mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-06-24 01:17:28 +08:00

* Add MusicGen model * add benchmarks * change to from_pretrained * symlinks * add readme and requirements * fix readme * readme
662 B
662 B
MusicGen
An example of Meta's MusicGen model in MLX.1 MusicGen is used to generate music from text descriptions.
Setup
Install the requirements:
pip install -r requirements.txt
Example
An example using the model:
import mlx.core as mx
from music_gen import MusicGen
from utils import save_audio
model = MusicGen.from_pretrained("facebook/musicgen-medium")
audio = model.generate("happy rock")
save_audio("out.wav", audio, model.sampling_rate)
-
Refer to the arXiv paper and code for more details. ↩︎