Freeze actual Google music metadata and precise speech timing diagnostics

This commit is contained in:
karl committed 2026-10-13 18:11:07 +02:00
1 parent 8b4275d9b4
commit 6353d02c04
8 files changed
+440 -1

No files matched your search

+27
View File
@@ -33,3 +33,30 @@ The dense reference samples video every two seconds and PCM in thirty-second win
- Model agreement with another implementation, synthetic document-seed scores, and this small-media benchmark each answer different questions. None is production quality certification.
Detailed provenance is in [the fixture README](../../fixtures/media/README.md). The final assessment belongs in [MEDIA-QUALITY.md](../../docs/MEDIA-QUALITY.md).
## Music metadata hypothesis diagnostic
`music_metadata` compares raw audio with the per-file maximum over real audio
and one Google-embedded metadata passage. It has no tuned weight or rejection
threshold and does not change production. `prepare` freezes actual FFprobe tags,
source hashes, default production audio windows, and all 65 existing queries
before inference. Existing plans/reports cannot be overwritten.
```powershell
cargo test --manifest-path tools/media-eval/Cargo.toml --bin music_metadata --locked
cargo run --manifest-path tools/media-eval/Cargo.toml --bin music_metadata --locked -- prepare fixtures/media .searchi/media-runtime/bin/ffmpeg.exe .searchi/media-runtime/bin/ffprobe.exe .searchi/qa/music-metadata-v1-plan.json
$env:SEARCHI_FORCE_CPU = '1'
cargo run --manifest-path tools/media-eval/Cargo.toml --bin music_metadata --locked -- run fixtures/media .searchi/media-runtime/bin/ffmpeg.exe .searchi/media-runtime/bin/ffprobe.exe .searchi/qa/music-metadata-v1-plan.json .searchi/models/embeddinggemma2 .searchi/runtime/auto/Release/searchi-gemma-worker.exe .searchi/qa/music-metadata-v1-results.json
```
The whitelist is artist, title, album, genre and composer in that fixed order,
bounded to 2048 UTF-8 bytes. Missing/blank tags produce no metadata vector;
encoder, comment, URLs and copyright boilerplate are excluded. Literal misleading
tags remain misleading evidence: this tool does not verify musical instruments
or generate a description. Metadata evidence has no invented timestamp.
This is the known two-music-file pool, not mixed production retrieval. Other-file
positives are explicitly ineligible, filters remain explicitly unsupported, and
all unfiltered negatives remain visible without abstention. Existing queries are
diagnostics rather than new held-out evidence. Unseen music with missing and
misleading tags needs independently frozen validation before deployment.