An advanced AI assistant that processes both audio and video inputs to provide interactive responses, utilizing LLMs like LLama3.1 using groq api, gemini-1.5-flash. We Optimized LangChain-based inference pipeline with message history management, enabling accurate voice command recognition and dynamic interactions, even in noisy environments.
Olive is a minimal floating dictation assistant for macOS that provides seamless voice-to-text transcription with global hotkey support.
A fully offline audio & video transcription web app built with Django and faster-whisper. Upload any file, extract audio via ffmpeg, and get timestamped transcripts, no APIs, no internet, no data leaves your machine. Supports SRT & TXT export with real-time progress tracking.
A PyQt5-based tool for video subtitle generation, translation, and fusion using Whisper, MarianMT, and FFmpeg.
Daily used tool for me and my frnd, here we have realtime voice to text in cli with very less cpu and gpu usage,and a clipboard and emoji board for linux
A study companion which summarizes youtube videos , classnotes , pdf for better understanding of students along with smart question generation to test themselves
To associate your repository with the wishper-model topic, visit your repo's landing page and select "manage topics."