mlx-examples/whisper/README.md

whisper

Speech recognition with Whisper in MLX. Whisper is a set of open source speech recognition models from Open AI, ranging from 39 million to 1.5 billion parameters¹.

Setup

First, install the dependencies.

pip install -r requirements.txt

Install ffmpeg:

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

Run

Transcribe audio with:

import whisper

text = whisper.transcribe(speech_file)["text"]

---

1. Refer to the arXiv paper, blog post, and code for more details. ↩︎