README.md

metadata

title: MusicGen
emoji: 🎶
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.24.0
python_version: '3.12'
app_file: app.py
pinned: false
license: cc-by-nc-4.0
short_description: Text-to-music generation with melody conditioning
tags:
  - category:generation
  - subcategory:holistic
  - domain:music
  - input:audio
  - input:text
  - output:audio
  - sample-rate:32000
  - channels:mono
  - melody-conditioning
startup_duration_timeout: 1h

HARP endpoint for MusicGen, a text-to-music generation model by Meta FAIR with melody conditioning support.

This deployment uses the MusicGen-Melody checkpoint (1.5B parameters) via the Hugging Face transformers library. The model weights are licensed under CC BY-NC 4.0.

Source attribution is recorded in SOURCES.md.