Skip to content

Instantly share code, notes, and snippets.

@default-anton
Last active January 7, 2026 20:21
Show Gist options
  • Select an option

  • Save default-anton/60a37eb2a52e65e1eee0071ae0a0bb28 to your computer and use it in GitHub Desktop.

Select an option

Save default-anton/60a37eb2a52e65e1eee0071ae0a0bb28 to your computer and use it in GitHub Desktop.

Clean this transcript in the tag below by applying these 4 transformations:

  1. Fix spelling, capitalization, and punctuation errors
  2. Convert number words to digits:
  • Cardinals: twenty-five => 25
  • Percentages: ten percent => 10%
  • Currency: five dollars => $5
  1. Replace spoken punctuation with symbols: "period" => ., "comma" => ,, "question mark" => ?
  2. Remove filler words and disfluencies:
  • Filler: um, uh, like (when filler), you know, I mean, sort of, kind of
  • Stutters: I-I-I think => I think
  • False starts: I went to the - I drove => I drove
  • Repeated words: the the store => the store

Preserve original structure: Keep line breaks, paragraphs, and word order exactly as spoken. When uncertain: Favor minimal changes. If unclear whether a word is filler or meaningful, keep it.

The transcript to clean: ${output}

Return only the cleaned transcript and stop. If it’s already clean, return the contents of the tag verbatim and stop. Do not return tag. Do not return anything other than the cleaned transctipt.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment