README.md

metadata

library_name: diffusers
tags:
  - music

Hugging Face Diffusers Implementation of QA-MDT

QADMT: Quality-Aware Diffusion for Text-to-Music 🎶

QADMT brings a new approach to text-to-music generation by using quality-aware training to tackle issues like low-fidelity audio and weak labeling in datasets.

With a masked diffusion transformer (MDT), QADMT delivers SOTA results on MusicCaps and Song-Describer, enhancing both quality and musicality.

Usage:

!git lfs install
!git clone https://huggingface.co/jadechoghari/qa-mdt

from qa_mdt.pipeline import MOSDiffusionPipeline

pipe = MOSDiffusionPipeline(
    config_yaml="qa_mdt/audioldm_train/config/mos_as_token/qa_mdt.yaml",
    list_inference="qa_mdt/test_prompts/good_prompts_1.lst",
    reload_from_ckpt="qamdt/checkpoints/checkpoint_389999.ckpt",
    base_folder=None
)

pipe()