momentry_core/scripts/asrx_processor_simplified.py

#!/opt/homebrew/bin/python3.11
"""
ASRX 處理器 - 簡化版
先做轉錄，說話人分離可選
修復 PyTorch 2.6 兼容性問題
"""

# Fix for PyTorch 2.6+ compatibility - MUST be set before importing torch
import os
os.environ["TORCH_FORCE_WEIGHTS_ONLY_LOAD"] = "0"

import sys
import json
import argparse
import signal
import subprocess

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from redis_publisher import RedisPublisher


def signal_handler(signum, frame):
    print(f"ASRX: Received signal {signum}, exiting...")
    sys.exit(1)


def has_audio_stream(video_path):
    """Check if video file has audio stream using ffprobe."""
    try:
        cmd = [
            "ffprobe",
            "-v",
            "error",
            "-select_streams",
            "a",
            "-show_entries",
            "stream=codec_type",
            "-of",
            "csv=p=0",
            video_path,
        ]
        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
        return bool(result.stdout.strip())
    except subprocess.CalledProcessError:
        return False
    except FileNotFoundError:
        print("WARNING: ffprobe not found, assuming audio exists")
        return True


def process_asrx(video_path: str, output_path: str, uuid: str = "", skip_diarization: bool = True):
    """
    Process video for speaker diarization using whisperx
    
    Args:
        video_path: Path to video file
        output_path: Path to output JSON
        uuid: UUID for Redis progress
        skip_diarization: Skip speaker diarization (only transcription)
    """
    
    signal.signal(signal.SIGTERM, signal_handler)
    signal.signal(signal.SIGINT, signal_handler)

    publisher = RedisPublisher(uuid) if uuid else None
    if publisher:
        publisher.info("asrx", "ASRX_START")

    try:
        import whisperx
        import torch
    except ImportError as e:
        if publisher:
            publisher.error("asrx", f"Missing dependency: {e}")
        result = {"language": None, "segments": []}
        if publisher:
            publisher.complete("asrx", "0 segments")
        with open(output_path, "w") as f:
            json.dump(result, f, indent=2)
        sys.exit(1)

    # Check for audio stream
    if not has_audio_stream(video_path):
        if publisher:
            publisher.info("asrx", "No audio stream detected, skipping transcription")
        output = {"language": "", "language_probability": 0.0, "segments": []}
        with open(output_path, "w") as f:
            json.dump(output, f, indent=2)
        if publisher:
            publisher.complete("asrx", "0 segments (no audio)")
        sys.stderr.write("ASRX: No audio stream, skipping transcription\n")
        sys.stderr.flush()
        sys.exit(0)

    if publisher:
        publisher.info("asrx", "ASRX_LOADING_MODEL")

    try:
        # Load model
        if publisher:
            publisher.info("asrx", "Loading whisperx base model (this may take a while)...")
        
        model = whisperx.load_model("base", device="cpu", compute_type="int8")
        
        if publisher:
            publisher.info("asrx", "ASRX_TRANSCRIBING")
        
        # Transcribe with language detection
        result = model.transcribe(video_path)
        
        if publisher:
            publisher.info("asrx", f"ASRX_LANGUAGE:{result.get('language', 'unknown')}")
        
        # Build output (without diarization for now)
        segments = []
        for seg in result.get("segments", []):
            text = seg.get("text", "").strip()
            if text:
                segments.append(
                    {
                        "start": seg.get("start", 0.0),
                        "end": seg.get("end", 0.0),
                        "text": text,
                        "speaker_id": None,  # Will be added when diarization is enabled
                    }
                )
        
        output_result = {
            "language": result.get("language"),
            "language_probability": result.get("language_probability", 0),
            "segments": segments,
            "diarization_enabled": not skip_diarization
        }
        
        if publisher:
            publisher.complete("asrx", f"{len(segments)} segments")
        
        with open(output_path, "w") as f:
            json.dump(output_result, f, indent=2, ensure_ascii=False)
        
        sys.stderr.write(
            f"ASRX: Transcription complete, {len(segments)} segments written to {output_path}\n"
        )
        sys.stderr.flush()
        sys.exit(0)
        
    except Exception as e:
        if publisher:
            publisher.error("asrx", f"Error: {e}")
        import traceback
        traceback.print_exc()
        result = {"language": None, "segments": [], "error": str(e)}
        if publisher:
            publisher.complete("asrx", "0 segments (error)")
        with open(output_path, "w") as f:
            json.dump(result, f, indent=2)
        sys.exit(1)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="ASRX Speaker Diarization (Simplified)")
    parser.add_argument("video_path", help="Path to video file")
    parser.add_argument("output_path", help="Output JSON path")
    parser.add_argument("--uuid", "-u", help="UUID for Redis progress", default="")
    parser.add_argument(
        "--skip-diarization",
        action="store_true",
        help="Skip speaker diarization (only transcription)"
    )
    args = parser.parse_args()

    process_asrx(
        args.video_path,
        args.output_path,
        args.uuid,
        args.skip_diarization
    )