Files
voculinux/pyproject.toml
T
Jatin K MalikandGitHub 1dc1d44665 feat: Alpha Launch v0.2.0 - Complete UX Overhaul 🚀🎤 (#39)
* feat: prepare for v0.2.0-alpha release

* feat: prepare for v0.2.0-alpha release

* chore: remove CHANGELOG.md, use GitHub Releases instead

* refactor: use existing About dialog instead of Settings section

* style: enhance About dialog UI readability

* style: fix formatting with black and isort

* feat: show VAD and silence timeout settings for Whisper engine

- Renamed 'VOSK Settings' to 'Recognition Settings'
- VAD Sensitivity and Silence Timeout now apply to both engines
- Added tooltips explaining each setting
- VOSK-specific model info only shown when VOSK selected

* fix: resolve overlapping UI elements in settings dialog

* fix: save VAD and silence timeout settings for both engines

Previously these settings were only saved when VOSK was selected.
Now they persist correctly for Whisper as well.

* fix: show download progress when selecting undownloaded model

Previously when auto-applying settings, models would download silently
in the background without showing the progress dialog. Now:
- Download progress dialog appears for undownloaded models
- Model icons update correctly after download completes

* feat: add download progress, speed, ETA and cancel button

- Show real download progress percentage for VOSK models
- Display download speed (MB/s) and estimated time remaining
- Add Cancel button to abort downloads
- Update status during extraction phase
- Whisper downloads still pulse (uses internal downloader)

* fix: defer model download until needed, don't block startup

- App now starts instantly even if models aren't downloaded
- Models are downloaded on-demand when selected in Settings
- If user tries to dictate without a model, plays error sound
- Added model_ready property to check if engine is usable

* fix: improve first-run UX without downloaded models

- Settings dialog now defaults to smallest available model, not saved config
- Only show saved model if it's actually downloaded
- Add desktop notification when trying to dictate without a model
- Prevents auto-downloading large models on first launch

* feat: add download progress tracking for Whisper models

- Implement custom Whisper model download with progress/speed/ETA
- Uses OpenAI's CDN URLs directly instead of whisper.load_model()
- Progress callback works the same as VOSK downloads
- Supports cancellation during download

* fix: enable download progress callback for Whisper models

Progress callback was only being set for VOSK downloads, not Whisper.
Now both engines show real-time progress, speed, and ETA.

* fix: update tests for defer_download and config manager mocking

- test_main: Mock ConfigManager to prevent saved config from overriding test values
- test_settings_dialog: Mock ModelDownloadDialog to prevent GTK init errors
- test_speech_recognition: Use proper MockVoskModule class instead of MagicMock, pass defer_download=False for download test
- test_whisper_support: Pass defer_download=False to trigger model loading in test

* fix: resolve test failures for CI

- test_main: Fix ConfigManager patch path to use source module
- test_settings_dialog: Mock _is_vosk_model_downloaded and _is_whisper_model_downloaded to skip download flow, add missing dialog attributes
- test_speech_recognition: Replace recognizer with properly configured mock that returns valid JSON, fixing test isolation issues when running all tests together

* fix: mock _download_whisper_model in whisper test to avoid requests exception handling issue

* fix: add gir1.2-girepository-2.0 dep for PyGObject on Ubuntu 24.04

- Add missing girepository-2.0 package for newer Ubuntu runners
- Use --no-build-isolation for PyGObject to use system packages

* fix: skip PyGObject pip install, use system python3-gi package

- Use --no-deps for editable install to skip PyGObject
- Install other deps explicitly without PyGObject
- Add python3-gi-cairo for complete GTK support
- Removes problematic girepository-2.0 build requirement

* fix: install PyGObject via pip with proper build deps

- Remove python3-gi/python3-gi-cairo (doesn't work with setup-python)
- Install PyGObject from pip after installing build dependencies
- Simplify venv setup without --system-site-packages hack

* Fix GObject

* fix: set GI_TYPELIB_PATH for pip-installed PyGObject to find AppIndicator3
2025-12-28 15:29:51 -08:00

154 lines
3.7 KiB
TOML

[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 = ">=3.8"
keywords = [
"voice", "dictation", "speech", "recognition",
"linux", "accessibility", "voice-typing", "speech-to-text"
]
classifiers = [
"Development Status :: 3 - Alpha",
"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 :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Desktop Environment :: Gnome",
"Topic :: Multimedia :: Sound/Audio :: Speech",
"Topic :: Text Processing",
"Topic :: Utilities",
]
dependencies = [
"vosk>=0.3.45",
"pydub>=0.25.1",
"pynput>=1.7.6",
"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'",
]
[project.optional-dependencies]
whisper = [
"openai-whisper>=20231117",
"torch>=2.0.0",
"torchaudio>=2.0.0",
]
dev = [
"pytest>=7.0.0",
"pytest-cov>=4.0.0",
"pytest-mock>=3.10.0",
"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.speech_recognition", "vocalinux.text_injection", "vocalinux.ui", "vocalinux.utils"]
package-dir = {"" = "src"}
[tool.setuptools.dynamic]
version = {attr = "vocalinux.version.__version__"}
[tool.setuptools.package-data]
"*" = ["*.svg", "*.wav"]
[tool.black]
line-length = 100
target-version = ['py38', 'py39', 'py310', 'py311']
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"
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__/*"]
[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 = "3.8"
warn_return_any = true
warn_unused_configs = true
ignore_missing_imports = true
exclude = ["venv", "build", "dist", "node_modules"]