asteroid-filterbanks

What it is and what it does

Asteroid Filterbanks is a PyTorch-based library that provides filterbank implementations for audio processing. It is part of the larger Asteroid toolkit for audio source separation research and offers modular filterbank components that researchers can use to decompose audio signals into frequency representations suitable for machine learning models.

The package depends on NumPy, PyTorch, and typing-extensions, making it a lightweight addition to existing audio processing pipelines. It is designed for researchers working on audio source separation and related signal processing tasks, though the project is no longer actively maintained—the last release was in April 2021 and there have been no commits since early 2025.

Use it for:

• Building audio source separation models that need learnable or fixed filterbank layers in PyTorch.
• Extracting time-frequency representations from raw audio for downstream machine learning tasks.
• Prototyping audio signal processing pipelines that require modular filterbank components.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides PyTorch-based filterbank implementations for audio signal processing, particularly designed for audio source separation tasks.

Yes, if you are working with audio source separation or signal processing in PyTorch and need stable filterbank implementations. The low install friction and permissive MIT license make it straightforward to adopt. However, be aware that the project is dormant—no active maintenance or updates are expected, so compatibility with very recent PyTorch or Python versions is not guaranteed. Suitable for research or production use where the filterbank API is stable enough for your needs.

Install

asteroid-filterbanks on PyPI

pip install asteroid-filterbanks

uv add asteroid-filterbanks

poetry add asteroid-filterbanks

Installing asteroid-filterbanks

Before you install

Low install friction with a pure-Python wheel distribution. Maintenance is dormant—last release was 2021-04-09 and no commits since 2025-01-12, so expect no active bug fixes or updates.

License in practice

MIT license is permissive; you can use this package freely in commercial and private projects with minimal restrictions.

Quickstart

pip install asteroid-filterbanks

import torch
from asteroid_filterbanks import Filterbank

fb = Filterbank()

Requires PyTorch (torch) and NumPy installed; requires Python 3.6 or later.

Verify before relying

• Whether filterbank implementations remain compatible with current PyTorch versions despite dormant maintenance status.
• Whether the package works reliably with Python versions beyond 3.8, given classifiers only declare support through 3.8.
• Specific filterbank parameters and configuration options available in the API.

Package facts

Evidence: asteroid_filterbanks-0.4.0-py3-none-any.whl

Tags

More Artificial Intelligence packages