Kanade-nya / vits-mzk Public

forked from jaywalnut310/vits

Notifications You must be signed in to change notification settings
Fork 3
Star 6

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

jaywalnut310.github.io/vits-demo/index.html

6 stars 1.3k forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 17 Commits
.idea		.idea
configs		configs
filelists		filelists
monotonic_align		monotonic_align
resources		resources
text		text
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
attentions.py		attentions.py
commons.py		commons.py
data_utils.py		data_utils.py
inference.ipynb		inference.ipynb
losses.py		losses.py
mel_processing.py		mel_processing.py
models.py		models.py
modules.py		modules.py
preprocess.py		preprocess.py
requirements.txt		requirements.txt
train.py		train.py
train_ms.py		train_ms.py
transforms.py		transforms.py
utils.py		utils.py

Repository files navigation

vits-mzk

代码及预训练模型

https://colab.research.google.com/drive/1OchYMXCSAuQxt6qIWBBD3RY6VIh1ta2F?usp=sharing

关于授权

基于开源协议。欢迎同人二创作品，但是请勿将语音合成结果直接用于商业目的。
二创作品请注明基于语音合成，并标注语音合成出处，并且请不要制作会造成不良影响的作品。避免造成不必要的误会。

其它

如果有以世界计划语音为基础制作模型的朋友，可能的话请留言，以避免进行重复的工作
目前进度：mzk（完成），airi（完成），saki（进行中）

参考

About

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

jaywalnut310.github.io/vits-demo/index.html

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 94.2%
Jupyter Notebook 4.9%
Cython 0.9%