10,638 stars | 784 forks | Jupyter Notebook
What it does
This repository provides a CLI tool for fast audio transcription using OpenAI's Whisper model with optimizations like Flash Attention, enabling users to transcribe hours of audio in minutes on-device.
Why it matters: 🚀 Transcribe 2.5 hours of audio in under 98 seconds with @Vaibhavs10's insanely-fast-whisper CLI! #AI #MachineLearning
Trending today with 1381 new stars
Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.





