Spaces:
Sleeping
Sleeping
Commit History
-
Profile intelligence, context-aware baselines, and Mirror Feed
Core additions: - Personality synthesis with paragraph + 5 scored dimensions (PersonalitySynthesizer) - Context-specific baselines: population norms per context type → personal context average once 3+ same-context sessions exist. Eliminates false-positive coaching (e.g. high talk ratio in evaluative contexts no longer flagged as domination) - Mirror Feed: per-session highlight feed on profile page, collapsed with peek effect - Reflect tab: pre-computed session Q&A (generate_reflection_questions) - Transcript quotes extracted and passed to profile synthesis for grounded narratives - Onboarding flow (3-step, localStorage gated) - Session delta: flags dimension score changes ≥8pts after each new session - Blind spots: top 3 context gaps the mirror hasn't seen - Profile completeness bar with depth label - Context detector pipeline stage (ContextDetector via Groq) - Voice enrollment UI (EnrollView) with 1–3 round recording - Auth UI (AuthView), Supabase client, API client - SSE-based pr…d4c6e81
-
Parallel transcription, SSE reliability fixes, HistoryView optimisation
- Parallelize Whisper + pyannote in prepare job using ThreadPoolExecutor (~4 min saved) - Add voiceprint.py speaker embedding module (pyannote/embedding, 70/30 blend) - Fix SSE done message dropped on stream close (asyncio.sleep flush before break) - Add onerror fallback: fetch result from DB if SSE drops after job completes - Reset UploadView to idle state after results delivered (no stuck finalizing screen) - Keep HistoryView always mounted; re-fetch only on tab activation (stops GET flooding) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>bd77e3e
-
Dimension scoring, expanded signals, and full results UI overhaul
- Add DimensionScorer with 4 behavioral dimensions (emotional state, relational dynamics, communication effectiveness, conversation arc), each with 5 sub-scores - Expand SignalExtractor with vocal energy, speech acceleration, questions, monologue detection, vocabulary richness, silence ratio, and notable signal detection - Add baseline comparison after 3+ sessions - Update InsightGenerator to include dimensions and transcript in LLM prompt, produce conversation summary and dimension narrative - Wire dimensions through main.py pipeline and database - Overhaul ResultsView to display all new signals and dimension scores Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>b18547f
-
Better diarization with pyannote, interruption detection, conversation summary with transcript
77265ce
-
MVP working - audio analysis pipeline with Whisper, MFCC diarization, Groq insights
b2eef7c