Bind your speech script on mouse button #2944
gnusupport
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Modern mouses have some buttons on sides, in my case those are buttons 8 and 9.
Install
xbindkeys
and configure in$HOME/.xbindkeysrc.scm
You may use different script to invoke the speech recognition. I am using this one:
https://gitea.com/gnusupport/LLM-Helpers/src/branch/main/bin/rcd-llm-speech-single-input.sh
I am running both speech recognition models such as NVIDIA Canary-1B-Flash, the fully free software model: nvidia/canary-1b-flash · Hugging Face:
https://huggingface.co/nvidia/canary-1b-flash and Whisper model.
That is because I often switch LLMs inside of GPU, and sometimes Canary is not running.
I have noticed that Whisper is not going to process 1 second audio, so I have added the command:
which is padding some silence to the audio file before processing it.
Once you have your speech script bound to mouse button, all your computer becomes super-accessible, you can search Internet, YouTube, Github, all by talking, and anything you talk becomes transcribed.
Beta Was this translation helpful? Give feedback.
All reactions