Omnizart

Omnizart: A General Toolbox for Automatic Music Transcription - Published in JOSS (2021)

https://github.com/music-and-culture-technology-lab/omnizart

Science Score: 95.0%

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

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 12 DOI reference(s) in README and JOSS metadata
  • Academic publication links
    Links to: joss.theoj.org, zenodo.org
  • Committers with academic emails
    3 of 14 committers (21.4%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
    Published in Journal of Open Source Software

Keywords

beat-tracking chord drum-transcription music-information-retrieval music-transcription vocal

Scientific Fields

Artificial Intelligence and Machine Learning Computer Science - 71% confidence
Mathematics Computer Science - 63% confidence
Last synced: 4 months ago · JSON representation

Repository

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

Basic Info
Statistics
  • Stars: 1,728
  • Watchers: 26
  • Forks: 120
  • Open Issues: 26
  • Releases: 14
Topics
beat-tracking chord drum-transcription music-information-retrieval music-transcription vocal
Created over 5 years ago · Last pushed over 1 year ago
Metadata Files
Readme Changelog Contributing License

README.md

OMNIZART

build docs PyPI version PyPI - License PyPI - Downloads Docker Pulls

DOI DOI

Omnizart is a Python library that aims for democratizing automatic music transcription. Given polyphonic music, it is able to transcribe pitched instruments, vocal melody, chords, drum events, and beat. This is powered by the research outcomes from Music and Culture Technology (MCT) Lab. The paper has been published to Journal of Open Source Software (JOSS).

Transcribe your favorite songs now in Colab Open In Colab or Replicate

Quick start

Visit the complete document for detailed guidance.

Pip

``` bash

Install omnizart

pip install omnizart

Download the checkpoints

omnizart download-checkpoints

Transcribe your songs

omnizart drum transcribe omnizart chord transcribe omnizart music transcribe ```

Docker

bash docker pull mctlab/omnizart:latest docker run -it mctlab/omnizart:latest bash

Conda (install from source)

``` bash git clone https://github.com/Music-and-Culture-Technology-Lab/omnizart cd omnizart

Create a new conda environment

conda env create -f environment.yml conda activate omnizart

Install omnizart

pip install . omnizart download-checkpoints ```

Supported applications

| Application | Transcription | Training | Evaluation | Description | |------------------|--------------------|--------------------|------------|--------------------------------------------------| | music | :heavycheckmark: | :heavycheckmark: | | Transcribe musical notes of pitched instruments. | | drum | :heavycheckmark: | :interrobang: | | Transcribe events of percussive instruments. | | vocal | :heavycheckmark: | :heavycheckmark: | | Transcribe note-level vocal melody. | | vocal-contour | :heavycheckmark: | :heavycheckmark: | | Transcribe frame-level vocal melody (F0). | | chord | :heavycheckmark: | :heavycheckmark: | | Transcribe chord progressions. | | beat | :heavycheckmark: | :heavycheckmark: | | Transcribe beat position. |

NOTES The current implementation for the drum model has unknown bugs, preventing loss convergence when training from scratch. Fortunately, you can still enjoy drum transcription with the provided checkpoints.

Compatibility Issue

Currently, Omnizart is incompatible for ARM-based MacOS system due to the underlying dependencies. More details can be found in the issue #38.

Citation

If you use this software in your work, please cite:

@article{Wu2021, doi = {10.21105/joss.03391}, url = {https://doi.org/10.21105/joss.03391}, year = {2021}, publisher = {The Open Journal}, volume = {6}, number = {68}, pages = {3391}, author = {Yu-Te Wu and Yin-Jyun Luo and Tsung-Ping Chen and I-Chieh Wei and Jui-Yang Hsu and Yi-Chin Chuang and Li Su}, title = {Omnizart: A General Toolbox for Automatic Music Transcription}, journal = {Journal of Open Source Software} }

Owner

  • Name: MCTLab
  • Login: Music-and-Culture-Technology-Lab
  • Kind: organization
  • Location: Taiwan

JOSS Publication

Omnizart: A General Toolbox for Automatic Music Transcription
Published
December 10, 2021
Volume 6, Issue 68, Page 3391
Authors
Yu-Te Wu
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Yin-Jyun Luo
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Tsung-Ping Chen
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
I-Chieh Wei
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Jui-Yang Hsu
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Yi-Chin Chuang
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Li Su
Music and Culture Technology Lab, Institute of Information Science, Academia Sinica, Taipei, Taiwan
Editor
Fabian-Robert Stöter ORCID
Tags
automatic music transcription music information retrieval audio signal processing artificial intelligence

GitHub Events

Total
  • Watch event: 99
  • Issue comment event: 3
  • Fork event: 22
Last Year
  • Watch event: 99
  • Issue comment event: 3
  • Fork event: 22

Committers

Last synced: 5 months ago

All Time
  • Total Commits: 536
  • Total Committers: 14
  • Avg Commits per committer: 38.286
  • Development Distribution Score (DDS): 0.177
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
BreezeWhite f****r@g****m 441
yjluo y****5@g****m 26
unknown s****u@b****m 22
BreezeWhite m****0@t****o 17
Felipe S. S. Schneider s****5@g****m 7
Yin-Jyun Luo j****o@Y****l 7
derek.wu d****u@t****w 6
Fabian-Robert Stöter m****l@f****m 2
Daniel S. Katz d****z@i****g 2
Chin-Yun Yu c****u@q****k 2
Vladislav Doster m****r@g****m 1
Chenxi 7****W 1
BreezeWhite w****o@p****e 1
Andrew Olney a****y@m****u 1
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: 4 months ago

All Time
  • Total issues: 76
  • Total pull requests: 37
  • Average time to close issues: 2 months
  • Average time to close pull requests: 17 days
  • Total issue authors: 50
  • Total pull request authors: 13
  • Average comments per issue: 2.79
  • Average comments per pull request: 0.73
  • Merged pull requests: 28
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 2.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • hagenw (11)
  • keunwoochoi (5)
  • schneiderfelipe (4)
  • MohammedMehdiTBER (4)
  • FawzanIF (2)
  • dianxin556 (2)
  • Alx-AI (2)
  • R-N (2)
  • krigeta (2)
  • PSCM (2)
  • liufeigit (1)
  • defoishugo (1)
  • stunlocked1 (1)
  • ycollet (1)
  • faroit (1)
Pull Request Authors
  • BreezeWhite (16)
  • schneiderfelipe (5)
  • yoyololicon (3)
  • ikitcheng (2)
  • Tsung-Ping (2)
  • gudgud96 (2)
  • yjlolo (2)
  • vladdoster (2)
  • aolney (1)
  • chenxwh (1)
  • e7mac (1)
  • faroit (1)
  • danielskatz (1)
Top Labels
Issue Labels
bug (5) colab (5) installation (5) enhancement (3) conda (2)
Pull Request Labels

Dependencies

poetry.lock pypi
  • 139 dependencies
pyproject.toml pypi
  • black ^19.10b0 develop
  • flake8 ^3.8.3 develop
  • numpydoc ^1.1.0 develop
  • pylint ^2.5.3 develop
  • pytest ^5.2 develop
  • pytest-cov ^2.10.1 develop
  • pytest-mock ^3.3.1 develop
  • sphinx-click ^2.5.0 develop
  • sphinx-press-theme ^0.5.1 develop
  • sphinxcontrib-bibtex ^1.0.0 develop
  • yapf ^0.30.0 develop
  • click ^7.1.2
  • jsonschema ^3.2.0
  • librosa ^0.8.0
  • madmom ^0.16.1
  • mir_eval ^0.6
  • pillow ^8.3.2
  • pretty_midi ^0.2.9
  • pyfluidsynth ^1.2.5
  • python >=3.6.1,<3.9
  • pyyaml ^5.3.1
  • spleeter ^2.3.0
  • tensorflow 2.5.0
  • tqdm ^4.49.0
  • urllib3 1.26.4
  • vamp ^1.1.0
requirements.txt pypi
  • absl-py ==0.15.0
  • appdirs ==1.4.4
  • astunparse ==1.6.3
  • async-generator ==1.10
  • attrs ==21.2.0
  • audioread ==2.1.9
  • cached-property ==1.5.2
  • cachetools ==4.2.4
  • certifi ==2021.10.8
  • cffi ==1.15.0
  • charset-normalizer ==2.0.7
  • click ==7.1.2
  • colorama ==0.4.4
  • contextvars ==2.4
  • cython ==0.29.24
  • dataclasses ==0.8
  • decorator ==5.1.0
  • ffmpeg-python ==0.2.0
  • flatbuffers ==1.12
  • future ==0.18.2
  • gast ==0.4.0
  • google-auth ==2.3.3
  • google-auth-oauthlib ==0.4.6
  • google-pasta ==0.2.0
  • grpcio ==1.34.1
  • h11 ==0.12.0
  • h2 ==4.1.0
  • h5py ==3.1.0
  • hpack ==4.0.0
  • httpcore ==0.13.3
  • httpx ==0.19.0
  • hyperframe ==6.0.1
  • idna ==3.3
  • immutables ==0.16
  • importlib-metadata ==3.10.1
  • importlib-resources ==4.1.1
  • joblib ==1.1.0
  • jsonschema ==3.2.0
  • keras-nightly ==2.5.0.dev2021032900
  • keras-preprocessing ==1.1.2
  • librosa ==0.8.0
  • llvmlite ==0.36.0
  • madmom ==0.16.1
  • markdown ==3.3.4
  • mido ==1.2.10
  • mir-eval ==0.6
  • norbert ==0.2.1
  • numba ==0.53.1
  • numpy ==1.19.5
  • oauthlib ==3.1.1
  • opt-einsum ==3.3.0
  • packaging ==21.2
  • pandas ==1.1.5
  • pillow ==8.4.0
  • pooch ==1.5.2
  • pretty-midi ==0.2.9
  • protobuf ==3.19.1
  • pyasn1 ==0.4.8
  • pyasn1-modules ==0.2.8
  • pycparser ==2.21
  • pyfluidsynth ==1.3.0
  • pyparsing ==2.4.7
  • pyrsistent ==0.18.0
  • python-dateutil ==2.8.2
  • pytz ==2021.3
  • pyyaml ==5.4.1
  • requests ==2.26.0
  • requests-oauthlib ==1.3.0
  • resampy ==0.2.2
  • rfc3986 ==1.5.0
  • rsa ==4.7.2
  • scikit-learn ==0.24.2
  • scipy ==1.5.4
  • six ==1.15.0
  • sniffio ==1.2.0
  • soundfile ==0.10.3.post1
  • spleeter ==2.3.0
  • tensorboard ==2.7.0
  • tensorboard-data-server ==0.6.1
  • tensorboard-plugin-wit ==1.8.0
  • tensorflow ==2.5.0
  • tensorflow-estimator ==2.5.0
  • termcolor ==1.1.0
  • threadpoolctl ==3.0.0
  • tqdm ==4.62.3
  • typer ==0.3.2
  • typing-extensions ==3.7.4.3
  • urllib3 ==1.26.4
  • vamp ==1.1.0
  • werkzeug ==2.0.2
  • wrapt ==1.12.1
  • zipp ==3.6.0
.github/workflows/doc-build.yml actions
  • actions/cache v2 composite
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
.github/workflows/general.yml actions
  • actions/cache v2 composite
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
.github/workflows/publish.yml actions
  • actions/checkout v2 composite
  • actions/create-release v1 composite
  • actions/setup-python v2 composite
  • docker/login-action v1 composite
Dockerfile docker
  • tensorflow/tensorflow 2.5.0-gpu build
setup.py pypi
environment.yml conda
  • python 3.8.*