From ef894a44ad49b695876f0abc4983cea1b61981be Mon Sep 17 00:00:00 2001 From: Accusys Date: Sun, 10 May 2026 01:11:42 +0800 Subject: [PATCH] docs: update Phase 1 report with all Qdrant collections + voice embeddings fix - Fixed asrx_processor_custom.py: embeddings now passed to asrx.json - Voice embeddings (192D ECAPA-TDNN) extracted for all 1815 ASRX segments - momentry_dev_voice Qdrant collection created (1815 vectors) - Updated Phase 1 report with 6 collections, key decisions --- docs/PHASE1_COMPLETION_REPORT.md | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/docs/PHASE1_COMPLETION_REPORT.md b/docs/PHASE1_COMPLETION_REPORT.md index 35c2455..aad6538 100644 --- a/docs/PHASE1_COMPLETION_REPORT.md +++ b/docs/PHASE1_COMPLETION_REPORT.md @@ -73,10 +73,14 @@ ### Qdrant Vector Collections -| Collection | Dims | Points | Content | -|-----------|------|--------|---------| -| `momentry_dev_v1` | 768 | 3,417 | Sentence chunk embeddings | -| `momentry_dev_faces` | 512 | **5,910** | Face embeddings (8Hz CoreML) | +| Collection | Dims | Points | Content | Status | +|-----------|------|--------|---------|--------| +| `momentry_dev_v1` | 768 | 3,417 | Sentence chunk embeddings (待重embed含speaker) | ⏳ | +| `momentry_dev_stories` | 768 | 456 | Story dialogue + LLM summary | ✅ | +| `momentry_dev_faces` | 512 | 5,910 | Face embeddings (8Hz CoreML) | ✅ | +| `momentry_dev_voice` | 192 | **1,815** | Voice embeddings (ECAPA-TDNN) | ✅ | +| `story_sentence` | 768 | 0 | Story processor template (待建立) | ⏳ | +| `sentence_summary` | 768 | 0 | LLM 50字摘要 (待建立) | ⏳ | ## 4. Release Package @@ -101,6 +105,10 @@ Location: `release/phase1/v1.0.0_20260509_101337/` | VNFaceprint not used | KVC returns nil in video pipeline | | Face Qdrant separate collection | Face 512D vs chunk 768D — different dimensions | | LLM reasoning off | `--reasoning off` needed for non-empty content | +| Voice embedding (ECAPA-TDNN) | SFSpeechAnalyzer 無暴露 speaker embedding (Apple 未開放 API) | +| ASRX embeddings bug | `asrx_processor_custom.py` 遺漏傳遞 embeddings → 已修復 | +| Speaker 匹配方式 | ASR × ASRX 時間重疊 (any overlap)，99% 配對率 | +| Story chunk 分組 | 固定 15 ASR segments，228 parent chunks | ## 6. Phase 2 Preparation