roman-vygon/triplet_loss_kws
Learning Efficient Representations for Keyword Spotting with Triplet Loss
This project helps machine learning engineers or researchers build better keyword spotting systems. It allows you to train models that can more accurately identify specific keywords in spoken audio, even with limited examples. You provide audio datasets, and it outputs trained models capable of efficient keyword recognition.
113 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing custom keyword spotting solutions and want to improve model performance and efficiency.
Not ideal if you are a non-technical user looking for an out-of-the-box keyword spotting application or a simple API to integrate.
Stars
113
Forks
16
Language
Python
License
MIT
Category
Last pushed
Sep 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/roman-vygon/triplet_loss_kws"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Ant-Brain/EfficientWord-Net
OneShot Learning-based hotword detection.
ARM-software/ML-KWS-for-MCU
Keyword spotting on Arm Cortex-M Microcontrollers
Tony607/Keras-Trigger-Word
How to do Real Time Trigger Word Detection with Keras | DLology
ardamavi/Vocalization-Sign-Language-iOS
Vocalization sign language iOS App with deep learning using CoreML.
mzakharo/lg_detector
Detect LG Appliance Completion with a Microphone, Machine Learning, and ESP32