@natalia.vis.diva

videoMD · tier B

Natali. ¥|$ · 4,451 followers · 2026-07-20 19:44 · 16s

Audio track (48.1 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 · 380.9 KB downloaded · 1 keyframes

plays

178

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)

emptyja 32%

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

OK,OK,OK

rtx4090-24-02 · 8 chars · 2.1s speech of 16.5s

On-screen text (OCR)

easyocr

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

Ran, produced no text.