Mustango

🚀 Mustango: Toward Controllable Text-to-Music Generation

Mustango is an exciting addition to the Multimodal Large Language Models for controlled music generation. It uses Latent Diffusion Model (LDM), Flan - T5, and musical features to achieve remarkable results.

🚀 Quick Start

Generate music from a text prompt:

import IPython
import soundfile as sf
from mustango import Mustango

model = Mustango("declare-lab/mustango")

prompt = "This is a new age piece. There is a flute playing the main melody with a lot of staccato notes. The rhythmic background consists of a medium tempo electronic drum beat with percussive elements all over the spectrum. There is a playful atmosphere to the piece. This piece can be used in the soundtrack of a children's TV show or an advertisement jingle."

music = model.generate(prompt)
sf.write(f"{prompt}.wav", audio, samplerate=16000)
IPython.display.Audio(data=audio, rate=16000)

📦 Installation

git clone https://github.com/AMAAI-Lab/mustango
cd mustango
pip install -r requirements.txt
cd diffusers
pip install -e .

📚 Documentation

Datasets

The MusicBench dataset contains 52k music fragments with a rich music - specific text caption.

Subjective Evaluation by Expert Listeners

Training

We use the accelerate package from Hugging Face for multi - gpu training. Run accelerate config from terminal and set up your run configuration by answering the questions asked.

You can now train Mustango on the MusicBench dataset using:

accelerate launch train.py \
--text_encoder_name="google/flan-t5-large" \
--scheduler_name="stabilityai/stable-diffusion-2-1" \
--unet_model_config="configs/diffusion_model_config_munet.json" \
--model_type Mustango --freeze_text_encoder --uncondition_all --uncondition_single \
--drop_sentences --random_pick_text_column --snr_gamma 5 \

The --model_type flag allows to choose either Mustango, or Tango to be trained with the same code. However, do note that you also need to change --unet_model_config to the relevant config: diffusion_model_config_munet for Mustango; diffusion_model_config for Tango.

The arguments --uncondition_all, --uncondition_single, --drop_sentences control the dropout functions as per Section 5.2 in our paper. The argument of --random_pick_text_column allows to randomly pick between two input text prompts - in the case of MusicBench, we pick between ChatGPT rephrased captions and original enhanced MusicCaps prompts, as depicted in Figure 1 in our paper.

Recommended training time from scratch on MusicBench is at least 40 epochs.

Model Zoo

We have released the following models:

• Mustango Pretrained: https://huggingface.co/declare-lab/mustango - pretrained
• Mustango: https://huggingface.co/declare-lab/mustango

📄 License

This project is licensed under the Apache 2.0 license.

📚 Citation

Please consider citing the following article if you found our work useful:

@misc{melechovsky2023mustango,
      title={Mustango: Toward Controllable Text-to-Music Generation}, 
      author={Jan Melechovsky and Zixun Guo and Deepanway Ghosal and Navonil Majumder and Dorien Herremans and Soujanya Poria},
      year={2023},
      eprint={2311.08355},
      archivePrefix={arXiv},
}

Useful Links

• Demo
• Model
• Website and Examples
• Paper
• Dataset
• Hugging Face Spaces

🔥 Live demo available on Replicate and HuggingFace.