Gregory's ServerSome notes on mlx-whisper - it's now really easy to run transcriptions through an Apple Silicon (and GPU) optimized Whisper model using Python on macOS https://simonwillison.net/2024/Aug/13/mlx-whisper/
 5 comments
@saurabhs anecdotally it sounds like it’s a lot faster: https://twitter.com/awnihannun/status/1822744609241682077 says “distil-large-v3 runs 40X faster than realtime on my M1 Max (transcribes 12 minutes in 18 seconds)”  @simon I wanted to know how the speed compares to `whisper.cpp`, since the openAI whisper is very slow on my mac, so I ran a test: https://notes.billmill.org/link_blog/2024/08/mlx-whisper.html mlx ran almost 3x faster than whisper.cpp with a model of the same size, and both were using the GPU. I would love to know why it's so much faster! |
@simon Nitpick: Whisper is speech-to-text. Text-to-speech is speech synthesis.