Jatin K MalikandGitHub
57a0ddd0b8
* feat(speech): add whisper.cpp with Vulkan support for GPU acceleration Add whisper.cpp as a new speech recognition engine with the following features: - Vulkan GPU acceleration support (AMD, Intel, NVIDIA) - Fallback to CUDA for NVIDIA GPUs - CPU-only mode with automatic thread optimization - Support for all model sizes: tiny, base, small, medium, large - Hardware detection to recommend best model/backend - Models downloaded from Hugging Face (ggml format) - Updated UI to show compute backend info in settings - pywhispercpp as the Python binding library - whisper_cpp as the new default engine Changes: - New whispercpp_model_info.py with model metadata and hardware detection - Updated recognition_manager.py with whisper.cpp init and transcription - Updated settings_dialog.py with whisper.cpp UI support - Updated config_manager.py with whisper_cpp_model_size config - Updated main.py with whisper_cpp CLI option - Updated pyproject.toml with pywhispercpp dependency - Updated install.sh with vulkan-tools for GPU detection Closes #104 * style: fix black and isort formatting issues * test: update config manager test for whisper_cpp default engine * feat(install): interactive mode with 3 engine choices and whisper.cpp as default Major changes to install.sh: - Interactive mode is now the DEFAULT (not --auto) - Added --auto flag for non-interactive automatic installation - New --engine flag to specify engine directly - Interactive mode shows 3 engine options with visual boxes: 1. whisper.cpp (recommended) - Vulkan/CUDA/CPU support 2. whisper (OpenAI) - PyTorch-based, NVIDIA-only 3. VOSK - lightweight option - Hardware detection with recommendations: - Detects Vulkan support (AMD/Intel/NVIDIA) - Detects NVIDIA CUDA - Checks available RAM - Recommends best engine based on hardware - Updated help text with new options and examples - Removed old --with-whisper, --whisper-cpu, --no-whisper flags - whisper.cpp is now the default engine for automatic mode * feat(uninstall): kill running vocalinux processes before uninstall * fix(whisper.cpp): auto-download model, use all CPU cores, hide unavailable engines Three fixes for whisper.cpp implementation: 1. Auto-download model during install - Added install_whispercpp_model() function to install.sh - Downloads ggml-tiny.bin (~39MB) from Hugging Face - Runs automatically when whisper.cpp engine is selected 2. Use all CPU cores for transcription - Added n_threads parameter to Model initialization - Uses multiprocessing.cpu_count() to get all cores - Significantly improves transcription speed 3. Hide unavailable engines from dropdown - Added get_available_engines() function to detect installed engines - Settings dialog now only shows engines that are actually installed - Falls back to first available engine if current not available Fixes user-reported issues with whisper.cpp integration. * ui(settings): display whisper.cpp correctly and increase dialog height - Changed engine display name from 'whisper_cpp' to 'whisper.cpp' - Added format_engine_display_name() helper function - Dialog now uses 75% of screen height for better visibility - More options visible by default without scrolling * revert(settings): remove display name change, keep dialog height increase - Reverted engine display name change (was breaking engine selection) - Kept dialog height at 75% of screen for better visibility * style: fix black and isort formatting for whisper.cpp logging * style: fix black formatting in settings_dialog.py * ci: fix Fedora 39 container package installation Add dnf cache update and fallback with --nogpgcheck for Fedora containers that may have stale or missing package metadata.
163 lines
4.0 KiB
TOML
163 lines
4.0 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 :: 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 :: 3.8",
|
|
"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",
|
|
"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'",
|
|
]
|
|
|
|
[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.ui.keyboard_backends", "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', 'py312', 'py313']
|
|
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__/*",
|
|
# 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 = "3.8"
|
|
warn_return_any = true
|
|
warn_unused_configs = true
|
|
ignore_missing_imports = true
|
|
exclude = ["venv", "build", "dist", "node_modules"]
|