Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.

iOS Voice Activity Detection (VAD). Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.

Use the yamnet TensorFlow model to classify live audio from a microphone and publish the predicted results to Home Assistant via MQTT

Simple real-time Sound Event Detector based on YAMNet and pyaudio.

Transfer learning and fine-tuning with YAMNet

Yamnet model using tflite_model_maker with esc-50 dataset

Raspberry Pi application that detects music with ML, identifies it using Shazam, and shows the song information on an e-ink display

🔉 A Sound Detection System for the Deaf and Hard of Hearing using On-Device Machine Learning

Sound Event Detection with YAMNet+tw on Raspberry Pi

YAMNet with latest TensorFlowLiteSwift

My music tech thesis prototype as well as recent class project

An AI-powered proctoring tool for secure online exams. Uses YOLOv5 for object detection, MTCNN for face detection, YAMNet for audio detection, and PyQt5 for the UI. Enforces fullscreen mode, disables shortcuts, and provides real-time monitoring with violation tracking. Scalable and resource-efficient.

Sound Event Detection with YAMNet on Jetson Nano

Acoustic event detection using yamnet model. Model is deployed using tensorflow serving in docker container and Flask API

PyTorch implementation of YAMNet model for audio classification

Software for Hard of Hearing

Developing a application and/or website for snore detection using DeepLearning

This git repository is an implementation of three different models for accent recognition and evaluation for the language of English

Raspberry Pi 5 security system combining real-time YOLOv8 object detection and YAMNet audio classification, with alerts via LED, alarm and email notifications.

This project builds a Music Genre Classification System using SVM, CNN, LSTM, and Transformer models, with YAMNet-based feature extraction. It processes audio files, extracts embeddings, and trains multiple models for comparison. The system predicts genres with high accuracy and provides evaluation metrics like classification reports and confusion.