xavierk/voculinux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity
Files
3e78a9bc4e13d777489e398f9b2eb4d88ac98427
voculinux/pyproject.toml
T
Jatin K MalikGitHubSbenazar
 3f5a5effff feat(vad): add Silero VAD and drop silence-only buffers (#447) 
* feat(vad): replace amplitude-based VAD with Silero neural network

Replace the simple amplitude threshold VAD with Silero VAD, a lightweight
neural network model that classifies audio as speech/non-speech. This
addresses the root cause of #302 (silence not stopping recording) and

- Add silero_vad.py wrapper using ONNX Runtime with bundled Silero v5 model
- Accumulate 512-sample chunks with 64-sample context window per official API
- Map existing vad_sensitivity (1-5) to Silero thresholds (0.8-0.3)
- Use max() across sub-chunks to avoid missing speech onsets
- Fall back to amplitude VAD when onnxruntime is unavailable
- Add onnxruntime as optional dependency (pip install vocalinux[vad])

Closes #344

* address review: add tests, LICENSE, logging, validation fixes

- Add unit tests for SileroVAD (process, reset, fallback, sensitivity mapping)
- Add MIT LICENSE for bundled Silero VAD model in data/
- Log which VAD backend is active on init
- Validate chunk length in SileroVAD.process()
- Skip is_speech check until a full Silero chunk is processed
- Add thread safety note to SileroVAD docstring
- Document resampling rate effect on VAD resolution
- Comment explaining why load_silero_vad() catches broad Exception

* address review: bundle license, document [vad] extra, surface backend in UI

- Pack data/LICENSE into the wheel (pyproject package-data) so attribution
  travels with the model
- README: short note on enabling neural VAD via vocalinux[vad]
- Settings: VAD Sensitivity row subtitle shows the active backend; if
  onnxruntime is missing, an info-row beneath the group spells out the
  install command and the restart requirement
- silero_vad.is_silero_available() probes onnxruntime + model presence
  w/o instantiating an InferenceSession
- CI installs .[dev,vad] so Silero paths get exercised
- Integration test for _record_audio Silero branch (mocked pyaudio +
  scripted SileroVAD), covering silence flush, speech reset, and
  sensitivity threshold mapping at sens=1 vs sens=5
- Tests no longer skip when other modules globally mock numpy: pop the
  top-level numpy ref so a fresh import gives the real package, and
  swap sys.modules["numpy"] inside the _record_audio call so the lazy
  import inside the function picks up real numpy too

* fix(vad): drop silence-only recording buffers

* test(vad): align stop buffer expectations

* test(vad): preserve real numpy module

* fix(install): install vad support opportunistically

* test(vad): cover recognition manager vad edges

---------

Co-authored-by: Sbenazar <127324689+Sbenazar@users.noreply.github.com>
2026-06-02 12:43:51 -07:00

171 lines
4.3 KiB
TOML
Raw Blame History

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "vocalinux"
dynamic = ["version"]
description = "A seamless voice dictation system for Linux"
readme = "README.md"
license = {text = "GPL-3.0"}
authors = [
{name = "Jatin K Malik", email = "jatinkrmalik@gmail.com"}
]
maintainers = [
{name = "Jatin K Malik", email = "jatinkrmalik@gmail.com"}
]
requires-python = ">=3.9"
keywords = [
"voice", "dictation", "speech", "recognition",
"linux", "accessibility", "voice-typing", "speech-to-text"
]
classifiers = [
"Development Status :: 4 - Beta",
"Environment :: X11 Applications :: GTK",
"Intended Audience :: End Users/Desktop",
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
"Operating System :: POSIX :: Linux",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
"Topic :: Desktop Environment :: Gnome",
"Topic :: Multimedia :: Sound/Audio :: Speech",
"Topic :: Text Processing",
"Topic :: Utilities",
]
dependencies = [
"vosk>=0.3.45",
"pywhispercpp>=1.2.0",
"pydub>=0.25.1",
"pynput>=1.7.6",
"evdev>=1.6.0; sys_platform == 'linux'",
"requests>=2.28.0",
"tqdm>=4.64.0",
"numpy>=1.22.0",
"pyaudio>=0.2.13",
"python-xlib; sys_platform == 'linux'",
"PyGObject; sys_platform == 'linux'",
"psutil>=5.9.0",
"lxml>=6.1.0",
]
[project.optional-dependencies]
whisper = [
"openai-whisper>=20231117",
"torch>=2.0.0",
"torchaudio>=2.0.0",
]
vad = [
"onnxruntime>=1.16.0",
]
dev = [
"pytest>=7.0.0",
"pytest-cov>=4.0.0",
"pytest-mock>=3.10.0",
"pytest-timeout>=2.1.0",
"black>=23.0.0",
"isort>=5.12.0",
"flake8>=6.0.0",
"pre-commit>=3.0.0",
"mypy>=1.0.0",
]
docs = [
"sphinx>=6.0.0",
"sphinx-rtd-theme>=1.2.0",
]
[project.scripts]
vocalinux = "vocalinux.main:main"
[project.gui-scripts]
vocalinux-gui = "vocalinux.main:main"
[project.urls]
Homepage = "https://github.com/jatinkrmalik/vocalinux"
Documentation = "https://github.com/jatinkrmalik/vocalinux/tree/main/docs"
Repository = "https://github.com/jatinkrmalik/vocalinux"
Issues = "https://github.com/jatinkrmalik/vocalinux/issues"
Changelog = "https://github.com/jatinkrmalik/vocalinux/releases"
[tool.setuptools]
packages = ["vocalinux", "vocalinux.resources", "vocalinux.speech_recognition", "vocalinux.text_injection", "vocalinux.ui", "vocalinux.ui.keyboard_backends", "vocalinux.utils"]
package-dir = {"" = "src"}
[tool.setuptools.dynamic]
version = {attr = "vocalinux.version.__version__"}
[tool.setuptools.package-data]
"*" = ["*.svg", "*.wav", "*.onnx"]
"vocalinux" = ["resources/**/*"]
"vocalinux.speech_recognition" = ["data/*.onnx", "data/LICENSE"]
[tool.black]
line-length = 100
target-version = ['py39', 'py310', 'py311', 'py312', 'py313', 'py314']
include = '\.pyi?$'
exclude = '''
/(
\.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| venv
| _build
| buck-out
| build
| dist
| node_modules
)/
'''
[tool.isort]
profile = "black"
line_length = 100
skip_gitignore = true
skip = [".git", "venv", "node_modules", "build", "dist"]
[tool.pytest.ini_options]
minversion = "7.0"
addopts = "-ra -q --strict-markers --timeout=10 --timeout_method=thread"
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]
markers = [
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
"integration: marks tests as integration tests",
"audio: marks tests that require audio hardware",
]
[tool.coverage.run]
source = ["src"]
branch = true
omit = [
"*/tests/*",
"*/__pycache__/*",
# GTK dialog files are untestable without a real GTK environment
"*/settings_dialog.py",
"*/logging_dialog.py",
]
[tool.coverage.report]
exclude_lines = [
"pragma: no cover",
"def __repr__",
"raise NotImplementedError",
"if TYPE_CHECKING:",
"if __name__ == .__main__.:",
]
show_missing = true
[tool.mypy]
python_version = "3.9"
warn_return_any = true
warn_unused_configs = true
ignore_missing_imports = true
exclude = ["venv", "build", "dist", "node_modules"]
Reference in New Issue View Git Blame Copy Permalink