mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-09-01 12:49:50 +08:00
ccd69f70ed
* Large-v3 requires 128 Mel frequency bins * extract correct model dimensions and use argparse * format * format --------- Co-authored-by: Awni Hannun <awni@apple.com>
Whisper
Speech recognition with Whisper in MLX. Whisper is a set of open source speech recognition models from OpenAI, 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"]
-
Refer to the arXiv paper, blog post, and code for more details. ↩︎