Voice Splitter) [Internet required for downloading model] ✅
Microphone Support ✅
TTS Support ✅
Model Downloader ✅
Batch Inference (Beta) ✅

Currently Working

Settings 🛠

Installation

Install Dependencies


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)

### Run WebUI <br />

For Windows:
```bash
Open run.bat

For Other:

python infer.py