@octavian._st1

videoMD · tier C

octavian · 192 followers · 2026-07-07 12:03 · 20s

Audio track (76.4 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 · 1.9 MB downloaded · 1 keyframes

plays

276

likes

comments

Topic

technologyconf 0.90neutralcommercial

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

Entities

CapCut

Keyphrases

use headphonesbetter experienceCapCut ID:storymasakini

gpt-4.1-nano · prompt v5 · $0.000114 · 2026-07-27 04:55

Caption

Author-written, as posted.

No caption. True for 83.6% of the corpus.

Speech (ASR)

suspect_enen 94%

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

of heaven waiting patient dogs from

rtx4090-24-01 · 35 chars · 5.2s speech of 20.8s

On-screen text (OCR)

macos-vision

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

use headphones for better experience & CapCut CapCut ID:storymasakini

m5-vision · 69 chars · 1 frames