b54c2def30
- Add database migrations (006-028) for face recognition, identity, file_uuid - Add test scripts for ASR, face, search, processing - Add portal frontend (Tauri) - Add config, benchmark, and monitoring utilities - Add model checkpoints and pretrained model references
67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Test transcription on extracted audio.
|
|
"""
|
|
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
# Add scripts directory to path
|
|
sys.path.insert(0, str(Path(__file__).parent / "scripts"))
|
|
|
|
|
|
def test_transcribe(audio_path):
|
|
"""Test transcription using faster_whisper."""
|
|
print(f"Testing transcription on: {audio_path}")
|
|
print(f"Size: {Path(audio_path).stat().st_size / 1024 / 1024:.1f} MB")
|
|
|
|
# Import faster_whisper
|
|
try:
|
|
from faster_whisper import WhisperModel
|
|
except ImportError as e:
|
|
print(f"Failed to import faster_whisper: {e}")
|
|
return False
|
|
|
|
# Load model
|
|
print("Loading Whisper model (tiny, cpu, int8)...")
|
|
start = time.time()
|
|
try:
|
|
model = WhisperModel("tiny", device="cpu", compute_type="int8")
|
|
load_time = time.time() - start
|
|
print(f"Model loaded in {load_time:.1f}s")
|
|
except Exception as e:
|
|
print(f"Model loading failed: {e}")
|
|
return False
|
|
|
|
# Transcribe first 30 seconds
|
|
print("Transcribing first 30 seconds...")
|
|
start = time.time()
|
|
try:
|
|
segments, info = model.transcribe(audio_path, beam_size=5)
|
|
# Convert generator to list to force processing
|
|
segments = list(segments)
|
|
transcribe_time = time.time() - start
|
|
print(f"Transcription completed in {transcribe_time:.1f}s")
|
|
print(
|
|
f"Detected language: {info.language} (prob {info.language_probability:.2f})"
|
|
)
|
|
print(f"Segments found: {len(segments)}")
|
|
for i, seg in enumerate(segments[:3]):
|
|
print(f" [{i}] {seg.start:.1f}-{seg.end:.1f}: {seg.text[:80]}...")
|
|
return True
|
|
except Exception as e:
|
|
print(f"Transcription failed: {e}")
|
|
import traceback
|
|
|
|
traceback.print_exc()
|
|
return False
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) != 2:
|
|
print(f"Usage: {sys.argv[0]} <audio_file>")
|
|
sys.exit(1)
|
|
success = test_transcribe(sys.argv[1])
|
|
sys.exit(0 if success else 1)
|