← overview

@stefanidumbra

videoMD · tier B

Stefani Dumbravă ♥️ · 22 followers · 2026-07-20 11:23 · 24s

https://www.tiktok.com/@stefanidumbra/video/7664569406789324040
Audio track (75.9 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 · 493.1 KB downloaded · 1 keyframes

plays
24
likes
2
comments
0
shares
0
Topic
otherconf 0.00neutral
Fixed taxonomy enforced as a schema enum. Prose instructions did not hold, and label drift makes week-over-week comparison meaningless.
Keyphrases
Terima kasih telah menonton

gpt-4.1-nano · prompt v5 · $0.000109 · 2026-07-27 05:00

Caption
Author-written, as posted.

No caption. True for 83.6% of the corpus.

Speech (ASR)
speechid 58%
faster-whisper large-v3-turbo behind Silero VAD, then a repetition filter.

Terima kasih telah menonton!

rtx4090-24-01 · 28 chars · 7.6s speech of 24.7s

On-screen text (OCR)
easyocr
EasyOCR for Latin script, macOS Vision for Cyrillic-suspect frames.

TARGET 9 Sec

rtx4090-24-01 · 12 chars · 1 frames