carlosholivan / musicaiz

A python framework for symbolic music generation, evaluation and analysis

I'm Carlos, a PhD student in Machine Learning and Music

Statistical data

Languages and Framewroks:

Others (basic user):

Contact info:

musicaiz's Issues

load midi error 'IndexError: list assignment index out of range'

I get this error 'IndexError: list assignment index out of range'
When I try to load this midi file: http://bachcentral.com/chorales/06Christus.mid
I call this method
midi = musicaiz.loaders.Musa(
file=midi_path
)

midi_path is correct and refers to my local file.
can you figure out the problem? thanks

Installation errors with pip

Hi Carlos,

Thanks for the great library! I was trying today to install it with the following command:

!pip install musicaiz

And I got this error:

Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting musicaiz
  Using cached musicaiz-0.1.1.tar.gz (143 kB)
  Installing build dependencies ... done
  error: subprocess-exited-with-error
  
  × Getting requirements to build wheel did not run successfully.
  │ exit code: 1
  ╰─> See above for output.
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  Getting requirements to build wheel ... error
error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.

I am using Google Colab. I had the same problem if I try to clone it and then run pip install -e .

Best regards,

Juan Carlos

Problems importing MMMTokenizerArguments

Hi,

I was trying to use the examples of the README file. Howevere, I am having this problem:

from musicaiz.tokenizers import MMMTokenizer, MMMTokenizerArguments

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
[<ipython-input-8-0bffbe238ff0>](https://localhost:8080/#) in <module>
----> 1 from musicaiz.tokenizers import MMMTokenizer, MMMTokenizerArguments
      2 from musicaiz.datasets import JSBChorales

ImportError: cannot import name 'MMMTokenizerArguments' from 'musicaiz.tokenizers' (/usr/local/lib/python3.8/dist-packages/musicaiz/tokenizers/__init__.py)

---------------------------------------------------------------------------
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the
"Open Examples" button below.
---------------------------------------------------------------------------

New export format - the one Musescore 4 introduced

I wonder if in addition to the MIDI export/conversion also the new format Musescore 4 introduced could be supported?

This new format shall completely mitigate all the shortcomings MIDI has. See the video which contains example recordings of the differences. It is huge.

Thanks!

Datasets create empty samples

Hi Carlos,

I created a dataset using Musicaiz. I used the provided code:

from musicaiz.tokenizers import MMMTokenizer, MMMTokenizerArguments
from musicaiz.datasets import JSBChorales

# Tokenize a dataset in musicaiz
output_path = "./BachChorales_4Bar_128"

args = MMMTokenizerArguments(
    prev_tokens="",
    windowing=True,
    time_unit="HUNDRED_TWENTY_EIGHT",
    num_programs=None,
    shuffle_tracks=True,
    track_density=True,
    window_size=4,
    hop_length=2,
    time_sig=False,
    velocity=False,
)
dataset = JSBChorales()
dataset.tokenize(
    dataset_path="/path/JSBChoralesDataset",
    output_path=output_path,
    output_file="token-sequences",
    args=args,
    tokenize_split="all"
)

When reviewing the dataset, I noticed that there were some empty lines:

You can also check it out in Hugging Face.

I am unsure about why this is happening. I could not install the repo locally now to debug it, but maybe it has to do with the mmm tokenizer? Line 174:

tokens += "\n".

I am happy to create a PR if I find the problem. But I wanted to create the issue first 😃

Thanks again for the great library.