Metadata-Version: 2.1
Name: rt-pie
Version: 0.1.15
Summary: Real Rime PItch Estimator
Home-page: https://github.com/wolfisberg/rt-pie
Author: Kaspar Wolfisberg
Requires-Python: >=3.7,<3.8
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Requires-Dist: librosa (>=0.8.0,<0.9.0)
Requires-Dist: matplotlib (>=3.2,<3.3)
Requires-Dist: mir_eval (>=0.6,<0.7)
Requires-Dist: numpy (>=1.19,<1.20)
Requires-Dist: sounddevice (>=0.4.1,<0.5.0)
Requires-Dist: tensorflow (>=2.4.1,<3.0.0)
Project-URL: Repository, https://github.com/wolfisberg/rt-pie
Description-Content-Type: text/markdown

# RT PIE<br>Real Time PItch Estimator

[**pypi link**](https://pypi.org/project/rt-pie)

To demonstrate the predictions of the various models used throughout the thesis, a simple demonstration application was developed.
The demonstrator app is a python command line application. It comes pre-packaged with various deep learning models used in this thesis. The CREPE models as well as the DEEPF0_256 models are not available through this package, due to the 100MB package limitation on pypi.

The demonstrator app takes a WAVE audio file as input and saves a spectrogram including the pitch predictions to disk under the name `spectrogram.png`.

## Installation

    pip install rt_pie

## Usage

    rt_pie --help

#### Authors
Kaspar Wolfisberg<br>
Luca Di Lanzo


