S.H.O.N.A.R._Desktop_Companion/backend/shonar/services/ai
2026-09-22 10:38:34 -05:00
..
.hermes-tmp.94QlWo Adopt engine jobs at startup and on 'already running'; live work outranks a saved report 2026-09-15 19:45:02 -05:00
__init__.py Summarize: LAN primary with local-Ollama rescue + in-app failure guidance 2026-09-17 21:44:02 -05:00
_llm.py Honest summarize progress from real completed work units 2026-09-18 15:42:16 -05:00
faster_whisper.py Standalone Shonar Desktop: vendor portable sources + local engine; decouple from ~/Projects/Shonar 2026-09-14 17:14:54 -05:00
model_registry.py Model registry: Large v3 speed label corrected to measured ~0.3-0.4x real-time (CPU int8 quiet-machine benchmark Sep 22: 0.27x on 300s, 0.43x on 1200s; prior '~1x' was optimistic) 2026-09-22 10:38:34 -05:00
ollama.py AI progress: honest milestone bar from closed JSON contract units 2026-09-18 15:00:04 -05:00
openai_compat.py AI progress: honest milestone bar from closed JSON contract units 2026-09-18 15:00:04 -05:00
whisper_http.py Standalone Shonar Desktop: vendor portable sources + local engine; decouple from ~/Projects/Shonar 2026-09-14 17:14:54 -05:00