OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Asteroid

Asteroid is an open-source Python library built on PyTorch for audio source-separation research, with tools and recipes for experimentation across supported datasets.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Asteroid — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Asteroid when an audio research workflow needs a PyTorch library with dataset support, model recipes and tutorials for source separation or related speech tasks.

Who it is for

  • Researchers experimenting with audio source-separation architectures and methods.
  • Python developers building speech-separation or speech-enhancement experiments with PyTorch.

Documented uses

  • Develop and compare audio source-separation experiments using supported datasets and architectures.
  • Follow provided recipes to reproduce selected research approaches.
  • Use tutorials covering API concepts, filterbanks, permutation-invariant training and large WAV processing.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. Installation instructions include pip and conda options.

  • Running recipes can require packages beyond the core installation; the README points to a requirements file.
  • The repository lists specific supported datasets and example recipes, so check those against the intended experiment.
  • The project provides tutorials for both library concepts and processing large WAV files.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare and start a documented recipe

Install the additional recipe requirements and invoke the WHAM ConvTasNet recipe.

Before you start

  • A cloned Asteroid repository
  • A Python environment with pip

Steps

  1. From the repository directory, run the command below.

    Documented command
    pip install -r requirements.txt

  2. Change to egs/wham/ConvTasNet.

  3. Run . ./run.sh.

Expected outcome

The documented recipe script is invoked after installing its listed requirements.

Guide limitations

  • The README notes that recipes may require additional packages.
  • The documented commands do not specify dataset preparation or guarantee successful execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
asteroid-team/asteroid · Official homepage title · retained in its source language
How we review sourcesSuggest a correction