Repository files navigation

简体中文

A fork ofso-vits-svc withrealtime support andgreatly improved interface. Based on branch4.0 (v1) (or4.1) and the models are compatible.4.1 models are not supported. Other models are also not supported.

• Within a year, the technology has evolved enormously and there are many better alternatives
• Was hoping to create a more Modular, easy-to-install repository, but didn't have the skills, time, money to do so
• PySimpleGUI is no longer LGPL
• Using Typer is getting more popular than directly using Click

Always beware of the very few influencers who arequite overly surprised about any new project/technology. You need to take every social networking post with semi-doubt.

The voice changer boom that occurred in 2023 has come to an end, and many developers, not just those in this repository, have been not very active for a while.

There are too many alternatives to list here but:

• RVC family:IAHispano/Applio (MIT),fumiama's RVC (AGPL) andoriginal RVC (MIT)
• VCClient (MIT etc.) is quite actively maintained and offers web-based GUI for real-time conversion.
• fish-diffusion tried to be quite modular but not quite actively maintained.
• yxlllc/DDSP-SVC - new releases are issued occasionally.yxlllc/ReFlow-VAE-SVC
• coqui-ai/TTS was for TTS but was partially modular. However, it is not maintained anymore, unfortunately.

Elsewhere, several start-ups have improved and marketed voice changers (probably for profit).

Updates to this repository have been limited to maintenance since Spring 2023.It is difficult to narrow the list of alternatives here, but please consider trying other projects if you are looking for a voice changer with even better performance (especially in terms of latency other than quality). >However, this project may be ideal for those who want to try out voice conversion for the moment (because it is easy to install).

• Realtime voice conversion (enhanced in v1.1.0)
• Partially integratesQuickVC
• Fixed misuse ofContentVec in the original repository.¹
• More accurate pitch estimation usingCREPE.
• GUI and unified CLI available
• ~2x faster training
• Ready to use just by installing withpip.
• Automatically download pretrained models. No need to installfairseq.
• Code completely formatted with black, isort, autoflake etc.

This BAT file will automatically perform the steps described below.

Windows (development version required due topypa/pipx#940):

py -3 -m pip install --user git+https://github.com/pypa/pipx.gitpy -3 -m pipx ensurepath

Linux/MacOS:

python -m pip install --user pipxpython -m pipx ensurepath

pipx install so-vits-svc-fork --python=3.11pipx inject so-vits-svc-fork torch torchaudio --pip-args="--upgrade" --index-url=https://download.pytorch.org/whl/cu121# https://download.pytorch.org/whl/nightly/cu121

py -3.11 -m venv venvvenv\Scripts\activate

python3.11 -m venv venvsource venv/bin/activate

conda create -n so-vits-svc-fork python=3.11 pipconda activate so-vits-svc-fork

Install this via pip (or your favourite package manager that uses pip):

python -m pip install -U pip setuptools wheelpip install -U torch torchaudio --index-url https://download.pytorch.org/whl/cu121# https://download.pytorch.org/whl/nightly/cu121pip install -U so-vits-svc-fork

Please update this package regularly to get the latest features and bug fixes.

pip install -U so-vits-svc-fork# pipx upgrade so-vits-svc-fork

GUI launches with the following command:

svcg

• Realtime (from microphone)

svc vc

• File

svc infer source.wav

Pretrained models are available onHugging Face orCIVITAI.

• If using WSL, please note that WSL requires additional setup to handle audio and the GUI will not work without finding an audio device.
• In real-time inference, if there is noise on the inputs, the HuBERT model will react to those as well. Consider using realtime noise reduction applications such asRTX Voice in this case.
• Models other than for 4.0v1 or this repository are not supported.
• GPU inference requires at least 4 GB of VRAM. If it does not work, try CPU inference as it is fast enough.²

• If your dataset has BGM, please remove the BGM using software such asUltimate Vocal Remover.3_HP-Vocal-UVR.pth orUVR-MDX-NET Main is recommended.³
• If your dataset is a long audio file with a single speaker, usesvc pre-split to split the dataset into multiple files (usinglibrosa).
• If your dataset is a long audio file with multiple speakers, usesvc pre-sd to split the dataset into multiple files (usingpyannote.audio). Further manual classification may be necessary due to accuracy issues. If speakers speak with a variety of speech styles, set --min-speakers larger than the actual number of speakers. Due to unresolved dependencies, please installpyannote.audio manually:pip install pyannote-audio.
• To manually classify audio files,svc pre-classify is available. Up and down arrow keys can be used to change the playback speed.

⁴

If you do not have access to a GPU with more than 10 GB of VRAM, the free plan of Google Colab is recommended for light users and the Pro/Growth plan of Paperspace is recommended for heavy users. Conversely, if you have access to a high-end GPU, the use of cloud services is not recommended.

Place your dataset likedataset_raw/{speaker_id}/**/{wav_file}.{any_format} (subfolders and non-ASCII filenames are acceptable) and run:

svc pre-resamplesvc pre-configsvc pre-hubertsvc train -t

• Dataset audio duration per file should be <~ 10s.
• Need at least 4GB of VRAM.⁵
• It is recommended to increase thebatch_size as much as possible inconfig.json before thetrain command to match the VRAM capacity. Settingbatch_size toauto-{init_batch_size}-{max_n_trials} (or simplyauto) will automatically increasebatch_size until OOM error occurs, but may not be useful in some cases.
• To useCREPE, replacesvc pre-hubert withsvc pre-hubert -fm crepe.
• To useContentVec correctly, replacesvc pre-config with-t so-vits-svc-4.0v1. Training may take slightly longer because some weights are reset due to reusing legacy initial generator weights.
• To useMS-iSTFT Decoder, replacesvc pre-config withsvc pre-config -t quickvc.
• Silence removal and volume normalization are automatically performed (as in the upstream repo) and are not required.
• If you have trained on a large, copyright-free dataset, consider releasing it as an initial model.
• For further details (e.g. parameters, etc.), you can see theWiki orDiscussions.

For more details, runsvc -h orsvc <subcommand> -h.

> svc -hUsage: svc [OPTIONS] COMMAND [ARGS]...  so-vits-svc allows any folder structurefor training data.  However, the following folder structure is recommended.      When training: dataset_raw/{speaker_name}/**/{wav_name}.{any_format}      When inference: configs/44k/config.json, logs/44k/G_XXXX.pth  If the folder structure is followed, you DO NOT NEED TO SPECIFY model path, config path, etc.  (The latest model will be automatically loaded.)  To train a model, run pre-resample, pre-config, pre-hubert, train.  To infer a model, run infer.Options:  -h, --help  Show this message and exit.Commands:  clean          Clean up files, only usefulif you are using the default file structure  infer          Inference  onnx           Export model to onnx (currently not working)  pre-classify   Classify multiple audio files into multiple files  pre-config     Preprocessing part 2: config  pre-hubert     Preprocessing part 3: hubert If the HuBERT model is not found, it will be...  pre-resample   Preprocessing part 1: resample  pre-sd         Speech diarization using pyannote.audio  pre-split      Split audio files into multiple files  train          Train model If D_0.pth or G_0.pth not found, automatically download from hub.  train-cluster  Train k-means clustering  vc             Realtime inference from microphone

Video Tutorial

Thanks goes to these wonderful people (emoji key):

34j 💻🤔📖💡🚇🚧👀⚠️✅📣🐛	GarrettConway 💻🐛📖👀	BlueAmulet 🤔💬💻🚧	ThrowawayAccount01 🐛	緋 📖🐛	Lordmau5 🐛💻🤔🚧💬📓	DL909 🐛
Satisfy256 🐛	Pierluigi Zagaria 📓	ruckusmattster 🐛	Desuka-art 🐛	heyfixit 📖	Nerdy Rodent 📹	谢宇 📖
ColdCawfee 🐛	sbersier 🤔📓🐛	Meldoner 🐛🤔💻	mmodeusher 🐛	AlonDan 🐛	Likkkez 🐛	Duct Tape Games 🐛
Xianglong He 🐛	75aosu 🐛	tonyco82 🐛	yxlllc 🤔💻	outhipped 🐛	escoolioinglesias 🐛📓📹	Blacksingh 🐛
Mgs. M. Thoyib Antarnusa 🐛	Exosfeer 🐛💻	guranon 🐛🤔💻	Alexander Koumis 💻	acekagami 🌍	Highupech 🐛	Scorpi 💻
Maximxls 💻	Star3Lord 🐛💻	Forkoz 🐛💻	Zerui Chen 💻🤔	Roee Shenberg 📓🤔💻	Justas 🐛💻	Onako2 📖
4ll0w3v1l 💻	j5y0V6b 🛡️	marcellocirelli 🐛	Priyanshu Patel 💻	Anna Gorshunova 🐛💻

This project follows theall-contributors specification. Contributions of any kind welcome!

This package was created withCopier and thebrowniebroke/pypackage-templateproject template.