ARIRIGI/SpeechModels

SpeechModel 语音模型

English | 简体中文

English

This repository, named "SpeechModel", is dedicated to storing audio algorithm-related models. The corresponding codebases can be found in separate repositories.

The project structure is as follows:

├── so-vits-svc
│ ├── araragi
│ ├── base
│ ├── haoyami_saori
│ ├── senjougahara
│ ├── smalljin
│ ├── sunyanzi
│ └── zoe_araragi_v1
└── vits
├── C
│ └── aishell3
├── CJ
│ ├── hayami_saori
│ └── oshino_shinobu
└── CJE

so-vits-svc

This directory contains models for voice conversion, originating from the project so-vits-svc. Each sub-directory represents a model for a specific speaker.

vits

This directory contains models for Text-to-Speech (TTS) from the project VITS. The sub-directories 'C', 'CJ', and 'CJE' respectively represent models for Chinese, Chinese-Japanese, and Chinese-Japanese-English.

---

简体中文

该仓库名为"SpeechModel"，专用于存储音频算法相关模型。相应的代码库可以在单独的仓库中找到。

项目结构如下：

├── so-vits-svc
│ ├── araragi
│ ├── base
│ ├── haoyami_saori
│ ├── senjougahara
│ ├── smalljin
│ ├── sunyanzi
│ └── zoe_araragi_v1
└── vits
├── C
│ └── aishell3
├── CJ
│ ├── hayami_saori
│ └── oshino_shinobu
└── CJE

so-vits-svc

该目录包含来自项目 so-vits-svc 的语音转换模型。每个子目录代表特定说话人的模型。

vits

该目录包含来自项目 VITS 的文本转语音（TTS）模型。子目录 'C', 'CJ', 和 'CJE' 分别代表中文、中日、中日英的模型。

---

license: mit