Update Hugging Face Space short description

Fix critical alignment bug: pass full frame to warpAffine, not crop

Update app description

Tighten recognition: raise threshold to 0.50, add 2-hit debounce

Hold GREETING state for at least 4 s so UI always shows recognition

Update app description in pyproject.toml

Make TTS robust: fallback to espeak, catch play_sound exceptions

Replace Haar cascade with YuNet deep-learning face detector

Show face snapshot in UI for greeting and enrolling states

Fix face recognition: BGR→RGB, robust zip extraction, schema versioning

Add GREETING state so recognised faces are shown in GUI and spoken

Fix: always speak name after enrollment, even when face save fails

Fix face recognition: align faces and enroll multiple frames

Fix model extraction path for buffalo_sc v0.7 zip

Align motion API with AGENTS.md recommendations

Switch to local ONNX face recognition (no compilation, no cloud)

Replace face-recognition/dlib with AWS Rekognition

Add reachy-mini keyword tag

Initial commit