feat: add migrations, test scripts, and utility tools

- 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

test_asr_v2.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+"""
+Test ASR v2 processor.
+"""
+
+import sys
+import os
+import tempfile
+import json
+import subprocess
+from pathlib import Path
+
+
+def test_asr_v2():
+    video_path = "../test_video/BigBuckBunny_320x180.mp4"
+    if not Path(video_path).exists():
+        print(f"Video not found: {video_path}")
+        sys.exit(1)
+
+    # Create output directory
+    output_dir = Path("test_output_v2")
+    output_dir.mkdir(exist_ok=True, parents=True)
+    output_path = output_dir / "asr_v2_output.json"
+
+    # Run ASR v2
+    script_path = Path("scripts/asr_processor_v2.py")
+    if not script_path.exists():
+        print(f"Script not found: {script_path}")
+        sys.exit(1)
+
+    cmd = [
+        sys.executable,
+        str(script_path),
+        video_path,
+        str(output_path),
+        "--chunk-duration",
+        "300",  # 5 minutes
+        "--model-size",
+        "tiny",
+        "--compute-type",
+        "int8",
+    ]
+
+    print(f"Running: {' '.join(cmd)}")
+    print(f"Video: {video_path}")
+
+    start_time = time.time()
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    elapsed = time.time() - start_time
+
+    print(f"Exit code: {result.returncode}")
+    print(f"Elapsed time: {elapsed:.1f}s")
+
+    if result.stdout:
+        print(f"Stdout:\n{result.stdout[:500]}")
+    if result.stderr:
+        print(f"Stderr:\n{result.stderr[:500]}")
+
+    if output_path.exists():
+        with open(output_path, "r") as f:
+            data = json.load(f)
+        print(f"\nResults:")
+        print(f"  Language: {data.get('language')}")
+        print(f"  Segments: {len(data.get('segments', []))}")
+        print(f"  Chunks: {data.get('chunk_count', 1)}")
+        print(f"  Processing mode: {data.get('processing_mode', 'unknown')}")
+
+        if data.get("segments"):
+            print(f"\nFirst 3 segments:")
+            for i, seg in enumerate(data["segments"][:3]):
+                print(
+                    f"  {i}: {seg['start']:.1f}-{seg['end']:.1f}: {seg['text'][:50]}..."
+                )
+
+    return result.returncode == 0
+
+
+if __name__ == "__main__":
+    import time
+
+    success = test_asr_v2()
+    sys.exit(0 if success else 1)