ufal / whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

server <- sounddevice and read from real time mic

RwGrid opened this issue · comments

commented

can u give us a running example with sounddevice and read from real time mic. it will give you greater reach

Hello,
thanks for your interest.

I'm sorry, I can't give example with mic stdin. I myself run whisper on a remote server where I don't have the sounddevice and can't plug the mic. The only what I can do is to add whisper_online_server that receives audio through TCP socket and sends the output there. Then you can use a client like your-way-for-realtime-mic-output | nc $HOST $PORT.

Are you interested in the server?

Furthermore, the way how to connect sounddevice and mic differs by OS and platform. I can't manage them and I want to keep the code simple. But it's open source -- anybody can fork and pull request.

commented

you're welcome.

Done.