Translation quality gating with decision models
Judging whether a machine translation or subtitle is accurate and fluent enough to publish or needs human post-editing.
2 public projects
SRT subtitle translator that translates with any OpenRouter LLM and asks Jev a review Noul per line to flag defects before export.
ProjectbetaPythonPre-registered paired audit of Jev on Spanish across 3,200 labelled items, plus a CLI to rerun it on your own data.
CLIresearchPython