You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Web application that transcribes YouTube videos using OpenAI's Whisper model. Users input a YouTube URL; the app downloads the audio, performs transcription, and displays results in real-time. Built with Flask, yt-dlp, and the Whisper library, it offers a simple and efficient interface for audio-to-text conversion from YouTube content.
A streamlined CLI tool combining `yt-dlp` and `whisperx` (or `openai-whisper`) for quick and efficient audio transcription from various video platforms.
Automatic transcriber made with the Nvidia NeMo AI toolkit. Used to transcribe speech to text in real-time from any source. Requires CUDA capable GPU to run on the local machine, if setup using virtual audio cables can transcribe the audio that is being played in real-time without any other requirements.