Data

Tools

Indexes

Applications

Experiments

Open Source Science

synthux

Redefining music creation with AI. Compose, produce, and innovate effortlessly.

https://github.com/synthuxai/synthux

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.7%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Redefining music creation with AI. Compose, produce, and innovate effortlessly.

Basic Info
  • Host: GitHub
  • Owner: SynthuxAI
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage: https://synthuxai.com
  • Size: 71.8 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Funding License Citation

README.md

SynthuxAI

Twitter Cover

SynthuxAI is an AI-powered music creation engine redefining how artists and creators compose, produce, and innovate. With SynthuxAI, explore endless musical possibilities and unleash your creativity effortlessly.

Follow us on Twitter for updates and inspiration.

Features

  • AI-Driven Music Generation: Compose polyphonic music and experiment with multi-track arrangements effortlessly.
  • User-Friendly Interface: Designed for creators of all skill levels, from beginners to professionals.
  • Customizable Settings: Fine-tune every aspect of your music to align with your creative vision.
  • Integration Ready: Seamlessly works with your existing music production tools.

Getting Started

Prerequisites

Make sure you have the following installed: - Python 3.8 or higher - pip or pipenv for managing dependencies

Install Dependencies

Using pipenv (recommended)

```sh

Install the dependencies

pipenv install

Activate the virtual environment

pipenv shell ```

Using pip

```sh

Install the dependencies

pip install -r requirements.txt ```

Prepare Training Data

SynthuxAI leverages training data from a variety of sources. To get started:

```sh

Download the training data

./scripts/download_data.sh

Process the training data

./scripts/process_data.sh ```

Scripts

Train a New Model

  1. Set up a new experiment: sh ./scripts/setup_exp.sh "./exp/my_experiment/" "Experiment notes here"

  2. Customize your configuration files.

  3. Train the model: sh ./scripts/run_train.sh "./exp/my_experiment/" "0"

Or run a full experiment: sh ./scripts/run_exp.sh "./exp/my_experiment/" "0"

Use Pretrained Models

  1. Download pretrained models: sh ./scripts/download_models.sh

  2. Perform inference: sh ./scripts/run_inference.sh "./exp/default/" "0"

Outputs

Generated music is stored in the following formats by default: - .npy: Raw numpy arrays - .png: Visualization of music tracks - .npz: Multi-track pianoroll files

Convert .npz to MIDI: python from pypianoroll import Multitrack m = Multitrack('./test.npz') m.write('./test.mid')

License

SynthuxAI is open-source. See the LICENSE file for details.

Contact

For inquiries or support, visit synthuxai.com or reach out on Twitter.

Owner

  • Login: SynthuxAI
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: If you use this software, please cite it using these metadata.
authors:
  - family-names: Dong
    given-names: Hao-Wen
title: MuseGAN
preferred-citation:
  type: article
  authors:
    - family-names: Dong
      given-names: Hao-Wen
    - family-names: Hsiao
      given-names: Wen-Yi
    - family-names: Yang
      given-names: Li-Chia
    - family-names: Yang
      given-names: Yi-Hsuan
  title: "MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment"
  journal: Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI)
  year: 2018
date-released: 2017-11-09
license: MIT
url: "https://salu133445.github.io/musegan/"
repository-code: "https://github.com/salu133445/musegan"

GitHub Events

Total
  • Push event: 1
  • Create event: 3
Last Year
  • Push event: 1
  • Create event: 3

Dependencies

Pipfile pypi
  • black * develop
  • flake8 * develop
  • flake8-bugbear * develop
  • flake8-docstrings * develop
  • pylint * develop
  • Markdown ==2.6.11
  • Pillow ==6.2.0
  • PyYAML ==3.13
  • SharedArray ==3.0.0
  • Werkzeug ==0.15.3
  • absl-py ==0.4.1
  • astor ==0.7.1
  • gast ==0.2.0
  • grpcio ==1.14.2
  • imageio ==2.3.0
  • mido ==1.2.8
  • numpy ==1.14.5
  • pretty_midi ==0.2.8
  • protobuf ==3.6.1
  • pypianoroll ==0.4.6
  • scipy ==1.1.0
  • six ==1.11.0
  • tensorboard ==1.10.0
  • tensorflow-gpu ==1.10.1
  • termcolor ==1.1.0
requirements.txt pypi
  • Markdown ==2.6.11
  • Pillow ==5.2.0
  • PyYAML ==3.13
  • SharedArray ==3.0.0
  • Werkzeug ==0.14.1
  • absl-py ==0.4.1
  • astor ==0.7.1
  • gast ==0.2.0
  • grpcio ==1.14.2
  • imageio ==2.3.0
  • mido ==1.2.8
  • numpy ==1.14.5
  • pretty-midi ==0.2.8
  • protobuf ==3.6.1
  • pypianoroll ==0.4.6
  • scipy ==1.1.0
  • setuptools ==39.1.0
  • six ==1.11.0
  • tensorboard ==1.10.0
  • tensorflow-gpu ==1.10.1
  • termcolor ==1.1.0