|
| 1 | +# Retrieval-based-Voice-Conversion-WebUI |
| 2 | + |
| 3 | +[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) |
| 4 | + |
| 5 | +[](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb) |
| 6 | +[](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt) |
| 7 | +[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/) |
| 8 | + |
| 9 | +### Realtime Voice Conversion Software using RVC : [w-okada/voice-changer](https://github.com/w-okada/voice-changer) |
| 10 | +------ |
| 11 | + |
| 12 | +An easy-to-use SVC framework based on VITS. |
| 13 | + |
| 14 | +[**English**](./README.md) | [**中文简体**](./README_zh_CN.md) |
| 15 | + |
| 16 | +> Check our [Demo Video](https://www.bilibili.com/video/BV1pm4y1z7Gm/) here! |
| 17 | +## Summary |
| 18 | +This repository has the following features: |
| 19 | ++ Using top1 feature model retrieval to reduce tone leakage; |
| 20 | ++ Easy and fast training, even on relatively poor graphics cards; |
| 21 | ++ Training with a small amount of data also obtains relatively good results; |
| 22 | ++ Supporting model fusion to change timbres; |
| 23 | ++ Easy-to-use Webui interface; |
| 24 | ++ Use the UVR5 model to quickly separate vocals and instruments. |
| 25 | +## Preparing the environment |
| 26 | +We recommend you install the dependencies through poetry. |
| 27 | + |
| 28 | +The following commands need to be executed in the environment of Python version 3.8 or higher: |
| 29 | +```bash |
| 30 | +# Install PyTorch-related core dependencies, skip if installed |
| 31 | +# Reference: https://pytorch.org/get-started/locally/ |
| 32 | +pip install torch torchvision torchaudio |
| 33 | + |
| 34 | +# Install the Poetry dependency management tool, skip if installed |
| 35 | +# Reference: https://python-poetry.org/docs/#installation |
| 36 | +curl -sSL https://install.python-poetry.org | python3 - |
| 37 | + |
| 38 | +# Install the project dependencies |
| 39 | +poetry install |
| 40 | +``` |
| 41 | +You can also use pip to install the dependencies |
| 42 | + |
| 43 | +```bash |
| 44 | +pip install -r requirements.txt |
| 45 | +``` |
| 46 | +## Preparation of other Pre-models |
| 47 | +RVC requires other pre-models to infer and train. |
| 48 | + |
| 49 | +You need to download them from our [Huggingface space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/). |
| 50 | + |
| 51 | +Here's a list of Pre-models and other files that RVC needs: |
| 52 | +```bash |
| 53 | +hubert_base.pt |
| 54 | + |
| 55 | +./pretrained |
| 56 | + |
| 57 | +./uvr5_weights |
| 58 | + |
| 59 | +#If you are using Windows, you may also need this dictionary, skip if FFmpeg is installed |
| 60 | +ffmpeg.exe |
| 61 | +``` |
| 62 | +Then use this command to start Webui: |
| 63 | +```bash |
| 64 | +python infer-web.py |
| 65 | +``` |
| 66 | +If you are using Windows, you can download and extract `RVC-beta.7z` to use RVC directly and use `go-web.bat` to start Webui. |
| 67 | + |
| 68 | +We will develop an English version of the WebUI in 2 weeks. |
| 69 | + |
| 70 | +There's also a tutorial on RVC in Chinese and you can check it out if needed. |
| 71 | + |
| 72 | +## Credits |
| 73 | + |
| 74 | +## Thanks to all contributors for their efforts |
| 75 | + |
| 76 | +<a href="https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors" target="_blank"> |
| 77 | + <img src="https://contrib.rocks/image?repo=liujing04/Retrieval-based-Voice-Conversion-WebUI" /> |
| 78 | +</a> |
| 79 | + |
0 commit comments