Midify is a command line tool for converting audio data in MIDI data identifying notes positions and frequencies.
Installation
Inside a virtualenv run
pip install midify
Usage
The simplest usage from the cli:
midify input.wav --output output.mid
You can also use it programatically from python or a jupyter notebook:
import scipy
from midify import midify
rate,data = scipy.io.wavfile.read("input.wav")
mf = midify(data=data,rate=rate)
waveform = mf.fluidsynth(fs=44100)
IPython.display.Audio(waveform, rate=44100)
Algorithm
The algorithm consists of two steps; first we use scipy.signal.find_peaks to find the beggining of each note; after that the program uses scipy FFT to find the first peak in the frequency spectrum which we assume is the root harmonic (the played note).
Acknowledgments
Made with Love by Daniel Santana
Release files for midify 0.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| midify-0.3.2.tar.gz | 4.0 kB | Details |
Release files / midify-0.3.2.tar.gz
| Download URL | midify-0.3.2.tar.gz |
|---|---|
| Size | 4.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
557c33adaa17028504482e969238cba2e9486b135a975129011607000be946d6
|
|
BLAKE2b-256 checksum How to use checksums |
4bab4137e2de1298f623ce8daece98bab9075d5b7b2ddeab34e1216e02770a37
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.10
|