version 0.1
add test.wav
default model needs installed message
sprec is a simple speech recognition command that can be used for transcription or automation.
It uses the Vosk speech recognition toolkit, which is FOSS and offline.
go
(aka golang
) and scdoc
are required.
A binary of the speech recognition library and an English model (about 40MB) can be installed with:
./get-vosk.sh && sudo ./get-vosk.sh install
./get-model.sh && sudo ./get-model.sh install
sprec itself can be installed with:
./build.sh && sudo ./build.sh install
sprec is documented in the manpage.
The sprec_type script types out speech recognition results in realtime. It uses arecord and dotool, and has a --help flag.
For full-on handsfree computing, see Numen.
You can send questions or patches by composing an email to ~geb/public-inbox@lists.sr.ht.
GPLv3 only, see LICENSE.
Copyright (c) 2023 John Gebbie