|
--- |
|
license: cc-by-nc-nd-4.0 |
|
language: |
|
- ja |
|
--- |
|
|
|
|
|
# 七海 TTS(Text-to-Speech) Models |
|
|
|
<p align="center"> |
|
<img src="./七海/nanami.webp" alt="七海 TTS" title="七海 TTS"> |
|
</p> |
|
|
|
## Overview |
|
Introducing the text-to-speech model of 七海(nanami) from Riddle Joker. |
|
|
|
This model is based on text-to-speech model developed in the [Style-Bert_VITS2](https://github.com/litagin02/Style-Bert-VITS2) repository. |
|
|
|
|
|
## Sample |
|
|
|
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/61960aa548981535eeb84cac/bIc2LxpiabAhIsRHVrlBz.wav"></audio> |
|
|
|
```txt |
|
こんにちは、初めまして。あなたの名前はなんていうの？ |
|
``` |
|
|
|
## Installation and Usage |
|
Detailed installation and usage guides can be found in model repositories. the Style-Bert_VITS2 model includes an API server for integration with other applications and tools. |
|
|
|
- Style-Bert_VITS2 Model: [Repository Link](https://github.com/litagin02/Style-Bert-VITS2) |
|
|
|
## License and Credits / Links |
|
|
|
This model is released only for research purpose. |
|
|
|
So, you can't use this model for commercial purpose. |
|
|
|
### Special Thanks |
|
|
|
Thank you for Awesome TTS model from [litagin02](https://github.com/litagin02) |
|
|
|
Thank you for extracting tool from [xmoezzz](https://github.com/xmoezzz/KrkrExtract) |
