Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/carlosholivan/musicaiz
A python framework for symbolic music generation, evaluation and analysis
https://github.com/carlosholivan/musicaiz
audio deep-learning machine-learning mir music music-generation music-information-retrieval python symbolic
Last synced: about 1 month ago
JSON representation
A python framework for symbolic music generation, evaluation and analysis
- Host: GitHub
- URL: https://github.com/carlosholivan/musicaiz
- Owner: carlosholivan
- License: agpl-3.0
- Created: 2022-07-15T11:03:04.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-06-15T01:37:05.000Z (over 1 year ago)
- Last Synced: 2024-07-07T09:47:39.858Z (2 months ago)
- Topics: audio, deep-learning, machine-learning, mir, music, music-generation, music-information-retrieval, python, symbolic
- Language: Python
- Homepage: https://carlosholivan.github.io/musicaiz
- Size: 5.36 MB
- Stars: 157
- Watchers: 5
- Forks: 16
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
- Citation: CITATION.cff
- Authors: AUTHORS.md
Awesome Lists containing this project
- project-awesome - carlosholivan/musicaiz - A python framework for symbolic music generation, evaluation and analysis (Python)
README
# MUSICAIZ
A Python library for symbolic music generation, analysis and visualization.
Published in SoftwareX 2023.
CI
Paper
PyPI
Activity
QA
Code
[See the docs](https://carlosholivan.github.io/musicaiz)
The modules contained in this library are:
- [Loaders](musicaiz/loaders.py)
contains the basic initialization to import files.
````python
from musicaiz.loaders import Musa
midi = Musa(
file="my_midifile.mid"
)
````
- [Structure](musicaiz/structure/)
contains the structure elements in music (instruments, bars and notes).
````python
# Define a Note object
from musicaiz.structure import Note
note = Note(
pitch=12,
start=0.0,
end=1.0,
velocity=75,
bpm=120,
resolution=96
)
````
- [Harmony](musicaiz/harmony/)
contains the harmonic elements in music (intervals, chords and keys).
````python
from musicaiz.structure import Chords, Tonality
# Initialize a chord by its notation
chord_name = "Cm7b5"
chord = Chord(chord_name)
# get the notes in the chord
chord.get_notes(inversion=0)
# Initialize Tonality
tonality = Tonality.E_MINOR
# get different scales
tonality.natural
tonality.harmonic
tonality.melodic
# get the notes in a scale
tonality.scale_notes("NATURAL")
# get a chord from a scale degree
Tonality.get_chord_from_degree(
tonality="E_MINOR",
degree="V",
scale="NATURAL",
chord_type="triad",
)
````
- [Rhythm](musicaiz/rhythm/)
contains rhythmic or timing elements in music (quantization).
- [Features](musicaiz/features/)
contains classic features to analyze symbolic music data (pitch class histograms...).
- [Algorithms](musicaiz/algorithms/)
contains algorithms for chord prediction, key prediction, harmonic transposition...
- [Plotters](musicaiz/plotters/)
contains different ways of plotting music (pinorolls or scores).
````python
from musicaiz.plotters import Pianoroll, PianorollHTML
# Matplotlib
musa_obj = Musa(midi_sample)
plot = Pianoroll(musa_obj)
plot.plot_instruments(
program=[48, 45],
bar_start=0,
bar_end=4,
print_measure_data=True,
show_bar_labels=False,
show_grid=False,
show=True,
)
# Pyplot HTML
musa_obj = Musa(midi_sample)
plot = PianorollHTML(musa_obj)
plot.plot_instruments(
program=[48, 45],
bar_start=0,
bar_end=4,
show_grid=False,
show=False
)
````
- [Tokenizers](musicaiz/tokenizers/)
contains different encodings to prepare symbolic music data to train a sequence model.
````python
from musicaiz.tokenizers import MMMTokenizer, MMMTokenizerArguments
# Tokenize file
midi = "my_midifile.mid"
args = MMMTokenizerArguments(
windowing=True,
time_unit="SIXTEENTH",
num_programs=None,
shuffle_tracks=True,
track_density=False,
window_size=4,
hop_length=1,
time_sig=False,
velocity=False,
quantize=False,
tempo=True,
)
# save configs
MMMTokenizerArguments.save(args, "./")
tokenizer = MMMTokenizer(midi, args)
got = tokenizer.tokenize_file()
# get tokens analysis
my_tokens = "PIECE_START TRACK_START ..."
MMMTokenizer.get_tokens_analytics(my_tokens)
# Convert tokens to Musa objects
MMMTokenizer.tokens_to_musa(
tokens=my_tokens,
absolute_timing=True,
time_unit="SIXTEENTH",
time_sig="4/4",
resolution=96
)
# get vocabulary
MMMTokenizer.get_vocabulary(
dataset_path="apth/to/dataset/tokens",
)
````
- [Converters](musicaiz/converters/)
contains converters to other formats (JSON,...).
````python
from musicaiz.loaders import Musa
from musicaiz.loaders import musa_to_proto, proto_to_musa
# Convert a musicaiz objects in protobufs
midi = Musa(midi_sample, structure="bars")
protobuf = musa_to_proto(midi)
# Convert a protobuf to musicaiz objects
musa = proto_to_musa(protobuf)
````
- [Datasets](musicaiz/datasets/)
contains helper methods to work with MIR open-source datasets.
````python
from musicaiz.tokenizers import MMMTokenizer, MMMTokenizerArguments
from musicaiz.datasets import JSBChorales
# Tokenize a dataset in musicaiz
output_path = "path/to/store/tokens"
args = MMMTokenizerArguments(
prev_tokens="",
windowing=True,
time_unit="HUNDRED_TWENTY_EIGHT",
num_programs=None,
shuffle_tracks=True,
track_density=False,
window_size=32,
hop_length=16,
time_sig=True,
velocity=True,
)
dataset = JSBChorales()
dataset.tokenize(
dataset_path="path/to/JSB Chorales/midifiles",
output_path=output_path,
output_file="token-sequences",
args=args,
tokenize_split="all"
)
vocab = MMMTokenizer.get_vocabulary(
dataset_path=output_path
)
````
- [Models](musicaiz/models/)
contains ML models to generate symbolic music.
## License
This project is licensed under the terms of the [AGPL v3 license](LICENSE).
## Install
To install the latest stable version run: `pip install musicaiz`
To install the latest version, clone this repository and run:
`pip install -e .`
If you want to train the models in the [models](musicaiz/models/) submodule, you must install `apex`. Follow the instructions on https://github.com/NVIDIA/apex.
## Develop
### Conda dev environment
Run the following commands to create a conda env. Note that if you skip the first command, a newer python version might be installed and the package will not work.
`conda create --name python=3.9`
`conda env update -f environment.yml`
`conda activate musicaiz`
### Linting
flake8 and black
### Typing
Use mypy package to check variables tpyes:
`mypy musicaiz`
## Examples
See docs.
## Citing
If you use this software for your research, please cite:
````
@article{HERNANDEZOLIVAN2023101365,
title = {Musicaiz: A python library for symbolic music generation, analysis and visualization},
journal = {SoftwareX},
volume = {22},
pages = {101365},
year = {2023},
issn = {2352-7110},
doi = {https://doi.org/10.1016/j.softx.2023.101365},
url = {https://www.sciencedirect.com/science/article/pii/S2352711023000614},
author = {Carlos Hernandez-Olivan and Jose R. Beltran},
}
````
## Contributing
Musicaiz software can be extended in different ways, see some example in [TODOs](TODOs.md). If you want to contribute, please follow the guidelines in [Develop](##Develop)