TTS

This is continue for Coqui Cantonese Development Notes

Coqui TTS

🐸（青蛙）TTS

https://github.com/coqui-ai/TTS

https://coqui.ai/

For the first time, tts need to download  a data model. If the download fails, it will fail for the second time. We need to remove empty data model folder from path below to make it do a retry download:

/home/hgneng/.local/share/tts/

希尔贝壳中文普通话语音数据库AISHELL-3的语音时长为85小时88035句，可做为多说话人合成系统。录制过程在安静室内环境中， 使用高保真麦克风（44.1kHz，16bit）。218名来自中国不同口音区域的发言人参与录制。专业语音校对人员进行拼音和韵律标注，并通过严格质量检验，此数据库音字确率在98%以上。

https://www.aishelltech.com/aishell_3

Common Voice Dataset

We’re building an open source, multi-language dataset of voices that anyone can use to train speech-enabled applications.

Includes both Cantonese and Mandarin Chinese!!

抽样粤语（Chinese Hong Kong）语音数据的质量不好，录音人声音不够清晰（不是声优级别的声音），背景噪音较大，标记文件有错。另外还有个Cantonese的分类。

感觉可能用现有的TTS生成数据质量会好得多。

According to https://docs.coqui.ai/en/stable/models/xtts.html , it supports Chinese.

run this to check:

 tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 \
   --list_language_idx

When it fails download, try to set proxy (pay attention that it's "http" for https_proxy):

它和Coqui一样都可以通过Python TTS模块调用（这是因为Coqui是Mozilla派生出来的）

https://github.com/mozilla/TTS

Coqui TTS (formerly Mozilla TTS):

一个集成过个TTS的服务框架，可以了解一些常用的TTS。

https://github.com/synesthesiam/opentts

https://github.com/atomicoo/FCH-TTS

We may encounter issue of fail to download cmudict. We need to solve it like this:

$ python3
>>> import nltk
>>> nltk.set_proxy('127.0.0.1:7890')
>>> nltk.downlad('cmudict')

据说这个网站也有数据库： MONLAM.AI  ，但我看不懂藏语。似乎也无法访问了。

https://www.zhihu.com/column/speech-synthesis