eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Implemented a second LLM stage for grammatical review

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-21 15:42:09 -05:00
parent ca01e46d77
commit 445329de81
13 changed files with 620 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -1,6 +1,6 @@
# Audita
Audita takes raw audio transcripts and uses an LLM to identify and fix misheard words, jargon, and domain-specific terms.
Audita takes raw audio transcripts and uses an LLM to identify and fix misheard words, jargon, domain-specific terms, and conservative readability issues.
## Development
@@ -42,9 +42,11 @@ Useful configuration can be supplied by CLI flag or environment variable:
- `AUDITA_MODEL`, default `openrouter/mistralai/mistral-small-3.2-24b-instruct`
- `AUDITA_BASE_URL`, default `https://openrouter.ai/api/v1`
- `AUDITA_MAX_SECTION_TOKENS`, default `16000`
- `AUDITA_CONFIDENCE_THRESHOLD`, default `0.60`
- `AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD`, default `0.60`
- `AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD`, default `0.60`
- `AUDITA_MAX_RETRIES`, default `3`
- `AUDITA_GLOSSARY_MAX_LLM_PASSES`, default `3`, for total glossary correction passes
- `AUDITA_GRAMMAR_MAX_LLM_PASSES`, default `3`, for total grammar/readability 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.
`AUDITA_WORK_DIR` stores per-run diagnostics while processing. Successful runs clean up their run directory unless corrections are skipped; failed runs and skipped-correction runs preserve diagnostics for debugging.