Files
mitus/process_meeting.py
2025-10-19 22:58:28 -03:00

402 lines
13 KiB
Python

#!/usr/bin/env python3
"""
Process meeting recordings to extract audio + screen content.
Combines Whisper transcripts with OCR from screen shares.
"""
import argparse
from pathlib import Path
import sys
import json
import logging
import subprocess
import shutil
from meetus.frame_extractor import FrameExtractor
from meetus.ocr_processor import OCRProcessor
from meetus.vision_processor import VisionProcessor
from meetus.transcript_merger import TranscriptMerger
logger = logging.getLogger(__name__)
def setup_logging(verbose: bool = False):
"""
Configure logging for the application.
Args:
verbose: If True, set DEBUG level, otherwise INFO
"""
level = logging.DEBUG if verbose else logging.INFO
# Configure root logger
logging.basicConfig(
level=level,
format='%(asctime)s - %(levelname)s - %(message)s',
datefmt='%H:%M:%S'
)
# Suppress verbose output from libraries
logging.getLogger('PIL').setLevel(logging.WARNING)
logging.getLogger('easyocr').setLevel(logging.WARNING)
logging.getLogger('paddleocr').setLevel(logging.WARNING)
def run_whisper(video_path: Path, model: str = "base", output_dir: str = "output") -> Path:
"""
Run Whisper transcription on video file.
Args:
video_path: Path to video file
model: Whisper model to use (tiny, base, small, medium, large)
output_dir: Directory to save output
Returns:
Path to generated JSON transcript
"""
# Check if whisper is installed
if not shutil.which("whisper"):
logger.error("Whisper is not installed. Install it with: pip install openai-whisper")
sys.exit(1)
logger.info(f"Running Whisper transcription (model: {model})...")
logger.info("This may take a few minutes depending on video length...")
# Run whisper command
cmd = [
"whisper",
str(video_path),
"--model", model,
"--output_format", "json",
"--output_dir", output_dir
]
try:
result = subprocess.run(
cmd,
check=True,
capture_output=True,
text=True
)
# Whisper outputs to <output_dir>/<video_stem>.json
transcript_path = Path(output_dir) / f"{video_path.stem}.json"
if transcript_path.exists():
logger.info(f"✓ Whisper transcription completed: {transcript_path}")
return transcript_path
else:
logger.error("Whisper completed but transcript file not found")
sys.exit(1)
except subprocess.CalledProcessError as e:
logger.error(f"Whisper failed: {e.stderr}")
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
description="Extract screen content from meeting recordings and merge with transcripts",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
# Run Whisper + vision analysis (recommended for code/dashboards)
python process_meeting.py samples/meeting.mkv --run-whisper --use-vision
# Use vision with specific context hint
python process_meeting.py samples/meeting.mkv --run-whisper --use-vision --vision-context code
# Traditional OCR approach
python process_meeting.py samples/meeting.mkv --run-whisper
# Re-run analysis using cached frames and transcript
python process_meeting.py samples/meeting.mkv --use-vision
# Force reprocessing (ignore cache)
python process_meeting.py samples/meeting.mkv --run-whisper --use-vision --no-cache
# Use scene detection for fewer frames
python process_meeting.py samples/meeting.mkv --run-whisper --use-vision --scene-detection
"""
)
parser.add_argument(
'video',
help='Path to video file'
)
parser.add_argument(
'--transcript', '-t',
help='Path to Whisper transcript (JSON or TXT)',
default=None
)
parser.add_argument(
'--run-whisper',
action='store_true',
help='Run Whisper transcription before processing'
)
parser.add_argument(
'--whisper-model',
choices=['tiny', 'base', 'small', 'medium', 'large'],
help='Whisper model to use (default: base)',
default='base'
)
parser.add_argument(
'--output', '-o',
help='Output file for enhanced transcript (default: output/<video>_enhanced.txt)',
default=None
)
parser.add_argument(
'--output-dir',
help='Directory for output files (default: output/)',
default='output'
)
parser.add_argument(
'--frames-dir',
help='Directory to save extracted frames (default: frames/)',
default='frames'
)
parser.add_argument(
'--interval',
type=int,
help='Extract frame every N seconds (default: 5)',
default=5
)
parser.add_argument(
'--scene-detection',
action='store_true',
help='Use scene detection instead of interval extraction'
)
parser.add_argument(
'--ocr-engine',
choices=['tesseract', 'easyocr', 'paddleocr'],
help='OCR engine to use (default: tesseract)',
default='tesseract'
)
parser.add_argument(
'--use-vision',
action='store_true',
help='Use local vision model (Ollama) instead of OCR for better context understanding'
)
parser.add_argument(
'--vision-model',
help='Vision model to use with Ollama (default: llava:13b)',
default='llava:13b'
)
parser.add_argument(
'--vision-context',
choices=['meeting', 'dashboard', 'code', 'console'],
help='Context hint for vision analysis (default: meeting)',
default='meeting'
)
parser.add_argument(
'--no-cache',
action='store_true',
help='Disable caching - reprocess everything even if outputs exist'
)
parser.add_argument(
'--no-deduplicate',
action='store_true',
help='Disable text deduplication'
)
parser.add_argument(
'--extract-only',
action='store_true',
help='Only extract frames and OCR, skip transcript merging'
)
parser.add_argument(
'--format',
choices=['detailed', 'compact'],
help='Output format style (default: detailed)',
default='detailed'
)
parser.add_argument(
'--verbose', '-v',
action='store_true',
help='Enable verbose logging (DEBUG level)'
)
args = parser.parse_args()
# Setup logging
setup_logging(args.verbose)
# Validate video path
video_path = Path(args.video)
if not video_path.exists():
logger.error(f"Video file not found: {args.video}")
sys.exit(1)
# Create output directory
output_dir = Path(args.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
# Set default output path
if args.output is None:
args.output = str(output_dir / f"{video_path.stem}_enhanced.txt")
# Define cache paths
whisper_cache = output_dir / f"{video_path.stem}.json"
analysis_cache = output_dir / f"{video_path.stem}_{'vision' if args.use_vision else 'ocr'}.json"
frames_cache_dir = Path(args.frames_dir)
# Check for cached Whisper transcript
if args.run_whisper:
if not args.no_cache and whisper_cache.exists():
logger.info(f"✓ Found cached Whisper transcript: {whisper_cache}")
args.transcript = str(whisper_cache)
else:
logger.info("=" * 80)
logger.info("STEP 0: Running Whisper Transcription")
logger.info("=" * 80)
transcript_path = run_whisper(video_path, args.whisper_model, str(output_dir))
args.transcript = str(transcript_path)
logger.info("")
logger.info("=" * 80)
logger.info("MEETING PROCESSOR")
logger.info("=" * 80)
logger.info(f"Video: {video_path.name}")
logger.info(f"Analysis: {'Vision Model' if args.use_vision else f'OCR ({args.ocr_engine})'}")
if args.use_vision:
logger.info(f"Vision Model: {args.vision_model}")
logger.info(f"Context: {args.vision_context}")
logger.info(f"Frame extraction: {'Scene detection' if args.scene_detection else f'Every {args.interval}s'}")
if args.transcript:
logger.info(f"Transcript: {args.transcript}")
logger.info(f"Caching: {'Disabled' if args.no_cache else 'Enabled'}")
logger.info("=" * 80)
# Step 1: Extract frames (with caching)
logger.info("Step 1: Extracting frames from video...")
# Check if frames already exist
existing_frames = list(frames_cache_dir.glob(f"{video_path.stem}_*.jpg")) if frames_cache_dir.exists() else []
if not args.no_cache and existing_frames and len(existing_frames) > 0:
logger.info(f"✓ Found {len(existing_frames)} cached frames in {args.frames_dir}/")
# Build frames_info from existing files
frames_info = []
for frame_path in sorted(existing_frames):
# Try to extract timestamp from filename (e.g., video_00001_12.34s.jpg)
try:
timestamp_str = frame_path.stem.split('_')[-1].rstrip('s')
timestamp = float(timestamp_str)
except:
timestamp = 0.0
frames_info.append((str(frame_path), timestamp))
else:
extractor = FrameExtractor(str(video_path), args.frames_dir)
if args.scene_detection:
frames_info = extractor.extract_scene_changes()
else:
frames_info = extractor.extract_by_interval(args.interval)
if not frames_info:
logger.error("No frames extracted")
sys.exit(1)
logger.info(f"✓ Extracted {len(frames_info)} frames")
# Step 2: Run analysis on frames (with caching)
if not args.no_cache and analysis_cache.exists():
logger.info(f"✓ Found cached analysis results: {analysis_cache}")
with open(analysis_cache, 'r', encoding='utf-8') as f:
screen_segments = json.load(f)
logger.info(f"✓ Loaded {len(screen_segments)} analyzed frames from cache")
else:
if args.use_vision:
# Use vision model
logger.info("Step 2: Running vision analysis on extracted frames...")
try:
vision = VisionProcessor(model=args.vision_model)
screen_segments = vision.process_frames(
frames_info,
context=args.vision_context,
deduplicate=not args.no_deduplicate
)
logger.info(f"✓ Analyzed {len(screen_segments)} frames with vision model")
except ImportError as e:
logger.error(f"{e}")
sys.exit(1)
else:
# Use OCR
logger.info("Step 2: Running OCR on extracted frames...")
try:
ocr = OCRProcessor(engine=args.ocr_engine)
screen_segments = ocr.process_frames(
frames_info,
deduplicate=not args.no_deduplicate
)
logger.info(f"✓ Processed {len(screen_segments)} frames with OCR")
except ImportError as e:
logger.error(f"{e}")
logger.error(f"To install {args.ocr_engine}:")
logger.error(f" pip install {args.ocr_engine}")
sys.exit(1)
# Save analysis results as JSON
with open(analysis_cache, 'w', encoding='utf-8') as f:
json.dump(screen_segments, f, indent=2, ensure_ascii=False)
logger.info(f"✓ Saved analysis results to: {analysis_cache}")
if args.extract_only:
logger.info("Done! (extract-only mode)")
return
# Step 3: Merge with transcript (if provided)
merger = TranscriptMerger()
if args.transcript:
logger.info("Step 3: Merging with Whisper transcript...")
transcript_path = Path(args.transcript)
if not transcript_path.exists():
logger.warning(f"Transcript not found: {args.transcript}")
logger.info("Proceeding with screen content only...")
audio_segments = []
else:
audio_segments = merger.load_whisper_transcript(str(transcript_path))
logger.info(f"✓ Loaded {len(audio_segments)} audio segments")
else:
logger.info("No transcript provided, using screen content only...")
audio_segments = []
# Merge and format
merged = merger.merge_transcripts(audio_segments, screen_segments)
formatted = merger.format_for_claude(merged, format_style=args.format)
# Save output
merger.save_transcript(formatted, args.output)
logger.info("=" * 80)
logger.info("✓ PROCESSING COMPLETE!")
logger.info("=" * 80)
logger.info(f"Enhanced transcript: {args.output}")
logger.info(f"OCR data: {ocr_output}")
logger.info(f"Frames: {args.frames_dir}/")
logger.info("")
logger.info("You can now use the enhanced transcript with Claude for summarization!")
if __name__ == '__main__':
main()