DeepFilterNet vs REUSE Tool

DeepFilterNet is a free, open-source framework for speech enhancement on full-band 48 kHz audio, using deep filtering. Its command-line tool suppresses noise in WAV files, with 48 kHz as its only supported sampling rate. A LADSPA plugin provides real-time noise suppression and can be used with PipeWire filter chains to create a virtual microphone or audio output, including for VoIP apps such as Zoom or Discord. The plugin's minimum latency is 20 ms from STFT processing, plus any delay added by the LADSPA host. The Rust command-line tool defaults to DeepFilterNet2; the Python interface documents DeepFilterNet and DeepFilterNet2. An optional post-filter may slightly over-attenuate very noisy sections. The framework supports Linux, macOS and Windows, though training is tested only under Linux. The Python package installs as deepfilternet, and an optional train extra adds data-loading functionality for Linux training. Code is available under either the MIT License or Apache License 2.0.

REUSE Tool helps software projects keep their own Free Software licensing information complete and machine-readable. Its command-line tools can download full license texts, add copyright and license details to file headers, and lint projects for problems. It can generate a software bill of materials with a command, while the REUSE API displays ongoing compliance status and can provide a badge and JSON output. Teams can run checks in CI/CD workflows such as Drone, Woodpecker CI, Forgejo Actions, GitHub Actions and Docker-based setups. A pre-commit hook can run linting at each Git commit and stop the commit if it reports an error. Installation options include Debian and Fedora packages, pipx, pip and source; Python 3.10 or newer is required. The tool is free, needs no registration and can be used offline. Its scope does not include checking whether a project complies with the licenses of its dependencies. The source code is GPL-3.0-or-later, documentation is CC-BY-SA-4.0, and some configuration and data files are CC0-1.0.