harvard-edge/multilingual_kws
Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus
This project helps you quickly create a system to detect specific keywords spoken in any language, even if you only have a few examples of the keyword. You provide audio recordings and a small number of keyword examples, and it outputs a model that can identify those keywords in new speech. It's designed for researchers or product developers building voice-controlled interfaces or spoken language understanding systems.
186 stars. No commits in the last 6 months.
Use this if you need to spot specific keywords across many languages with minimal training data for each keyword.
Not ideal if you're looking for a general-purpose speech-to-text transcription service rather than specific keyword detection.
Stars
186
Forks
42
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/harvard-edge/multilingual_kws"
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.