docs(data-model): audio.wav split layout + audio_layout column; drop mic_activity.json (FR-SPK)

This commit is contained in:
iamdoubz committed 2026-07-14 12:22:56 -05:00
1 parent 32bb4057ec
commit 3d183fdd7c
1 file changed
+3 -3
+3 -3
View File
@@ -14,9 +14,8 @@ Default root: `%LOCALAPPDATA%\WhispAssist\` (user-configurable, FR-STORE-2).
│ └── spk-eres2net.onnx
└── meetings\
└── <meeting_id>\ # one folder per meeting (uuid)
├── audio.wav # canonical recording — present ONLY if "Record" was on (ADR-0009)
├── voiceprint.wav # mic-only 16kHz sample for "You" re-matching on reprocess (FR-SPK); lives/dies with audio.wav
├── mic_activity.json # Phase 3 "You" spans (mic-speech timeline) for per-stream attribution on reprocess (FR-SPK); local-only, lives/dies with audio.wav
├── audio.wav # canonical recording — present ONLY if "Record" was on (ADR-0009). Mic on → stereo split (L=mic/"You", R=loopback/"Speaker", `audio_layout=split`); mic off → summed. Playback folds to mono; export folds to dual-mono (ADR-0005 Phase 3.5)
├── voiceprint.wav # mic-only 16kHz sample for "You" re-matching on reprocess of a SUMMED recording (FR-SPK); lives/dies with audio.wav
├── transcript.json # canonical transcript (segments+speakers+timings)
├── manual_notes.json # raw user-authored notes captured live during recording
├── notes.md # the final notes document: manual notes + transcript, merged at finalize
@@ -88,6 +87,7 @@ CREATE TABLE meetings (
language TEXT, -- detected/selected language code
backend_used TEXT, -- npu|nvidia|amd|intel|cpu
model_used TEXT, -- e.g. whisper-base
audio_layout TEXT, -- split|summed|NULL; how audio.wav's channels are laid out (0009, ADR-0005 Phase 3.5)
calendar_event_id TEXT, -- FK -> calendar_events.id (nullable)
template_id TEXT, -- note-template id (T8.1, FR-NOTE-5); catalog is
-- a built-in Rust list (notes::templates), not a table