Added support for multiple LLM passes to correct the transcript based upon the provided glossary

This commit is contained in:
2026-04-21 13:12:08 -05:00
parent 4296e3576e
commit 7e1a3f721a
12 changed files with 306 additions and 55 deletions

View File

@@ -44,6 +44,7 @@ Useful configuration can be supplied by CLI flag or environment variable:
- `AUDITA_MAX_SECTION_TOKENS`, default `16000`
- `AUDITA_CONFIDENCE_THRESHOLD`, default `0.80`
- `AUDITA_MAX_RETRIES`, default `3`
- `AUDITA_GLOSSARY_MAX_LLM_PASSES`, default `3`, for total glossary correction passes
- `AUDITA_WORK_DIR`, default `/tmp/audita`
`AUDITA_WORK_DIR` stores per-run diagnostics while processing. Successful runs clean up their run directory unless corrections are skipped for target mismatches; failed runs and skipped-correction runs preserve diagnostics for debugging.