pluto 4bb609049a feat: voice recognition — resemblyzer embed + cosine similarity matching ...

Implements pack/unpack_embedding, cosine_similarity, find_best_speaker_match
(max-per-speaker grouping, known/ambiguous/unknown thresholds), and embed_audio
with lazy resemblyzer import so tests run without the docker-only dependency.
10 tests passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-28 10:30:38 -05:00

..

__init__.py

feat: scaffold project structure

2026-05-28 10:22:03 -05:00

recognition.py

feat: voice recognition — resemblyzer embed + cosine similarity matching

2026-05-28 10:30:38 -05:00