search

shirayu / whispering

Streaming transcriber with whisper
MIT License
682 stars 53 forks source link

Possible to use with a pipe? #52

Closed jshep321 closed 1 year ago

jshep321 commented 1 year ago

I'm curious what the required input format is? I would like to point this to a stream and test it out. It's an mp3 stream, but I have access to the source audio and can encode in any format.

Running headless on a linux cloud server ideally.

shirayu commented 1 year ago

It is possible to write codes of web sockets clients.

The current websocket client listens to microphone with sounddevice.

https://github.com/shirayu/whispering/blob/f3c9d8ad105953233c33bd035c9aba1e41ef3499/whispering/websocket_client.py#L36-L43

I'm not very sure but there should be a way to get audio data from mp3 instead from microphone.

github-actions[bot] commented 1 year ago

This issue is stale because it has been open for 21 days with no activity.