Giter Site home page Giter Site logo

diff-svc-1's Introduction

diff-svc

基于DiffSinger非官方仓库 实现的 diffsvc

暂时依然在开发测试中, 训练应该是没问题的,但推理脚本目前不太完善,还没整合切片机
暂时测试的结论是,当数据集人数过多(比如六七十个人)时音色泄漏会加重,而5个人左右音色泄漏和则单人情况基本差不多
目前可以看到有一堆分支,都是在测试中的各种方案
sr分支(中文hubert+freevc数据增强5倍):中文hubert优化了咬字,数据增强缓解了音色泄漏以及变调问题
discrete分支:使用kmeans聚类对hubert进行离散化,真正完全消除了音色泄漏问题,但是咬字炸了
freevc_encoder分支:使用freevc的预训练模型中的encoder替换softvc hubert,测试下来效果和softvc类似

简介

基于Diffsinger + softvc 实现歌声音色转换。相较于原diffsvc仓库,本仓库优缺点如下

  • 支持多说话人
  • 本仓库基于非官方diffsinger仓库修改实现,代码结构更加简单易懂
  • 声码器同样使用 441khz diffsinger社区声码器
  • 不支持加速

提前下载的文件

  • softvc hubert (hubert-soft-0d54a1f4.pt)放在hubert目录下
  • 441khz diffsinger社区声码器 (model)放在hifigan目录下

数据集准备

仅需要以以下文件结构将数据集放入dataset_raw目录即可

dataset_raw
├───speaker0
│   ├───xxx1-xxx1.wav
│   ├───...
│   └───Lxx-0xx8.wav
└───speaker1
    ├───xx2-0xxx2.wav
    ├───...
    └───xxx7-xxx007.wav

数据预处理

整体基本类似sovits3.0

  1. 重采样
python resample.py
  1. 自动划分训练集 验证集 测试集
python preprocess_flist_config.py
  1. 生成hubert、f0、mel与stats
python preprocess_hubert_f0.py && python gen_stats.py

执行完以上步骤后 dataset 目录便是预处理完成的数据,可以删除dataset_raw文件夹, 也可以删除重采样后的临时wav文件rm dataset/*/*.wav

训练

python3 train.py --model naive --dataset ms --restore_step RESTORE_STEP 

推理

inference.py

diff-svc-1's People

Contributors

innnky avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.