README.md

PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective

tl;dr: Fast and powerful pitch estimator based on machine learning

This code is the implementation of the PESTO paper, that has been accepted at ISMIR 2023.

Disclaimer: This repository contains minimal code and should be used for inference only. If you want full implementation details or want to use PESTO for research purposes, take a look at this repository (coming soon!).

Installation

pip install pesto-pitch

That's it!

Dependencies

This repository is implemented in PyTorch and has the following additional dependencies:

• numpy for basic I/O operations
• torchaudio for audio loading
• matplotlib for exporting pitch predictions as images (optional)

Usage

Command-line interface

This package includes a CLI as well as pretrained models. To use it, type in a terminal:

pesto my_file.wav

or

python -m pesto my_file.wav

Output formats

The output format can be specified with option -e/--export_format. By default, the predicted pitch is saved in a .csv file that looks like this:

time,frequency,confidence
0.00,185.616,0.907112
0.01,186.764,0.844488
0.02,188.356,0.798015
0.03,190.610,0.746729
0.04,192.952,0.771268
0.05,195.191,0.859440
0.06,196.541,0.864447
0.07,197.809,0.827441
0.08,199.678,0.775208
...

This structure is voluntarily the same as in CREPE repo for easy comparison between both methods.