Reproduce “CodeVaani: A Multilingual, Voice-Based Code Learning Assistant” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jayant Havare, Srikanth Tamilselvam, Ashish Mittal, Shalaka Thorat, Soham Jadia, Varsha Apte, Ganesh Ramakrishnan
CodeVaani supports spoken code questions in learners’ languages by transcribing speech, correcting likely technical-term errors with Gemma-27B, and generating answers with Codestral-22B. In a lab study of 28 participants across nine Indian languages, participants marked 72 of 96 queries exactly correct, yielding 75% accuracy. This initial evaluation does not compare systems or establish that transcript refinement caused the result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.