调用kaldi的模型进行解码

Posted 2020-10-06 JarvanWang

At the moment Kaldi is targeted more at people who are building ASR systems

than those who just want to use them. We may in future cater to needs such

as yours.

目前Kaldi面向构建ASR系统的人而不是使用ASR系统的人，以后可能会有API。

Regarding API, the idea is that you would write your decoder code in C++,

patterned after code already in Kaldi.

目前的做法是：仿照Kaldi中的已有的代码，用C++写自己的解码器。

Dan

   

Kaldi的FastCGI，使得基于Kaldi的语音识别可以在支持FastCGI的HTTP服务器（如Apache、nginx）。其中还包含一个基于html的客户端，用于在网页上测试Kaldi语音识别。

https://github.com/api-ai/asr-server

   

   

https://github.com/alumae/kaldi-gstreamer-server