@diananorosian_

videoMD · tier A

diananorosian_ · 44,973 followers · 2026-07-23 10:03 · 11s

Audio track (38.6 KB), what ASR actually heard

16 kHz mono Opus. Ogg Opus does not play in Safari; Chrome and Firefox are fine.

eagle · fetched 2026-07-26 05:44 · 1.0 MB downloaded · 4 keyframes

plays

3,897

likes

comments

Topic

Fixed taxonomy enforced as a schema enum. Prose instructions did not hold, and label drift makes week-over-week comparison meaningless.

Not tagged yet; the sweep is still running.

Caption

Author-written, as posted.

No caption. True for 83.6% of the corpus.

Speech (ASR)

suspect_enen 70%

faster-whisper large-v3-turbo behind Silero VAD, then a repetition filter.

I'm getting around

rtx4090-24-01 · 18 chars · 0.8s speech of 11.6s

On-screen text (OCR)

easyocrcyrillic

EasyOCR for Latin script, macOS Vision for Cyrillic-suspect frames.

Sarea miaiei Oligan! | кан Мід! Н

rtx4090-24-01 · 6 chars · 2 frames