Real-time speech recognition and display of recognition results in the browser

[litongjava]

Real-time speech recognition and display of recognition results in the browser
Functionality is complete and ready for testing

backend

https://github.com/litongjava/whisper-cpp-server

frontend

https://github.com/litongjava/listen-know-web

whisper-cpp-server-test.mp4

[eschmidbauer]

Can it handle multiple concurrent audio streams (e.g. connections from users)?
If not, i setup a fork which can handle multiple connections by switching to boost. Please consider incorporating the change to support multiple streams

[litongjava]

@eschmidbauer HTTP interface support, WebSocket interface is not supported, but can be implemented by simply modifying the code. Put the user and the audio to be processed to a map