Initial commit: Local Transcription App v1.0

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>

test_components.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""
+Test script to verify all components work without GUI.
+This can run in headless environments.
+"""
+
+import sys
+from pathlib import Path
+
+# Add project root to Python path
+project_root = Path(__file__).parent
+sys.path.insert(0, str(project_root))
+
+print("=" * 60)
+print("Testing Local Transcription Components (No GUI)")
+print("=" * 60)
+
+# Test 1: Configuration
+print("\n1. Testing Configuration System...")
+try:
+    from client.config import Config
+    config = Config()
+    print(f"   ✓ Config loaded: {config.config_path}")
+    print(f"   ✓ User name: {config.get('user.name')}")
+    print(f"   ✓ Model: {config.get('transcription.model')}")
+except Exception as e:
+    print(f"   ✗ Config failed: {e}")
+    sys.exit(1)
+
+# Test 2: Device Detection
+print("\n2. Testing Device Detection...")
+try:
+    from client.device_utils import DeviceManager
+    device_mgr = DeviceManager()
+    print(f"   ✓ Available devices: {device_mgr.available_devices}")
+    print(f"   ✓ Current device: {device_mgr.current_device}")
+    print(f"   ✓ GPU available: {device_mgr.is_gpu_available()}")
+
+    device_info = device_mgr.get_device_info()
+    for dev_id, dev_desc in device_info:
+        print(f"      - {dev_id}: {dev_desc}")
+except Exception as e:
+    print(f"   ✗ Device detection failed: {e}")
+    sys.exit(1)
+
+# Test 3: Audio Devices
+print("\n3. Testing Audio Capture...")
+try:
+    from client.audio_capture import AudioCapture
+    devices = AudioCapture.get_input_devices()
+    print(f"   ✓ Found {len(devices)} audio input device(s)")
+    for idx, name in devices[:5]:  # Show first 5
+        print(f"      - [{idx}] {name}")
+    if len(devices) > 5:
+        print(f"      ... and {len(devices) - 5} more")
+except Exception as e:
+    print(f"   ✗ Audio capture failed: {e}")
+
+# Test 4: Noise Suppression
+print("\n4. Testing Noise Suppression...")
+try:
+    from client.noise_suppression import NoiseSuppressor
+    import numpy as np
+
+    suppressor = NoiseSuppressor(sample_rate=16000, method="noisereduce", strength=0.7)
+    print(f"   ✓ Noise suppressor created: {suppressor}")
+
+    # Test with dummy audio
+    test_audio = np.random.randn(16000).astype(np.float32) * 0.1
+    processed = suppressor.process(test_audio, skip_silent=False)
+    print(f"   ✓ Processed audio shape: {processed.shape}")
+except Exception as e:
+    print(f"   ✗ Noise suppression failed: {e}")
+
+# Test 5: Transcription Engine
+print("\n5. Testing Transcription Engine (Loading Model)...")
+try:
+    from client.transcription_engine import TranscriptionEngine
+
+    device = device_mgr.get_device_for_whisper()
+    compute_type = device_mgr.get_compute_type()
+
+    print(f"   → Using device: {device} with compute type: {compute_type}")
+    print(f"   → Loading model (this may take 1-2 minutes on first run)...")
+
+    engine = TranscriptionEngine(
+        model_size="tiny",  # Use tiny for faster testing
+        device=device,
+        compute_type=compute_type,
+        language="en"
+    )
+
+    success = engine.load_model()
+    if success:
+        print(f"   ✓ Model loaded successfully!")
+        print(f"   ✓ Engine: {engine}")
+
+        # Test transcription with dummy audio
+        print(f"\n   Testing transcription with silent audio...")
+        test_audio = np.zeros(48000, dtype=np.float32)  # 3 seconds of silence
+        result = engine.transcribe(test_audio, sample_rate=16000, user_name="Test")
+
+        if result:
+            print(f"   ✓ Transcription result: '{result.text}'")
+        else:
+            print(f"   ℹ No transcription (expected for silent audio)")
+
+        engine.unload_model()
+    else:
+        print(f"   ✗ Model loading failed")
+        sys.exit(1)
+
+except Exception as e:
+    print(f"   ✗ Transcription engine failed: {e}")
+    import traceback
+    traceback.print_exc()
+    sys.exit(1)
+
+print("\n" + "=" * 60)
+print("✓ All Components Tested Successfully!")
+print("=" * 60)
+print("\nThe application is ready to use!")
+print("Run 'uv run python main.py' on a system with a display.")
+print("=" * 60)