Cloyir/index-tts2-ForDgxSpark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #368 from index-tts/tts2dev

Browse Source 
Include usage notes for Pinyin
This commit is contained in:
index-tts 2025-09-16 13:22:22 +08:00 committed by GitHub
commit 45d8d13f0b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 1760 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -35,9 +35,9 @@
<img src='https://img.shields.io/badge/HuggingFace-Model-blue?logo=huggingface' />
</a>
<br/>
<!--a href='https://modelscope.cn/studios/IndexTeam/IndexTTS-Demo'>
<a href='https://modelscope.cn/studios/IndexTeam/IndexTTS-2-Demo'>
<img src='https://img.shields.io/badge/ModelScope-Demo-purple?logo=modelscope'/>
</a-->
</>
<a href='https://modelscope.cn/models/IndexTeam/IndexTTS-2'>
<img src='https://img.shields.io/badge/ModelScope-Model-purple?logo=modelscope'/>
</a>
@ -363,6 +363,18 @@ emo_text = "你吓死我了！你是鬼吗？"
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, emo_text=emo_text, use_random=False, verbose=True)
```
> [!TIP]
> **Pinyin Usage Notes:**
>
> IndexTTS2 still supports mixed modeling of Chinese characters and Pinyin.
> When you need precise pronunciation control, please provide text with specific Pinyin annotations to activate the Pinyin control feature.
> Note that Pinyin control does not work for every possible consonant–vowel combination; only valid Chinese Pinyin cases are supported.
> For the full list of valid entries, please refer to `checkpoints/pinyin.vocab`.
>
> Example:
> ```
> 之前你做DE5很好，所以这一次也DEI3做DE2很好才XING2，如果这次目标完成得不错的话，我们就直接打DI1去银行取钱。
> ```
### Legacy: IndexTTS1 User Guide
@ -382,7 +394,7 @@ or visit the IndexTTS1 repository at <a href="https://github.com/index-tts/index
## Our Releases and Demos
### IndexTTS2: [[Paper]](https://arxiv.org/abs/2506.21619); [[Demo]](https://index-tts.github.io/index-tts2.github.io/); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS-2-Demo)
### IndexTTS2: [[Paper]](https://arxiv.org/abs/2506.21619); [[Demo]](https://index-tts.github.io/index-tts2.github.io/); [[ModelScope]](https://modelscope.cn/studios/IndexTeam/IndexTTS-2-Demo); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS-2-Demo)
### IndexTTS1: [[Paper]](https://arxiv.org/abs/2502.05512); [[Demo]](https://index-tts.github.io/); [[ModelScope]](https://modelscope.cn/studios/IndexTeam/IndexTTS-Demo); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS)

1728
checkpoints/pinyin.vocab Normal file
View File

File diff suppressed because it is too large Load Diff

18
docs/README_zh.md
View File

@ -33,6 +33,9 @@
<img src='https://img.shields.io/badge/HuggingFace-Model-blue?logo=huggingface' />
</a>
<br/>
<a href='https://modelscope.cn/studios/IndexTeam/IndexTTS-2-Demo'>
<img src='https://img.shields.io/badge/ModelScope-Demo-purple?logo=modelscope'/>
</>
<a href='https://modelscope.cn/models/IndexTeam/IndexTTS-2'>
<img src='https://img.shields.io/badge/ModelScope-Model-purple?logo=modelscope'/>
</a>
@ -291,6 +294,19 @@ emo_text = "你吓死我了！你是鬼吗？"
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, emo_text=emo_text, use_random=False, verbose=True)
```
> [!TIP]
> **拼音使用注意事项:**
>
> IndexTTS2依然支持中文字符与拼音混合建模。
> 在使用时，如果需要精确的发音控制，请输入包含特定拼音标注的文本来触发拼音控制功能。
> 需要注意的是：拼音控制并不是对所有声母韵母（辅音、元音）组合都生效，系统仅保留中文合法拼音的发音。
> 具体合法情况可参考项目中的`checkpoints/pinyin.vocab`文件。
>
> 参考样例:
> ```
> 之前你做DE5很好，所以这一次也DEI3做DE2很好才XING2，如果这次目标完成得不错的话，我们就直接打DI1去银行取钱。
> ```
### 旧版IndexTTS1使用指南
如果需要使用旧的IndexTTS1.5模型，可以import旧模块：
@ -307,7 +323,7 @@ tts.infer(voice, text, 'gen.wav')
## 演示
### IndexTTS2: [[论文]](https://arxiv.org/abs/2506.21619); [[演示]](https://index-tts.github.io/index-tts2.github.io/); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS-2-Demo)
### IndexTTS2: [[论文]](https://arxiv.org/abs/2506.21619); [[演示]](https://index-tts.github.io/index-tts2.github.io/); [[ModelScope]](https://modelscope.cn/studios/IndexTeam/IndexTTS-2-Demo); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS-2-Demo)
### IndexTTS1: [[论文]](https://arxiv.org/abs/2502.05512); [[演示]](https://index-tts.github.io/); [[ModelScope]](https://modelscope.cn/studios/IndexTeam/IndexTTS-Demo); [[HuggingFace]](https://huggingface.co/spaces/IndexTeam/IndexTTS)