@sergiucristian03

videoMD · tier B

Cristian Sergiu · 7,874 followers · 2026-07-14 11:27 · 35s

Audio track (104.6 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 · 2.8 MB downloaded · 1 keyframes

plays

12,345

likes

287

comments

Topic

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

Keyphrases

Quando c'è tromba

gpt-4.1-nano · prompt v5 · $0.000109 · 2026-07-27 04:56

Caption

Author-written, as posted.

No caption. True for 83.6% of the corpus.

Speech (ASR)

speechit 22%

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

Quando c'è tromba se con te

rtx4090-24-02 · 27 chars · 2.6s speech of 35.8s

On-screen text (OCR)

easyocr

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

siîncă 0

rtx4090-24-02 · 8 chars · 1 frames