Skip to content

Releases: ericcayers-ai/Neiro

v1.2.1

Choose a tag to compare

@github-actions github-actions released this 17 Jul 15:05
c3cc5c0

Neiro v1.2.1

Desktop

Platform installers are attached below (Windows .msi/.exe, macOS .dmg,
Linux .AppImage/.deb). The desktop shell supervises a local Python
engine; neural model weights are not bundled — they download on first
use under each model's own license (see docs/models.md).

Python

pip install the attached wheel, or install from source via pyproject.toml.

Evaluation notes

Synthetic goldens always run in CI. Full MUSDB18-HQ / MAESTRO numbers
require user-provisioned datasets (NEIRO_EVAL_MUSDB, NEIRO_EVAL_MAESTRO);
see docs/evaluation.md.

Changelog

See CHANGELOG.md for the curated entry matching this tag.

What's Changed

Full Changelog: v1.2.0...v1.2.1

v1.2.0

Choose a tag to compare

@github-actions github-actions released this 17 Jul 11:20
704ddce

Neiro v1.2.0

Desktop

Platform installers are attached below (Windows .msi/.exe, macOS .dmg,
Linux .AppImage/.deb). The desktop shell supervises a local Python
engine; neural model weights are not bundled — they download on first
use under each model's own license (see docs/models.md).

Python

pip install the attached wheel, or install from source via pyproject.toml.

Evaluation notes

Synthetic goldens always run in CI. Full MUSDB18-HQ / MAESTRO numbers
require user-provisioned datasets (NEIRO_EVAL_MUSDB, NEIRO_EVAL_MAESTRO);
see docs/evaluation.md.

Changelog

See CHANGELOG.md for the curated entry matching this tag.

What's Changed

Full Changelog: v1.1.1...v1.2.0

Neiro 1.1.1 — UI navigation QOL

Choose a tag to compare

@ericcayers-ai ericcayers-ai released this 17 Jul 04:58

Neiro v1.1.1

Desktop

Platform installers are attached below (Windows .msi/.exe, macOS .dmg,
Linux .AppImage/.deb). The desktop shell supervises a local Python
engine; neural model weights are not bundled — they download on first
use under each model's own license (see docs/models.md).

Python

pip install the attached wheel, or install from source via pyproject.toml.

Evaluation notes

Synthetic goldens always run in CI. Full MUSDB18-HQ / MAESTRO numbers
require user-provisioned datasets (NEIRO_EVAL_MUSDB, NEIRO_EVAL_MAESTRO);
see docs/evaluation.md.

Changelog

See CHANGELOG.md for the curated entry matching this tag.

What's Changed

Full Changelog: v1.1.0...v1.1.1

v1.1.0

Choose a tag to compare

@github-actions github-actions released this 16 Jul 14:17

Neiro v1.1.0

Desktop

Platform installers are attached below (Windows .msi/.exe, macOS .dmg,
Linux .AppImage/.deb). The desktop shell supervises a local Python
engine; neural model weights are not bundled — they download on first
use under each model's own license (see docs/models.md).

Python

pip install the attached wheel, or install from source via pyproject.toml.

Evaluation notes

Synthetic goldens always run in CI. Full MUSDB18-HQ / MAESTRO numbers
require user-provisioned datasets (NEIRO_EVAL_MUSDB, NEIRO_EVAL_MAESTRO);
see docs/evaluation.md.

Changelog

See CHANGELOG.md for the curated entry matching this tag.

What's Changed

New Contributors

Full Changelog: v1.0.0...v1.1.0

Neiro 1.0.0

Choose a tag to compare

@ericcayers-ai ericcayers-ai released this 15 Jul 14:58

Neiro v1.0.0

Desktop

Platform installers are attached below (Windows .msi/.exe, macOS .dmg,
Linux .AppImage/.deb). The desktop shell supervises a local Python
engine; neural model weights are not bundled — they download on first
use under each model's own license (see docs/models.md).

Python

pip install the attached wheel, or install from source via pyproject.toml.

Evaluation notes

Synthetic goldens always run in CI. Full MUSDB18-HQ / MAESTRO numbers
require user-provisioned datasets (NEIRO_EVAL_MUSDB, NEIRO_EVAL_MAESTRO);
see docs/evaluation.md.

Changelog

See CHANGELOG.md for the curated entry matching this tag.

Full Changelog: v0.3.3...v1.0.0

v0.3.3

Choose a tag to compare

@github-actions github-actions released this 14 Jul 06:12

Summary

Critical fix for Windows one-click launchers: first-run pip install of the bundled wheel with [all] extras no longer collapses to a bare [all] requirement.

Fixed

  • Windows launchers (Neiro UI.bat / Neiro CLI.bat): install via %%~ff[all] inside the for loop (absolute path). %NEIRO_WHL% was expanded at parse time inside an if block and was empty.

Changed

  • Unix launchers use an absolute path ($PWD/wheels/...) before pip install …[all].
  • Release zip packs only the current-version wheel from dist/.

Assets

  • Neiro-0.3.3.zip — one-click launcher bundle (use this on Windows/macOS/Linux)
  • Wheel / sdist — for pip install

See CHANGELOG for details.

v0.3.2

Choose a tag to compare

@github-actions github-actions released this 13 Jul 14:38

Full Changelog: v0.3.1...v0.3.2

v0.3.1

Choose a tag to compare

@github-actions github-actions released this 13 Jul 12:23

Full Changelog: v0.3.0...v0.3.1

v0.3.0

Choose a tag to compare

@github-actions github-actions released this 13 Jul 10:25

Full Changelog: v0.2.0...v0.3.0

v0.2.0 — Ensembles, restoration, transcription, audio editor

Choose a tag to compare

@ericcayers-ai ericcayers-ai released this 12 Jul 08:21

A large expansion across every phase of roadmap.md, plus a full repository-health pass. Everything is tested (74 tests, ~84% coverage) and runs with no model downloads.

Try it

pip install -e .
neiro ui                                 # local interface (127.0.0.1)
neiro separate song.wav --preset vocals-ensemble
neiro transcribe song.wav --out song.mid
neiro enhance old.wav                    # auto-repair from analysis

New in this release

Separation — ensemble engine with weighted complex-spectrogram fusion (mean/median/max/min) and test-time augmentation; ensembles are themselves manifests. New vocals-ensemble preset.

Restoration — de-clip, mains-hum removal, spectral-gate denoise, normalize — applied automatically as conditioning chains from detected conditions, or on demand via neiro enhance.

Transcription — audio → MIDI with YIN pitch tracking, a timeline compiler doing reversible groove-preserving quantization (grid for notation, micro-offsets for feel), and a dependency-free Standard MIDI File writer. Auto-splits dense mixes first. Optional polyphonic Basic Pitch backend.

Audio editor — a basic waveform + spectrogram editor (trim, delete, silence, fade, gain, normalize, reverse) with non-destructive undo, in the browser.

Local interface — drag-and-drop Simple mode on 127.0.0.1: analysis card, separation with a stem mixer, transcription with a synced piano-roll, restoration, and the editor. Path-traversal protected; nothing leaves the machine.

Analysis — added mains-hum (50/60 Hz) and echo/delay detection.

Repository health

  • CI across Ubuntu/macOS/Windows × Python 3.10–3.12 with lint, format, and coverage; tag-triggered release workflow.
  • Ruff lint + format, coverage config, py.typed.
  • Docs: architecture, adding models, performance + a runnable benchmark.
  • CONTRIBUTING, CODE_OF_CONDUCT, SECURITY, issue/PR templates, Dependabot.

Licensing

Engine is MIT. Model weights carry their own licenses — each manifest records its terms and neiro models shows them.

Full changelog: CHANGELOG.md

🤖 Generated with Claude Code

Full Changelog: v0.1.0...v0.2.0