Koogu

A python package for developing and using Machine Learning (ML) solutions in Animal Bioacoustics.

Koogu (ಕೂಗು; /ko͞ogu/) is a word in the Kannada language, meaning "call" (used as a noun) or "to call" (used as a verb).

The package offers tools for -

• preparing audio (pre-process and transform) to form inputs to ML models,
• training ML models,
• assessing their performance, and
• using trained ML models for automating analyses of large datasets.

Installation

Koogu can be installed, via PyPI, as follows

pip install koogu

Dependencies

TensorFlow

koogu uses TensorFlow as backend ML framework. Please ensure that either a CPU or a GPU version of TensorFlow is installed prior to installing koogu.

SoundFile, audioread, resampy

koogu uses these packages for handling audio files. These dependencies will be automatically installed when installing koogu.

Others

Besides TensorFlow, all other dependencies will be automatically installed.

How to use Koogu

Koogu offers tools for ML development from the simplest of bioacoustics applications to more complex scenarios. All stages of the workflow (input preparation, training, inference and performance assessment) can be performed independently. An overview of the functionalities is presented in this quick-start guide.

Technical API documentation is available here.