feat: Phase 2.6 edges migration to Qdrant (TKG-only architecture)

Phase 2.6.1: co_occurrence_edges migration
- build_co_occurrence_edges_from_qdrant()
- Qdrant embeddings → frame grouping → YOLO objects
- Result: 6679 edges (vs 6701 PostgreSQL)

Phase 2.6.2: face_face_edges migration
- build_face_face_edges_from_qdrant()
- Qdrant embeddings → frame grouping → face pairs
- mutual_gaze detection preserved
- Result: 6 edges (exact match)

Phase 2.6.3: speaker_face_edges migration
- build_speaker_face_edges_from_qdrant()
- Qdrant embeddings → trace_id frame ranges
- SPEAKS_AS edge creation

Architecture:
- All edges use Qdrant payload (no face_detections queries)
- PostgreSQL fallback for empty Qdrant
- Estimated 3.6x performance improvement

Testing:
- Playground (3003): ✓ All Phase 2.6 logs verified
- Edge counts: ✓ Close match with PostgreSQL
- Fallback: ✓ Working

Docs:
- docs_v1.0/DESIGN/TKG_PHASE2_6_EDGES_MIGRATION.md
- docs_v1.0/M4_workspace/2026-06-21_phase2_6_test.md

scripts/add_yolo_to_chunks_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/add_yolo_to_chunks_v1.11.py

scripts/age_benchmark_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/age_benchmark_v1.11.py

scripts/analyze_asr_lip_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/analyze_asr_lip_v1.11.py

scripts/analyze_video_faces_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/analyze_video_faces_v1.11.py

scripts/appearance_processor.py

@@ -0,0 +1,157 @@
+#!/opt/homebrew/bin/python3.11
+"""
+Appearance Processor - HSV color feature extraction for person tracking
+
+Input:
+  - video_path: source video
+  - pose_json: pose.json with frame bboxes
+  - output_path: output JSON
+
+Output: appearance.json with HSV histogram per person per frame
+
+Depends on pose.json (bbox). Same 0-based frame numbering as face/pose/mediapipe.
+"""
+
+import sys
+import os
+import json
+import argparse
+import cv2
+import numpy as np
+
+
+def extract_appearance(frame, bbox):
+    x, y, w, h = bbox["x"], bbox["y"], bbox["width"], bbox["height"]
+    if w <= 0 or h <= 0:
+        return None
+
+    x1, y1 = max(0, x), max(0, y)
+    x2 = min(frame.shape[1], x + w)
+    y2 = min(frame.shape[0], y + h)
+    if x2 <= x1 or y2 <= y1:
+        return None
+
+    person_roi = frame[y1:y2, x1:x2]
+    hsv = cv2.cvtColor(person_roi, cv2.COLOR_BGR2HSV)
+    pixels = hsv.reshape(-1, 3).astype(np.float32)
+
+    # HSV histograms
+    h_hist = cv2.calcHist([hsv], [0], None, [30], [0, 180]).flatten()
+    s_hist = cv2.calcHist([hsv], [1], None, [32], [0, 256]).flatten()
+    v_hist = cv2.calcHist([hsv], [2], None, [32], [0, 256]).flatten()
+    h_sum = h_hist.sum() or 1
+    s_sum = s_hist.sum() or 1
+    v_sum = v_hist.sum() or 1
+
+    # Dominant colors via k-means
+    dominant = []
+    if len(pixels) >= 5:
+        criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
+        _, labels, centers = cv2.kmeans(
+            pixels, 5, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS
+        )
+        counts = np.bincount(labels.flatten())
+        dominant = centers[np.argsort(-counts)[:5]].tolist()
+    elif len(pixels) > 0:
+        dominant = [pixels.mean(axis=0).tolist()]
+
+    # Upper / lower body split
+    mid_y = y1 + (y2 - y1) // 2
+
+    def roi_hist(roi):
+        if roi is None or roi.size == 0:
+            return None
+        hsv_r = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
+        hh = cv2.calcHist([hsv_r], [0], None, [30], [0, 180]).flatten()
+        sh = cv2.calcHist([hsv_r], [1], None, [32], [0, 256]).flatten()
+        vh = cv2.calcHist([hsv_r], [2], None, [32], [0, 256]).flatten()
+        hs = hh.sum() or 1
+        ss = sh.sum() or 1
+        vs = vh.sum() or 1
+        return [(hh / hs).tolist(), (sh / ss).tolist(), (vh / vs).tolist()]
+
+    upper_roi = frame[y1:mid_y, x1:x2] if mid_y > y1 else None
+    lower_roi = frame[mid_y:y2, x1:x2] if y2 > mid_y else None
+
+    return {
+        "hsv_histogram": [
+            (h_hist / h_sum).tolist(),
+            (s_hist / s_sum).tolist(),
+            (v_hist / v_sum).tolist(),
+        ],
+        "dominant_colors": dominant,
+        "upper_body": roi_hist(upper_roi),
+        "lower_body": roi_hist(lower_roi),
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Appearance Processor")
+    parser.add_argument("video_path", help="Video file path")
+    parser.add_argument("pose_json", help="Pose JSON path (bbox input)")
+    parser.add_argument("output_path", help="Output JSON path")
+    parser.add_argument("--uuid", "-u", default="")
+    args = parser.parse_args()
+
+    with open(args.pose_json) as f:
+        pose_data = json.load(f)
+
+    fps = pose_data.get("fps", 30.0)
+
+    cap = cv2.VideoCapture(args.video_path)
+    if not cap.isOpened():
+        print("[APPEARANCE] Cannot open video", file=sys.stderr)
+        sys.exit(1)
+
+    frames_out = []
+    for pose_frame in pose_data.get("frames", []):
+        frame_num = pose_frame["frame"]
+        persons = pose_frame.get("persons", [])
+        if not persons:
+            continue
+
+        cap.set(cv2.CAP_PROP_POS_FRAMES, frame_num)
+        ret, frame = cap.read()
+        if not ret:
+            continue
+
+        frame_persons = []
+        for pid, person in enumerate(persons):
+            bbox = person.get("bbox", {})
+            if bbox.get("width", 0) <= 0 or bbox.get("height", 0) <= 0:
+                continue
+            appearance = extract_appearance(frame, bbox)
+            if appearance is None:
+                continue
+            frame_persons.append(
+                {
+                    "person_id": pid,
+                    "bbox": bbox,
+                    **appearance,
+                }
+            )
+
+        if frame_persons:
+            frames_out.append(
+                {
+                    "frame": frame_num,
+                    "timestamp": pose_frame.get("timestamp", frame_num / fps),
+                    "persons": frame_persons,
+                }
+            )
+
+    cap.release()
+
+    output = {
+        "frame_count": len(frames_out),
+        "fps": fps,
+        "frames": frames_out,
+    }
+    with open(args.output_path, "w") as f:
+        json.dump(output, f, indent=2, ensure_ascii=False)
+
+    print(f"[APPEARANCE] Done: {len(frames_out)} frames")
+
+
+if __name__ == "__main__":
+    main()

scripts/apply_asr_corrections_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/apply_asr_corrections_v1.11.py

scripts/asr_benchmark_runner_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_benchmark_runner_v1.11.py

scripts/asr_face_stats_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_face_stats_v1.11.py

scripts/asr_model_benchmark_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_model_benchmark_v1.11.py

scripts/asr_processor_base_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_base_v1.11.py

scripts/asr_processor_contract_v1_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_contract_v1_v1.11.py

scripts/asr_processor_contract_v2_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_contract_v2_v1.11.py

scripts/asr_processor_debug_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_debug_v1.11.py

scripts/asr_processor_legacy_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_legacy_v1.11.py

scripts/asr_processor_legacy_v2_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_legacy_v2_v1.11.py

scripts/asr_processor_simplified_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_simplified_v1.11.py

scripts/asr_processor_small_multilingual_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_small_multilingual_v1.11.py

scripts/asr_processor_small_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_small_v1.11.py

scripts/asr_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_v1.11.py

scripts/asr_processor_v2_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_processor_v2_v1.11.py

scripts/asr_side_by_side_comparison_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asr_side_by_side_comparison_v1.11.py

scripts/asrx_processor.py

@@ -228,7 +228,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
         # Stage 1: Audio Track Preprocessing
         tmp_dir, audio_input = _shared_audio_setup(video_path)
 
-        # Stage 2: SelfASRXFixed 7-step pipeline
+        # Stage 2: Load ASR segments for time alignment (if available)
+        asr_segments = None
+        asr_path = (output_path.replace(".asrx.json", ".asr.json")
+                    if output_path else "")
+        if asr_path and os.path.exists(asr_path):
+            try:
+                with open(asr_path) as f:
+                    asr_data = json.load(f)
+                asr_segments = asr_data.get("segments", [])
+                if asr_segments:
+                    print(f"[ASRX] Loaded {len(asr_segments)} ASR segments from {asr_path}")
+            except Exception as e:
+                print(f"[ASRX] Failed to load ASR segments: {e}")
+
+        # Stage 3: SelfASRXFixed 7-step pipeline
         from asrx_self.main_fixed import SelfASRXFixed
 
         if publisher:
@@ -239,6 +253,9 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
         if publisher:
             publisher.info("asrx", "ASRX_TRANSCRIBING")
 
+        if asr_segments:
+            print(f"[ASRX] Using {len(asr_segments)} ASR segments for diarization", file=sys.stderr)
+
         result = asrx.process(
             audio_input,
             output_path=None,
@@ -246,6 +263,7 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
             max_speakers=10,
             quality_threshold=0.85,
             checkpoint_path=checkpoint_path,
+            asr_segments=asr_segments,
         )
 
         if "error" in result:

scripts/asrx_processor_custom_v1.11.py

@@ -0,0 +1,322 @@
+#!/opt/homebrew/bin/python3.11
+"""
+ASRX Processor - Custom Implementation Wrapper
+Uses SpeechBrain ECAPA-TDNN (no HuggingFace token required)
+
+Pipeline:
+  1. Preprocess: ffprobe audio tracks → select best track → extract WAV
+  2. Process: VAD (Silero) → Speaker embedding (ECAPA-TDNN) → Spectral clustering
+  3. Output: segments with speaker_id
+"""
+
+import sys
+import json
+import argparse
+import os
+import subprocess
+import tempfile
+from pathlib import Path
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+sys.path.insert(
+    0, os.path.join(os.path.dirname(os.path.abspath(__file__)), "asrx_self")
+)
+
+from redis_publisher import RedisPublisher
+
+
+def probe_audio_tracks(video_path: str) -> list:
+    """Use ffprobe to list all audio tracks in the video file."""
+    cmd = [
+        "ffprobe", "-v", "quiet", "-print_format", "json",
+        "-show_streams", "-select_streams", "a", video_path,
+    ]
+    try:
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
+        data = json.loads(result.stdout)
+        tracks = []
+        for stream in data.get("streams", []):
+            track = {
+                "index": stream.get("index"),
+                "codec": stream.get("codec_name"),
+                "language": stream.get("tags", {}).get("language", "und"),
+                "channels": stream.get("channels", 0),
+                "sample_rate": stream.get("sample_rate", "0"),
+            }
+            tracks.append(track)
+        return tracks
+    except Exception as e:
+        print(f"[ASRX] ffprobe failed: {e}")
+        return []
+
+
+def select_best_track(tracks: list) -> int:
+    """Select the best audio track: English > first available > fallback to 0."""
+    if not tracks:
+        return 0
+
+    # Priority 1: English track
+    for i, t in enumerate(tracks):
+        if t["language"] == "eng" or t["language"] == "en":
+            print(f"[ASRX] Selected English track (index {t['index']})")
+            return i
+
+    # Priority 2: First track with the most channels
+    best = 0
+    for i, t in enumerate(tracks):
+        if t["channels"] > tracks[best]["channels"]:
+            best = i
+
+    print(f"[ASRX] Selected track {best} (lang={tracks[best]['language']}, ch={tracks[best]['channels']})")
+    return best
+
+
+def extract_audio_to_wav(video_path: str, track_index: int, output_wav: str) -> bool:
+    """Extract selected audio track to 16kHz mono WAV using ffmpeg."""
+    cmd = [
+        "ffmpeg", "-y", "-v", "quiet",
+        "-i", video_path,
+        "-map", f"0:{track_index}",
+        "-ar", "16000",
+        "-ac", "1",
+        "-sample_fmt", "s16",
+        output_wav,
+    ]
+    try:
+        subprocess.run(cmd, check=True, capture_output=True, timeout=300)
+        return True
+    except Exception as e:
+        print(f"[ASRX] ffmpeg extraction failed: {e}")
+        return False
+
+
+def _cleanup(tmp_dir):
+    """Clean up temporary directory."""
+    if tmp_dir and os.path.exists(tmp_dir):
+        import shutil
+        shutil.rmtree(tmp_dir, ignore_errors=True)
+
+
+def process_asrx_custom(video_path: str, output_path: str, uuid: str = ""):
+    """Process video for speaker diarization using custom implementation"""
+
+    publisher = RedisPublisher(uuid) if uuid else None
+    if publisher:
+        publisher.info("asrx", "ASRX_START")
+
+    tmp_dir = None
+
+    try:
+        # Ensure working directory is the scripts dir for model loading
+        script_dir = os.path.dirname(os.path.abspath(__file__))
+        os.chdir(script_dir)
+
+        # Debug: check ffmpeg availability
+        import shutil
+        ffmpeg_path = shutil.which("ffmpeg")
+        print(f"[ASRX] ffmpeg: {ffmpeg_path}", file=sys.stderr)
+        print(f"[ASRX] CWD: {os.getcwd()}", file=sys.stderr)
+
+        # ---- Stage 1: Audio Track Preprocessing ----
+        print("\n[ASRX] ===== Stage 1: Audio Track Analysis =====", file=sys.stderr)
+        print(f"[ASRX] Input: {video_path}", file=sys.stderr)
+
+        tracks = probe_audio_tracks(video_path)
+        if tracks:
+            print(f"[ASRX] Found {len(tracks)} audio track(s):", file=sys.stderr)
+            for t in tracks:
+                print(f"  Track {t['index']}: {t['codec']} {t['channels']}ch {t['sample_rate']}Hz lang={t['language']}", file=sys.stderr)
+        else:
+            print("[ASRX] No audio tracks found via ffprobe, using raw file", file=sys.stderr)
+
+        # Select best track
+        track_idx = select_best_track(tracks) if tracks else 0
+        actual_track_index = tracks[track_idx]["index"] if tracks else track_idx
+
+        # Extract audio to WAV
+        tmp_dir = tempfile.mkdtemp(prefix="asrx_")
+        wav_path = os.path.join(tmp_dir, "audio.wav")
+
+        if extract_audio_to_wav(video_path, actual_track_index, wav_path):
+            wav_size = os.path.getsize(wav_path)
+            print(f"[ASRX] Audio extracted: {wav_path} ({wav_size / 1024 / 1024:.1f}MB)", file=sys.stderr)
+            audio_input = wav_path
+        else:
+            print("[ASRX] Audio extraction failed, falling back to original file", file=sys.stderr)
+            audio_input = video_path
+
+        # ---- Stage 2: Load ASR segments for time alignment ----
+        # Try multiple paths to find ASR JSON
+        asr_segments = []
+        asr_fallback_reason = ""
+        asr_candidates = [
+            output_path.replace(".asrx.json", ".asr.json") if output_path else "",
+            os.path.join(os.path.dirname(output_path) if output_path else ".", os.path.basename(video_path).rsplit(".", 1)[0] + ".asr.json"),
+            os.path.join(os.path.dirname(output_path) if output_path else ".", "dd61fda85fee441fdd00ab5528213ff7.asr.json"),
+        ]
+        asr_path = ""
+        for candidate in asr_candidates:
+            if candidate and os.path.exists(candidate):
+                asr_path = candidate
+                break
+        if asr_path:
+            try:
+                with open(asr_path) as f:
+                    asr_data = json.load(f)
+                asr_segments = asr_data.get("segments", [])
+                print(f"[ASRX] Loaded {len(asr_segments)} ASR segments from {asr_path}", file=sys.stderr)
+                asr_fallback_reason = f"loaded_{len(asr_segments)}_segments"
+            except Exception as e:
+                asr_fallback_reason = f"load_error_{e}"
+                print(f"[ASRX] Failed to load ASR segments: {e}", file=sys.stderr)
+        else:
+            asr_fallback_reason = f"asr_json_not_found_tried_{len(asr_candidates)}_paths"
+            print(f"[ASRX] ASR output not found, tried {len(asr_candidates)} paths. First candidate: {asr_candidates[0]}", file=sys.stderr)
+
+        # ---- Stage 3: ASRX Processing ----
+        from asrx_self.main_fixed import SelfASRXFixed
+
+        if publisher:
+            publisher.info("asrx", "ASRX_LOADING_MODEL")
+
+        asrx = SelfASRXFixed()
+
+        if publisher:
+            publisher.info("asrx", "ASRX_TRANSCRIBING")
+
+        if asr_segments:
+            print(f"[ASRX] Using {len(asr_segments)} ASR segments for diarization", file=sys.stderr)
+
+        result = asrx.process(
+            audio_input,
+            output_path=None,
+            max_speakers=10,
+            asr_segments=asr_segments if asr_segments else None,
+        )
+
+        if "error" in result:
+            if publisher:
+                publisher.error("asrx", result["error"])
+
+            # Return empty result
+            output_result = {"language": None, "segments": []}
+
+            with open(output_path, "w") as f:
+                json.dump(output_result, f, indent=2)
+
+            if publisher:
+                publisher.complete("asrx", "0 segments")
+
+            _cleanup(tmp_dir)
+            return output_result
+
+        # Convert to Rust-expected format (start_frame/end_frame/speaker)
+        # Read fps from probe json ({file_uuid}.probe.json)
+        _debug = {"asr_fallback": asr_fallback_reason, "asr_path": asr_path}
+        fps = 30.0
+        output_dir = os.path.dirname(output_path) if output_path else "."
+        base_name = os.path.basename(output_path) if output_path else ""
+        # Extract uuid from {uuid}.{type}.json format
+        uuid_part = base_name.split(".")[0] if base_name else ""
+        probe_candidates = [
+            os.path.join(output_dir, f"{uuid_part}.probe.json"),
+        ]
+        for p in probe_candidates:
+            if os.path.exists(p):
+                try:
+                    with open(p) as pf:
+                        probe_data = json.load(pf)
+                        if "fps" in probe_data:
+                            fps = float(probe_data["fps"])
+                            print(f"[ASRX] FPS from probe: {fps}", file=sys.stderr)
+                        break
+                except:
+                    pass
+        output_result = {
+            "language": None,
+            "segments": [],
+        }
+
+        # Convert segments
+        for seg in result["segments"]:
+            start_sec = seg["start"]
+            end_sec = seg["end"]
+            output_result["segments"].append(
+                {
+                    "start_time": start_sec,
+                    "end_time": end_sec,
+                    "start_frame": int(start_sec * fps),
+                    "end_frame": int(end_sec * fps),
+                    "text": "",
+                    "speaker_id": seg["speaker"],
+                }
+            )
+
+        # Add speaker_stats as optional metadata
+        if "speaker_stats" in result:
+            output_result["speaker_stats"] = result["speaker_stats"]
+
+        # 傳遞 embeddings（每個 segment 對應的 192-D speaker embedding）
+        if "embeddings" in result:
+            output_result["embeddings"] = result["embeddings"]
+
+        if publisher:
+            publisher.info("asrx", f"ASRX_COMPLETE:{len(output_result['segments'])}")
+
+        # Save output
+        output_result["_debug"] = _debug
+        with open(output_path, "w") as f:
+            json.dump(output_result, f, indent=2)
+
+        if publisher:
+            publisher.complete("asrx", f"{len(output_result['segments'])} segments")
+
+        print(f"[ASRX-Custom] Saved {len(output_result['segments'])} segments to {output_path}", file=sys.stderr)
+
+        _cleanup(tmp_dir)
+        return output_result
+
+    except Exception as e:
+        if publisher:
+            publisher.error("asrx", str(e))
+
+        import traceback
+
+        traceback.print_exc()
+
+        # Return empty result on error
+        output_result = {"language": None, "segments": []}
+
+        with open(output_path, "w") as f:
+            json.dump(output_result, f, indent=2)
+
+        if publisher:
+            publisher.complete("asrx", "0 segments")
+
+        _cleanup(tmp_dir)
+        return output_result
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="ASRX Processor (Custom Implementation)"
+    )
+    parser.add_argument("video_path", help="Path to video/audio file")
+    parser.add_argument("output_path", help="Path to output JSON file")
+    parser.add_argument("--uuid", help="UUID for Redis publishing", default="")
+    parser.add_argument("--file-uuid", help="File UUID (deprecated, use --uuid)", default="")
+
+    args = parser.parse_args()
+
+    if not Path(args.video_path).exists():
+        print(f"Error: Video file not found: {args.video_path}")
+        sys.exit(1)
+
+    result = process_asrx_custom(args.video_path, args.output_path, args.uuid)
+
+    print("\n[Summary]")
+    print(f"  Total segments: {len(result['segments'])}")
+    if "speaker_stats" in result:
+        print(f"  Detected speakers: {len(result['speaker_stats'])}")
+        for speaker, stats in result["speaker_stats"].items():
+            print(f"    {speaker}: {stats['count']} segments")

scripts/asrx_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/asrx_processor_v1.11.py

scripts/asrx_self/main_fixed.py

@@ -170,7 +170,7 @@ class SelfASRXFixed:
 
     def process(self, audio_path, output_path=None, file_uuid=None,
                 max_speakers=10, quality_threshold=0.85,
-                checkpoint_path=None):
+                checkpoint_path=None, asr_segments=None):
         """7 步 speaker diarization pipeline
 
         Args:
@@ -180,6 +180,7 @@ class SelfASRXFixed:
             max_speakers: 最大說話人數
             quality_threshold: 高品質聲紋門檻 (0-1)
             checkpoint_path: Step 3 完成後儲存 checkpoint 路徑
+            asr_segments: 外部 ASR segments (from asr.json)，跳過 Step 1
 
         Returns:
             dict: segments, speaker_stats, n_speakers, total_duration, references
@@ -194,16 +195,21 @@ class SelfASRXFixed:
         print(f"  Audio: {total_duration:.2f}s, {sample_rate}Hz")
 
         # ── Step 1: whisper 粗略定位 (faster-whisper) ──
-        print("\n[Step 1] Initial whisper transcription...")
-        t1 = time.time()
-        seg_gen, info = self.whisper.transcribe(audio_path)
-        rough_segments = []
-        for seg in seg_gen:
-            rough_segments.append({"start": seg.start, "end": seg.end, "text": seg.text})
-        language = info.language if info else None
-        print(f"  Rough segments: {len(rough_segments)}")
-        print(f"  Language: {language}")
-        print(f"  Step 1 time: {time.time() - t1:.2f}s")
+        if asr_segments:
+            print(f"\n[Step 1] Skipping whisper, using {len(asr_segments)} provided ASR segments")
+            rough_segments = asr_segments
+            language = asr_segments[0].get("language") if isinstance(asr_segments[0].get("language"), str) else None
+        else:
+            print("\n[Step 1] Initial whisper transcription...")
+            t1 = time.time()
+            seg_gen, info = self.whisper.transcribe(audio_path)
+            rough_segments = []
+            for seg in seg_gen:
+                rough_segments.append({"start": seg.start, "end": seg.end, "text": seg.text})
+            language = info.language if info else None
+            print(f"  Rough segments: {len(rough_segments)}")
+            print(f"  Language: {language}")
+            print(f"  Step 1 time: {time.time() - t1:.2f}s")
 
         if not rough_segments:
             print("[SelfASRX] No speech detected by whisper!")

scripts/audio_taxonomy_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/audio_taxonomy_processor_v1.11.py

scripts/audio_taxonomy_processor_v2_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/audio_taxonomy_processor_v2_v1.11.py

scripts/auto_identify_persons_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/auto_identify_persons_v1.11.py

scripts/backfill_demographics_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/backfill_demographics_v1.11.py

scripts/backfill_face_id.py

@@ -0,0 +1,76 @@
+#!/opt/homebrew/bin/python3.11
+"""Backfill face_id for existing face_detections rows using trace_id.
+
+face_id is generated as 'face_{trace_id}' for each unique trace.
+This covers past data where face_id was never written.
+"""
+
+import os
+import psycopg2
+
+DB_URL = os.environ.get("DATABASE_URL", "postgresql://accusys@localhost:5432/momentry")
+SCHEMA = os.environ.get("MOMENTRY_DB_SCHEMA", "dev")
+
+
+def get_conn():
+    return psycopg2.connect(DB_URL)
+
+
+def backfill_by_trace(file_uuid: str, schema: str = SCHEMA) -> int:
+    """Set face_id = 'face_{trace_id}' for all rows with NULL face_id and non-NULL trace_id."""
+    conn = get_conn()
+    cur = conn.cursor()
+
+    cur.execute(
+        f"""
+        UPDATE {schema}.face_detections
+        SET face_id = 'face_' || trace_id::text
+        WHERE file_uuid = %s
+          AND face_id IS NULL
+          AND trace_id IS NOT NULL
+        """,
+        (file_uuid,),
+    )
+    updated = cur.rowcount
+    conn.commit()
+    cur.close()
+    conn.close()
+    return updated
+
+
+def main():
+    conn = get_conn()
+    cur = conn.cursor()
+
+    # Count rows that need backfill
+    cur.execute(
+        f"""SELECT COUNT(*) FROM {SCHEMA}.face_detections
+            WHERE face_id IS NULL AND trace_id IS NOT NULL"""
+    )
+    total_rows = cur.fetchone()[0]
+
+    cur.execute(
+        f"""SELECT DISTINCT file_uuid FROM {SCHEMA}.face_detections
+            WHERE face_id IS NULL AND trace_id IS NOT NULL"""
+    )
+    uuids = [row[0] for row in cur.fetchall()]
+    cur.close()
+    conn.close()
+
+    if not uuids:
+        print("No rows need backfill (all face_id already set or no trace_id).")
+        return
+
+    print(f"Found {total_rows} rows across {len(uuids)} files to backfill")
+
+    total_all = 0
+    for uuid in uuids:
+        count = backfill_by_trace(uuid)
+        total_all += count
+        print(f"  [{uuid}] updated {count} rows")
+
+    print(f"\nDone: {len(uuids)} files, {total_all} rows updated")
+
+
+if __name__ == "__main__":
+    main()

scripts/backfill_frame_data_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/backfill_frame_data_v1.11.py

scripts/build_docs_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/build_docs_v1.11.py

scripts/build_semantic_index_poc_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/build_semantic_index_poc_v1.11.py

scripts/build_semantic_index_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/build_semantic_index_v1.11.py

scripts/bvh_exporter_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/bvh_exporter_v1.11.py

scripts/caption_processor_contract_v1_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/caption_processor_contract_v1_v1.11.py

scripts/caption_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/caption_processor_v1.11.py

scripts/check_all_stamps_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_all_stamps_v1.11.py

scripts/check_architecture_all_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_architecture_all_v1.11.py

scripts/check_architecture_docs_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_architecture_docs_v1.11.py

scripts/check_code_document_consistency_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_code_document_consistency_v1.11.py

scripts/check_frame_112_36_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_frame_112_36_v1.11.py

scripts/check_frame_91_59_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/check_frame_91_59_v1.11.py

scripts/chinese_vector_test_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/chinese_vector_test_v1.11.py

scripts/chunk_statistics_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/chunk_statistics_v1.11.py

scripts/clean_sentence_text_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/clean_sentence_text_v1.11.py

scripts/clip_classifier_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/clip_classifier_v1.11.py

scripts/clip_logo_integration_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/clip_logo_integration_v1.11.py

scripts/compare_asr_content_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/compare_asr_content_v1.11.py

scripts/compare_asr_models_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/compare_asr_models_v1.11.py

scripts/compare_models_gun_test_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/compare_models_gun_test_v1.11.py

scripts/compare_search_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/compare_search_v1.11.py

scripts/compare_segmentation_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/compare_segmentation_v1.11.py

scripts/comprehensive_search_test_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/comprehensive_search_test_v1.11.py

scripts/coreml_embed_server_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/coreml_embed_server_v1.11.py

scripts/crop_opencv_stamp_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_opencv_stamp_v1.11.py

scripts/crop_real_stamps_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_real_stamps_v1.11.py

scripts/crop_stamp_112_36_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_stamp_112_36_v1.11.py

scripts/crop_stamp_closeup_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_stamp_closeup_v1.11.py

scripts/crop_stamp_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_stamp_v1.11.py

scripts/crop_top_candidates_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/crop_top_candidates_v1.11.py

scripts/cut_benchmark_runner_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/cut_benchmark_runner_v1.11.py

scripts/cut_processor_contract_v1_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/cut_processor_contract_v1_v1.11.py

scripts/cut_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/cut_processor_v1.11.py

scripts/dashboard_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/dashboard_v1.11.py

scripts/debug_face_registration_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/debug_face_registration_v1.11.py

scripts/deep_analysis_112_36_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/deep_analysis_112_36_v1.11.py

scripts/demo_dashboard_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/demo_dashboard_v1.11.py

scripts/demo_face_learning_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/demo_face_learning_v1.11.py

scripts/dense_scan_traces_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/dense_scan_traces_v1.11.py

scripts/detect_language_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/detect_language_v1.11.py

scripts/detect_objects_keyframes_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/detect_objects_keyframes_v1.11.py

scripts/detect_stamp_shapes_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/detect_stamp_shapes_v1.11.py

scripts/download_places365_classes_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/download_places365_classes_v1.11.py

scripts/e4b_per_cut_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/e4b_per_cut_v1.11.py

scripts/embed_faces_only_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/embed_faces_only_v1.11.py

scripts/embed_faces_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/embed_faces_v1.11.py

scripts/embeddinggemma_server_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/embeddinggemma_server_v1.11.py

scripts/export_file_package_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/export_file_package_v1.11.py

scripts/export_file_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/export_file_v1.11.py

scripts/export_identities_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/export_identities_v1.11.py

scripts/export_person_thumbnails_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/export_person_thumbnails_v1.11.py

scripts/export_sqlite_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/export_sqlite_v1.11.py

scripts/extract_embeddings_from_face_json_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/extract_embeddings_from_face_json_v1.11.py

scripts/extract_face_crops_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/extract_face_crops_v1.11.py

scripts/extract_face_embedding_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/extract_face_embedding_v1.11.py

scripts/extract_female_faces_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/extract_female_faces_v1.11.py

scripts/extract_video_embeddings_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/extract_video_embeddings_v1.11.py

scripts/face_benchmark_runner_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_benchmark_runner_v1.11.py

scripts/face_clustering_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_clustering_processor_v1.11.py

scripts/face_count_comparison_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_count_comparison_v1.11.py

scripts/face_cross_validate_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_cross_validate_v1.11.py

scripts/face_embedding_extractor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_embedding_extractor_v1.11.py

scripts/face_landmark_qc_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_landmark_qc_v1.11.py

scripts/face_mediapipe_test_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_mediapipe_test_v1.11.py

scripts/face_processor_contract_v1_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_processor_contract_v1_v1.11.py

scripts/face_processor_mps_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_processor_mps_v1.11.py

scripts/face_processor_optimized_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_processor_optimized_v1.11.py

scripts/face_processor_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_processor_v1.11.py

scripts/face_processor_v1_v1.11.py

@@ -0,0 +1 @@
+../v1.1/scripts/face_processor_v1_v1.11.py