Starstruk Logo MarkStarstruk

v0.0.1

biomejs/biomev0.0.1Nov 19, 2023by jianchang512

AI Summary

Initial release providing full model downloads for text-to-speech and voice-to-voice conversion.

Key Highlights

  • Full model package including tts and tts_cache folders
  • Instructions for folder structure and troubleshooting
  • Separate downloads for TTS and STS models
  • Training file download instructions

New Features

  • TTS and STS models
  • Model setup instructions
  • Training file support

Full Release Notes

## 完整模型下载(文字转声音和声音转声音)

> 下载完整模型压缩后，压缩包内含有2个文件夹，分别是`tts`和`tts_cache`, 将这2个文件夹覆盖`app.py或app.exe`所在目录下的同名文件夹
> 如图
> ![image](https://github.com/user-attachments/assets/c9e6b8d6-4733-4c1a-80f5-ecfc5e3c28ab)
> 
> 软件目录下有一个`tts`文件夹，包含“文字转声音”和“声音转文字”全部模型后，该文件夹内会存在3个子文件夹，分别是 
>  `tts_models--multilingual--multi-dataset--xtts_v2文件夹`  `voice_conversion_models--multilingual--vctk--freevc24文件夹`  `wavlm 文件夹
>  如下图
> ![image](https://github.com/user-attachments/assets/b379e857-133b-47c6-829e-b571710f65ac)


**百度网盘下载链接(2个模型2.9G):**  https://pan.baidu.com/s/1LkCbGJHeQaRs-sUoB_IbTw?pwd=dqv3

**Huggingface.co下载(2个模型2.9G)**  https://huggingface.co/spaces/mortimerme/s4/resolve/main/clone-voice-all-models.7z?download=true


## 单独下载每个模型

也可单独下载每个模型，在`tts`文件夹内解压


**GitHub下载载文字->声音模型(1.6G )：**  https://github.com/jianchang512/clone-voice/releases/download/v0.0.1/model-tts.7z

**GitHub下载声音->声音模型(1.3G)：** https://github.com/jianchang512/clone-voice/releases/download/v0.0.1/model-sts.7z

----
----

## 提示 声音-声音线程失败，显示连接 github 错误解决

使用预编译时，如果模型均已下载，并正确解压，解压后目录结构如上图所示，但仍提示连接 github 网站失败，请 [下载 extra-to-tts_cache.zip](https://github.com/jianchang512/clone-voice/releases/download/v0.0.1/extra-to-tts_cache.zip) 解压后得到2个文件，将这2个文件复制到 tts_cache 目录下

----
----

## 下载用于训练的文件

下载训练文件后，在软件根目录下解压，然后双击 runtrain.bat 


百度网盘下载：https://pan.baidu.com/s/1_9n-4GJjvUoeVYhkHllJOA?pwd=1k1g

huggingface下载：https://huggingface.co/spaces/mortimerme/s4/resolve/main/train-extract.7z?download=true


----
----

## 模型协议/ Model License 

本项目所用模型为[coqui.ai](https://coqui.ai/)出品的xtts_v2，模型开源协议为[Coqui Public Model License 1.0.0](https://coqui.ai/cpml.txt),使用本项目请遵循该协议，协议全文见 https://coqui.ai/cpml.txt


The model used in this project is xtts_v2 produced by [coqui.ai](https://coqui.ai/), and the model open source license is [Coqui Public Model License 1.0.0](https://coqui.ai/cpml.txt) , please follow this agreement when using this project. The full text of the agreement can be found at https://coqui.ai/cpml.txt