API Reference

A core package for acoustic communication research in Python.

This section documents the vocalpy API.

Data types

Data types for acoustic communication data.

Sound(data, samplerate)	Class that represents a sound.
Spectrogram(data, frequencies, times)	Class that represents a spectrogram.
Annotation(data, path)	Class that represents annotation data.
Segments(start_inds, lengths, samplerate[, ...])	Class that represents a set of line segments returned by a segmenting algorithm.
Features(data)	Class that represents features extracted from sound.

Classes for Pipelines

Classes for common steps in pipelines.

Segmenter([callback, params])	Class that represents the segmenting step in a pipeline.
SpectrogramMaker([callback, params])	Class that represents the step in a pipeline that makes spectrograms from audio.
FeatureExtractor(callback[, params])	Class that represents the step in a pipeline that extracts features.
Params()	A class to represent the parameters used with a method, that can be unpacked with the ** operator.

Signal processing

signal	Functions for signal processing.
segment	Algorithms for segmentation.
spectral	Spectral representations.

spectrogram(sound[, n_fft, hop_length, ...])

Get a spectrogram from audio.

Feature Extraction

feature

Feature extraction

Metrics

metrics	Metrics for methods and models in acoustic communication.
metrics.segmentation	Metrics for segmentation algorithms.
metrics.segmentation.ir	Metrics for segmentation adapted from information retrieval.

Visualization

plot	Module for plotting and visualizations.

Example Data

example(name[, return_path])

Get an example from vocalpy.examples.

examples

Example data built into VocalPy.

examples.ExampleData(**kwargs)

A dict-like container for example data.

Other

constants	Constants used throughout vocalpy.
validators	Functions for input validation.
paths	Functions for working with paths.