Silero VAD: pre-trained enterprise-grade Voice Activity Detector

An audio/acoustic activity detection and audio segmentation tool

A stream-translator fork with VAD based audio slicing & GPT / Gemini translation.

Binary classification problem that aims to classify human voices from audio recordings. Implemented using PyTorch and Librosa.

The Poetry Pronunciation Learning App is an interactive AI-powered tool that helps users practice and improve their pronunciation of poems. It uses real-time speech recognition, voice activity detection, and fuzzy word matching to provide instant feedback on spoken verses.

End-to-end pipeline for training a custom keyword detection model with TensorFlow & TFLite expor

TranscribeTube is a Python tool that transcribes and generates subtitles for videos from local files or YouTube links using Hugging Face models. It features an interactive Gradio web interface, allowing users to easily upload videos, select languages, and download subtitles in SRT format.

Spoofing voice detection : 2nd YAICON

DΞCIBΞLION is an audio intelligence module forged in the labs of OBINexus, where noise meets logic and shouting is a feature, not a bug. It mathematically analyzes human vocal input to determine emotional projection through log-scaled loudness evaluation, using a sacred constant: 85 dB.

Deep learning model to detect real vs fake (deepfake) voices using CNN and MFCC features.

A robust AI-powered API to detect deepfake audio using Wav2Vec2 and FastAPI. Deployed on Hugging Face Spaces for the CyberSecurity Hackathon.

REST API for detecting AI-generated vs human voices across 5 Indian languages (Tamil, English, Hindi, Malayalam, Telugu) using audio analysis and machine learning

A Python project that handles speech commands and retrieves results from Google or Wikipedia based on the spoken input. Functions are organized in separate files, with a single raw file to execute the project. This repository is intended for project purposes and will be updated with additional features in the future.