mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-06-24 09:21:18 +08:00
07c163d9d9
* 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 | ||
| benchmark.py | ||
| README.md | ||
| requirements.txt | ||
| test.py | ||
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. ↩︎