Josh Knapp
472233aec4
Phase 1 Complete - Standalone Desktop Application Features: - Real-time speech-to-text with Whisper (faster-whisper) - PySide6 desktop GUI with settings dialog - Web server for OBS browser source integration - Audio capture with automatic sample rate detection and resampling - Noise suppression with Voice Activity Detection (VAD) - Configurable display settings (font, timestamps, fade duration) - Settings apply without restart (with automatic model reloading) - Auto-fade for web display transcriptions - CPU/GPU support with automatic device detection - Standalone executable builds (PyInstaller) - CUDA build support (works on systems without CUDA hardware) Components: - Audio capture with sounddevice - Noise reduction with noisereduce + webrtcvad - Transcription with faster-whisper - GUI with PySide6 - Web server with FastAPI + WebSocket - Configuration system with YAML Build System: - Standard builds (CPU-only): build.sh / build.bat - CUDA builds (universal): build-cuda.sh / build-cuda.bat - Comprehensive BUILD.md documentation - Cross-platform support (Linux, Windows) Documentation: - README.md with project overview and quick start - BUILD.md with detailed build instructions - NEXT_STEPS.md with future enhancement roadmap - INSTALL.md with setup instructions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
60 lines
1.2 KiB
TOML
60 lines
1.2 KiB
TOML
[project]
|
|
name = "local-transcription"
|
|
version = "0.1.0"
|
|
description = "A standalone desktop application for real-time speech-to-text transcription using Whisper models"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
license = {text = "MIT"}
|
|
authors = [
|
|
{name = "Your Name", email = "your.email@example.com"}
|
|
]
|
|
keywords = ["transcription", "speech-to-text", "whisper", "streaming", "obs"]
|
|
|
|
dependencies = [
|
|
"numpy>=1.24.0",
|
|
"pyyaml>=6.0",
|
|
"sounddevice>=0.4.6",
|
|
"scipy>=1.10.0",
|
|
"noisereduce>=3.0.0",
|
|
"webrtcvad>=2.0.10",
|
|
"faster-whisper>=0.10.0",
|
|
"torch>=2.0.0",
|
|
"PySide6>=6.6.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
server = [
|
|
"fastapi>=0.104.0",
|
|
"uvicorn>=0.24.0",
|
|
"websockets>=12.0",
|
|
"requests>=2.31.0",
|
|
]
|
|
dev = [
|
|
"pytest>=7.4.0",
|
|
"black>=23.0.0",
|
|
"ruff>=0.1.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
local-transcription = "main:main"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["client", "gui"]
|
|
|
|
[tool.uv]
|
|
dev-dependencies = [
|
|
"pyinstaller>=6.17.0",
|
|
]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py39"
|
|
|
|
[tool.black]
|
|
line-length = 100
|
|
target-version = ["py39"]
|