This branch is up to date with hhguo/EA-SVC:master.

Name	Name	Last commit message	Last commit date
Latest commit /bin/eash update readme Nov 4, 2020 38ee75f · Nov 4, 2020 History 3 Commits
configs	configs	build repo	Sep 1, 2020
models	models	build repo	Sep 1, 2020
utils	utils	build repo	Sep 1, 2020
.gitignore	.gitignore	Initial commit	Sep 1, 2020
LICENSE	LICENSE	Initial commit	Sep 1, 2020
README.md	README.md	update readme	Nov 4, 2020
distributed.py	distributed.py	build repo	Sep 1, 2020
inference.py	inference.py	build repo	Sep 1, 2020
train.py	train.py	build repo	Sep 1, 2020

Repository files navigation

EA-SVC

An implement of "Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training"

Data prepare

PPG features (10ms frameshift)
F0 features (10ms frameshift)
Speaker embedding (One embedding per wav file)
Audio files (wave format, 24000 sample rate, mono)

Write Configuration

Set path / directory or other configurations in .json files in directory "configs" Rewrite your data load function in utils/dataset.py

Model Training

Single GPU

CUDA_VISIBLE_DEVICES=0 python train.py -c configs/stage1.json
CUDA_VISIBLE_DEVICES=0 python train.py -c configs/stage2.json
CUDA_VISIBLE_DEVICES=0 python train.py -c configs/stage3.json