jsvir/sparknet
[Tiny KWS] SparkNet: Sparse Binarization for Fast Keyword Spotting
This project helps embedded systems engineers and product developers add always-on voice command capabilities to very small, low-power devices. It takes spoken audio input and identifies predefined keywords or phrases, outputting a recognition signal. This is ideal for anyone building smart devices that respond to simple voice commands without needing a constant internet connection.
No commits in the last 6 months.
Use this if you need to integrate efficient and accurate keyword spotting directly onto micro-controllers or edge devices with very limited computational resources and battery life.
Not ideal if you need to process complex natural language, transcribe continuous speech, or operate in environments without strict power or memory constraints.
Stars
17
Forks
1
Language
Python
License
MIT
Category
Last pushed
Aug 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jsvir/sparknet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Picovoice/porcupine
On-device wake word detection powered by deep learning
MycroftAI/mycroft-precise
A lightweight, simple-to-use, RNN wake word listener
arcosoph/nanowakeword
A lightweight, open-source, and intelligent wake word detection engine. Train custom,...
mozilla/DeepSpeech
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run...
OAID/cortex-m-kws
Cortex M KWS example with Tengine Lite.