verify_installation.py

#!/usr/bin/env python3
"""
Installation verification script
Checks that all components are properly installed and configured
"""

import sys
from pathlib import Path
import importlib

def check_python_version():
    """Check Python version."""
    print("Checking Python version...")
    version = sys.version_info
    if version.major >= 3 and version.minor >= 10:
        print(f"  ✅ Python {version.major}.{version.minor}.{version.micro}")
        return True
    else:
        print(f"  ❌ Python {version.major}.{version.minor}.{version.micro} (requires 3.10+)")
        return False

def check_package(package_name, import_name=None):
    """Check if a package is installed."""
    if import_name is None:
        import_name = package_name
    
    try:
        mod = importlib.import_module(import_name)
        version = getattr(mod, '__version__', 'unknown')
        print(f"  ✅ {package_name} ({version})")
        return True
    except ImportError:
        print(f"  ❌ {package_name} not found")
        return False

def check_cuda():
    """Check CUDA availability."""
    print("Checking CUDA...")
    try:
        import torch
        if torch.cuda.is_available():
            print(f"  ✅ CUDA available (version {torch.version.cuda})")
            print(f"     GPU: {torch.cuda.get_device_name(0)}")
            return True
        else:
            print("  ⚠️  CUDA not available (CPU mode)")
            return False
    except ImportError:
        print("  ❌ PyTorch not installed")
        return False

def check_files():
    """Check that all required files exist."""
    print("Checking project files...")
    
    required_files = [
        'src/__init__.py',
        'src/vad.py',
        'src/diarization.py',
        'src/pipeline.py',
        'src/utils.py',
        'app.py',
        'vad_diarization.py',
        'requirements.txt',
        'Dockerfile',
        'README.md'
    ]
    
    all_exist = True
    for file in required_files:
        path = Path(file)
        if path.exists():
            print(f"  ✅ {file}")
        else:
            print(f"  ❌ {file} missing")
            all_exist = False
    
    return all_exist

def check_hf_token():
    """Check for Hugging Face token."""
    print("Checking Hugging Face token...")
    import os
    token = os.environ.get('HF_TOKEN')
    if token:
        print(f"  ✅ HF_TOKEN found (length: {len(token)})")
        return True
    else:
        print("  ⚠️  HF_TOKEN not set (required for full pipeline)")
        print("     Set with: export HF_TOKEN='your_token_here'")
        return False

def test_vad():
    """Test VAD functionality."""
    print("Testing VAD...")
    try:
        from src.vad import SileroVAD
        vad = SileroVAD(threshold=0.5)
        print("  ✅ VAD initialized successfully")
        
        # Quick benchmark
        metrics = vad.benchmark_latency(duration_seconds=1.0)
        latency = metrics['latency_per_second_ms']
        print(f"  ✅ VAD latency: {latency:.2f}ms per second")
        
        if latency < 100:
            print("  ✅ Latency target achieved (<100ms)")
        else:
            print("  ⚠️  Latency above target")
        
        return True
    except Exception as e:
        print(f"  ❌ VAD test failed: {e}")
        return False

def main():
    """Run all verification checks."""
    print("\n" + "="*60)
    print("INSTALLATION VERIFICATION")
    print("="*60 + "\n")
    
    results = {}
    
    # Python version
    results['python'] = check_python_version()
    print()
    
    # Required packages
    print("Checking required packages...")
    packages = [
        ('torch', 'torch'),
        ('numpy', 'numpy'),
        ('librosa', 'librosa'),
        ('soundfile', 'soundfile'),
        ('gradio', 'gradio'),
        ('matplotlib', 'matplotlib'),
        ('silero-vad', 'silero_vad'),
        ('pyannote.audio', 'pyannote.audio')
    ]
    
    results['packages'] = all(check_package(name, imp) for name, imp in packages)
    print()
    
    # CUDA
    results['cuda'] = check_cuda()
    print()
    
    # Files
    results['files'] = check_files()
    print()
    
    # HF Token
    results['token'] = check_hf_token()
    print()
    
    # VAD test
    results['vad'] = test_vad()
    print()
    
    # Summary
    print("="*60)
    print("VERIFICATION SUMMARY")
    print("="*60)
    
    total = len(results)
    passed = sum(1 for v in results.values() if v)
    
    for check, result in results.items():
        status = "✅ PASS" if result else "❌ FAIL"
        print(f"{check.upper():20s}: {status}")
    
    print()
    print(f"Results: {passed}/{total} checks passed")
    
    if passed == total:
        print("\n🎉 All checks passed! System is ready to use.")
        print("\nNext steps:")
        print("1. Run demo: python vad_diarization.py")
        print("2. Launch Gradio: python app.py")
        print("3. Run benchmarks: python benchmarks/run_benchmarks.py --quick")
    elif results['python'] and results['packages'] and results['files']:
        print("\n✅ Core system is functional.")
        if not results['token']:
            print("⚠️  Set HF_TOKEN for full pipeline functionality")
        if not results['cuda']:
            print("⚠️  CUDA not available, will use CPU (slower)")
    else:
        print("\n❌ Installation incomplete. Please fix the issues above.")
        print("\nTry running: ./setup.sh")
    
    print("="*60 + "\n")
    
    return passed == total

if __name__ == "__main__":
    success = main()
    sys.exit(0 if success else 1)