← ClaudeAtlas

cut-auditlisted

Prove a clip's cut is actually clean before it is styled or rendered. ASR cannot hear a false start — it de-duplicates immediate repeats — so this skill gates on ENERGY and SPECTRUM of the voice stem instead: stretched-word screening, syllable-budget folds, the clip-list screen, onset-vs-word ratio, spectral self-similarity (repeat scan), per-burst isolated probes, and the tail/head release audit. Use after every cut, whenever a doubled or clipped word is suspected, and whenever one caption is persistently out of sync.
vaibhav-barman/live-clipper · ★ 0 · AI & Automation · score 72
Install: claude install-skill vaibhav-barman/live-clipper
# CUT AUDIT — the transcript is not evidence > **THE ONE FACT:** an ASR language model is built to produce fluent text, so **two identical adjacent > phrases decode as one**. A clean transcript proves nothing. In the original project, **five separate > transcripts** called a cut clean that had two doubled lines in the first 20 seconds. A human found > them by listening. **Streamers restart lines constantly**, talk over game audio, and get interrupted by alerts and TTS donations. Assume there are more problems than you found. Adapted from the creator's skill. **Kept:** every gate and its measured threshold. **Changed:** all energy reads run on the **Demucs voice stem** (`a.wav` from `shortform-cutaway`), never on the mix — on the mix, a gunshot is a "syllable" and a music bed is "speech". Thresholds were measured on a talking-head mic; **re-calibrate them on your first 3–5 stream clips** and note the new values here. ## The gates, in order Run all of them. Each catches a class the others structurally cannot. Loop: any FAIL → back to the cutter with the evidence, max 2 rounds, then flag the clip for a human. ### 1. Stretched-word screen (before beats are written) Any word longer than ~1 s is an artifact: the aligner smeared one word across a hidden pause or a retake. - Flag every word with `end − start > 1.0 s`; **at a clip EDGE, probe regardless of length**; for a short function word, **> 0.55 s** is already suspicious. - Resolve each against an **RMS energy map** (4