#!/usr/bin/env python3
"""Simple script to transcribe the BAP South meeting recording."""

import asyncio
import json
from pathlib import Path
from src.services.local_transcription_service import create_local_transcription_service, LocalTranscriptionConfig
from src.repositories.transcription_repository import create_transcription_repository

async def main():
    """Transcribe the BAP South meeting recording."""
    # Use the clean WAV file instead of the problematic M4A
    audio_file = Path("BAP_South_Meeting_Clean.wav")
    
    if not audio_file.exists():
        print(f"❌ Audio file not found: {audio_file}")
        return
    
    print(f"🎵 Transcribing: {audio_file.name}")
    print(f"📁 File size: {audio_file.stat().st_size / (1024*1024):.1f} MB")
    
    try:
        # Create repository and service
        repository = await create_transcription_repository()
        service = create_local_transcription_service(repository)
        
        # Initialize service
        await service.initialize()
        
        # Configure transcription
        config = LocalTranscriptionConfig(
            model="distil-large-v3",
            language=None,  # Auto-detect
            temperature=0.0,  # Deterministic
            chunk_size_seconds=600,  # 10 minutes
            enable_m3_preprocessing=True
        )
        
        print("🚀 Starting transcription...")
        
        # Transcribe the audio
        result = await service.transcribe_audio(audio_file, config)
        
        print("✅ Transcription completed!")
        print(f"📝 Text length: {len(result.text_content)} characters")
        print(f"⏱️  Processing time: {result.processing_time_ms / 1000:.1f} seconds")
        print(f"🎯 Accuracy estimate: {result.accuracy_estimate * 100:.1f}%")
        
        # Save to text file
        output_file = Path("BAP_South_Meeting_Transcript.txt")
        with open(output_file, "w", encoding="utf-8") as f:
            f.write(f"BAP South Meeting - August 28, 2025\n")
            f.write(f"Transcription completed at: {result.completed_at}\n")
            f.write(f"Model: {result.model_used}\n")
            f.write(f"Accuracy: {result.accuracy_estimate * 100:.1f}%\n")
            f.write(f"Processing time: {result.processing_time_ms / 1000:.1f} seconds\n")
            f.write(f"Word count: {result.word_count}\n")
            f.write("=" * 80 + "\n\n")
            f.write(result.text_content)
        
        print(f"💾 Transcript saved to: {output_file}")
        
        # Also save as JSON for detailed analysis
        json_output = {
            "text": result.text_content,
            "segments": result.segments,
            "accuracy": result.accuracy_estimate,
            "processing_time": result.processing_time_ms / 1000.0,
            "word_count": result.word_count,
            "model_used": result.model_used,
            "completed_at": result.completed_at,
            "quality_warnings": result.quality_warnings
        }
        
        json_file = Path("BAP_South_Meeting_Transcript.json")
        with open(json_file, "w", encoding="utf-8") as f:
            json.dump(json_output, f, indent=2, ensure_ascii=False)
        
        print(f"📊 Detailed data saved to: {json_file}")
        
    except Exception as e:
        print(f"❌ Transcription failed: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    asyncio.run(main())