8f05a7c188
- Update ASR, face, OCR, pose processors - Add release pre-flight check script - Add synonym generation, chunk processing scripts - Add face recognition, stamp search utilities
120 lines
3.5 KiB
Python
Executable File
120 lines
3.5 KiB
Python
Executable File
#!/opt/homebrew/bin/python3.11
|
|
import sys
|
|
import json
|
|
import os
|
|
import argparse
|
|
import signal
|
|
import subprocess
|
|
from faster_whisper import WhisperModel
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
from redis_publisher import RedisPublisher
|
|
|
|
|
|
def signal_handler(signum, frame):
|
|
print(f"ASR: 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 run_asr(video_path, output_path, uuid: str = ""):
|
|
# Set up signal handlers
|
|
signal.signal(signal.SIGTERM, signal_handler)
|
|
signal.signal(signal.SIGINT, signal_handler)
|
|
|
|
publisher = RedisPublisher(uuid) if uuid else None
|
|
if publisher:
|
|
publisher.info("asr", "ASR_START")
|
|
|
|
# Check for audio stream
|
|
if not has_audio_stream(video_path):
|
|
if publisher:
|
|
publisher.info("asr", "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("asr", "0 segments (no audio)")
|
|
sys.stderr.write("ASR: No audio stream, skipping transcription\n")
|
|
sys.stderr.flush()
|
|
sys.exit(0)
|
|
|
|
if publisher:
|
|
publisher.info("asr", "Loading Whisper model...")
|
|
|
|
# Use base model with CPU (MPS not supported by faster_whisper)
|
|
model = WhisperModel("base", device="cpu", compute_type="int8")
|
|
|
|
if publisher:
|
|
publisher.info("asr", f"Transcribing: {video_path}")
|
|
|
|
segments, info = model.transcribe(video_path, beam_size=5)
|
|
|
|
if publisher:
|
|
publisher.info("asr", f"ASR_LANGUAGE:{info.language}")
|
|
|
|
results = []
|
|
total_segments = 0
|
|
|
|
for segment in segments:
|
|
results.append(
|
|
{"start": segment.start, "end": segment.end, "text": segment.text.strip()}
|
|
)
|
|
total_segments += 1
|
|
if total_segments % 100 == 0:
|
|
if publisher:
|
|
publisher.progress(
|
|
"asr", total_segments, 0, f"Segment {total_segments}"
|
|
)
|
|
|
|
output = {
|
|
"language": info.language,
|
|
"language_probability": info.language_probability,
|
|
"segments": results,
|
|
}
|
|
|
|
with open(output_path, "w") as f:
|
|
json.dump(output, f, indent=2)
|
|
|
|
if publisher:
|
|
publisher.complete("asr", f"{len(results)} segments")
|
|
|
|
sys.stderr.write(
|
|
f"ASR: Transcription complete, {len(results)} segments written to {output_path}\n"
|
|
)
|
|
sys.stderr.flush()
|
|
sys.exit(0)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(description="ASR Transcription (base model)")
|
|
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="")
|
|
args = parser.parse_args()
|
|
|
|
run_asr(args.video_path, args.output_path, args.uuid)
|