Self-hosted Offline Speech Assessment On A 12gb Gpu

A Next.js web app that scores English read-aloud: streaming R2T2 ASR transcribes speech, word-level alignment finds mismatches, and the Jev LLM answers closed questions (same word? error type? same sentence?) to flag errors and compute a weighted total. Self-hostable on a 12GB NVIDIA GPU or via a relay demo; pronunciat

AI Tools | JavaScript · streaming-asr · speech-recognition