nsry123 / UniSwitchView on GitHub
A local acoustic control system that learns user-defined labels for the surface or location of knocks, such as desk or wall. It also counts threshold-qualified knocks within each captured window. By default, a frozen Microsoft BEATs Iter3+ AS2M encoder creates 768-D audio embeddings and an incremental classifier learns the user's labels.
☆44Oct 13, 2026Updated this week

Alternatives and similar repositories for UniSwitch

Users that are interested in UniSwitch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?