@kd.david88

videoMD · tier B

MTBDavid · 219 followers · 2026-07-13 05:50 · 19s

Audio track (54.5 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 · 1.2 MB downloaded · 1 keyframes

plays

267

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 33%

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

I'm focused on this.

rtx4090-24-01 · 20 chars · 1.0s speech of 19.9s

On-screen text (OCR)

easyocr

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

rtx5070-16 · 1 chars · 1 frames