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

Implemented the spoken_word LLM review module

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-25 08:12:36 -05:00
parent 92c8c371a6
commit 52d29f7228
13 changed files with 484 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@@ -4,7 +4,7 @@ Audita is a framework-first transcript correction application. The public `audit
- deterministic transcript normalization
- token-batched module orchestration
- concrete `glossary` and `homophones` modules built on reusable proposal / validator contracts
- concrete `glossary`, `homophones`, and `spoken_word` modules built on reusable proposal / validator contracts
- structured run reporting and work-dir diagnostics
The previous working implementation has been preserved as `audita_prototype` inside this repository. Its full regression suite lives under `tests/audita_prototype`.
@@ -44,8 +44,8 @@ Resolved run instance names are auto-numbered for repeats, so the default report
The default module sequence is partially implemented today:
- `glossary`, `homophones`, and the second `glossary` pass run real LLM-backed proposal and validation stages
- `spoken_word` and `grammar` remain stubs and currently propose no corrections
- `glossary`, `homophones`, the second `glossary` pass, and `spoken_word` run real LLM-backed proposal and validation stages
- `grammar` remains a stub and currently proposes no corrections
To run a custom module sequence, pass `--modules`:
@@ -77,7 +77,7 @@ audita process transcript.json --glossary glossary.yaml --output corrected.json
Without `--output`, Audita writes the corrected transcript JSON to stdout and progress logs to stderr.
`--report-json` writes a separate machine-readable run report and never mixes report data into stdout.
Useful configuration can be supplied by CLI flag or environment variable. CLI flags take precedence over environment variables. Normal runs now require `OPENROUTER_API_KEY`, because the `glossary` and `homophones` modules make real LLM calls.
Useful configuration can be supplied by CLI flag or environment variable. CLI flags take precedence over environment variables. Normal runs now require `OPENROUTER_API_KEY`, because the `glossary`, `homophones`, and `spoken_word` modules make real LLM calls.
| Environment variable | CLI flag | Default | Purpose |
| --- | --- | --- | --- |
@@ -88,6 +88,7 @@ Useful configuration can be supplied by CLI flag or environment variable. CLI fl
| `AUDITA_MAX_SECTION_TOKENS` | `--max-section-tokens` | `6144` | Maximum estimated tokens per transcript batch |
| `AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD` | `--glossary-confidence-threshold` | `0.8` | Minimum confidence required for glossary proposals to survive validation |
| `AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD` | `--homophones-confidence-threshold` | `0.8` | Minimum confidence required for homophone proposals to survive validation |
| `AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD` | `--spoken-word-confidence-threshold` | `0.8` | Minimum confidence required for spoken-word proposals to survive validation |
| `AUDITA_NORMALIZE_MAX_SEGMENT_GAP` | `--normalize-max-segment-gap` | `4.0` | Same-speaker gaps eligible for deterministic merging |
| `AUDITA_NORMALIZE_ELLIPSIS_GAP` | `--normalize-ellipsis-gap` | `3.5` | Same-speaker gaps above this value are joined with ` ... ` |
| `AUDITA_NORMALIZE_MAX_SEGMENT_DURATION` | `--normalize-max-segment-duration` | `60.0` | Maximum merged segment duration |