---
title: OpenMusic
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/OpenMusic"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/OpenMusic.md"
repository: AI-ModelScope/OpenMusic
last_updated: 2024-10-11
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 2762
stars: 5
tags:
  - music
---

# OpenMusic

> OpenMusic - AI-ModelScope 在 ModelScope 开源的模型。Official Hugging Face Diffusers Implementation of QA-MDT QAMDT: Quality-Aware Diffusion for Text-to-Music 🎶

- **Repository**: AI-ModelScope/OpenMusic
- **Tags**: music
- **Downloads**: 2762
- **Stars**: 5
- **Last updated**: 2024-10-11

Source: https://www.modelscope.cn/models/AI-ModelScope/OpenMusic

---

# Official Hugging Face Diffusers Implementation of QA-MDT 
**QAMDT: 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. 

It follows from [this paper](https://arxiv.org/pdf/2405.15863) by the University of Science and Technology of China, authored by [@changli](https://github.com/ivcylc) *et al.*.
## Usage:

```bash
!git lfs install
!git clone https://huggingface.co/jadechoghari/openmusic qa_mdt
```

This command will change the folder name from `openmusic` to `qa_mdt`

```bash
pip install -r qa_mdt/requirements.txt
pip install xformers==0.0.26.post1
pip install torchlibrosa==0.0.9 librosa==0.9.2
pip install -q pytorch_lightning==2.1.3 torchlibrosa==0.0.9 librosa==0.9.2 ftfy==6.1.1 braceexpand
pip install torch==2.3.0+cu121 torchvision==0.18.0+cu121 torchaudio==2.3.0 --index-url https://download.pytorch.org/whl/cu121
```

```python
from qa_mdt.pipeline import MOSDiffusionPipeline

pipe = MOSDiffusionPipeline()
pipe("A modern synthesizer creating futuristic soundscapes.")
```

# Enjoy the music!! 🎶