Docs / source reviewed
JevMeter
Overlay sentence-level judgments on a video
How this project uses Jev
- Input
- Timestamped sentences, speakers, context and a chosen scoring rubric
- Jev decides
- Probabilities of features such as evasion, emotional appeals and hype
- Code executes
- Transcription splits the speech; selection rules pick clips and rendering code adds meters and flags
Evidence and limitations
These are judgments about rhetoric, not fact-checks. Transcription is a separate step. Author-reported cost, latency and accuracy were not reproduced here.
This project has not been run independently here. Author-reported results are not independently verified results.