An hour of audio transcribed in about 13s on MacBook Air

A new demo of an AI-powered speech-to-text model, EG2, shows impressive results, transcribing an hour of audio in just 13 seconds on a MacBook Air. The model was trained on a large dataset of audio files and has been shown to outperform other models in terms of speed and accuracy. The demo was shared on a website and has garnered 19 points and 4 comments on Hacker News.