Skip to content

An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)

Notifications You must be signed in to change notification settings

hrnoh24/stream-vc

Repository files navigation

[WIP] StreamVC (Real-Time Low-Latency Voice Conversion)

PyTorch Lightning Config: Hydra Template
Paper Conference

Description

An unofficial PyTorch implementation of Google's StreamVC. Architecture

Installation

Pip

# clone project
git clone https://github.com/hrnoh24/stream-vc.git
cd stream-vc

# [OPTIONAL] create conda environment
conda create -n streamvc python=3.10
conda activate streamvc

# install pytorch according to instructions
# https://pytorch.org/get-started/

# install requirements
pip install -r requirements.txt

How to run

Train model with default configuration

# train on CPU
python src/train.py trainer=cpu

# train on GPU
python src/train.py trainer=gpu

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_name.yaml

You can override any parameter from command line like this

python src/train.py trainer.max_epochs=20 data.batch_size=64

Reference

https://github.com/lucidrains/audiolm-pytorch/tree/main
https://github.com/facebookresearch/encodec/tree/main
https://github.com/jaywalnut310/vits/tree/main
https://github.com/wesbz/SoundStream/blob/main/main.py
https://github.com/bshall/soft-vc
https://github.com/descriptinc/melgan-neurips/tree/master

About

An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages