Expand description
Post-transcription text cleanup ( “flow”).
Two backends:
- rules (default): pure on-device regex/heuristics — no network, no model
- openrouter: LLM rewrite via chat completions (optional, explicit)
Cleanup is opt-in at the CLI/library boundary so raw ASR stays available.
Re-exports§
pub use openrouter::OpenRouterCleanup;pub use rules::RulesCleanup;
Modules§
- openrouter
- LLM-assisted cleanup via OpenRouter chat completions.
- rules
- On-device rule-based cleanup.
Structs§
- Cleanup
Result - Result of a cleanup pass.
Enums§
- Cleanup
Provider Kind - Where cleanup runs.
- Cleanup
Style - How aggressively / in what shape to clean transcript text.
- Segment
Cleanup Policy - How to treat ASR segments after cleaning the full transcript text.
Traits§
- Text
Cleanup - Pluggable cleanup backend.
Functions§
- apply_
cleanup - Apply cleanup to a full transcription result.
- apply_
cleanup_ with_ segments - Like
apply_cleanupwith explicit segment policy. - cleanup_
text - Clean a bare string (stdin / text file path) without a full transcription result.