Collected sources and patterns will appear here. Add from search or the patterns library.
RawTranscription -> RichTranscription
Parse and structure metadata tags (e.g., laughter, coughing, bgm) from the raw model-generated token sequence into user-friendly text.
Problem it solves
Raw speech-to-text outputs mix literal transcription text and acoustic event markers in the same prediction sequence.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.