Skip to content

Open-source AI podcast clipper. Generate vertical clips with face tracking and burned-in captions. CLI, MCP server, web app.

fix: unpack 4-value face_observations tuple (was unpacking 3 after adding cy)

Nika Siradze76d1e7b97010
diff --git a/backend/services/video_processor.py b/backend/services/video_processor.py
index 8ebc3fe..9dd732b 100644
--- a/backend/services/video_processor.py
+++ b/backend/services/video_processor.py
@@ -619,7 +619,7 @@ def _build_speaker_aware_crop(
]
cluster_votes = [0] * len(clusters)
for t in speaker_times:
- for obs_t, obs_cx, obs_fw in face_observations:
+ for obs_t, obs_cx, obs_fw, *_ in face_observations:
if abs(obs_t - t) < 1.0:
for ci, cl in enumerate(clusters):
if abs(obs_cx - cl["center_x"]) < width * 0.15: