Editorial question43.6K views1,035 votes0 answers4,060 following
AI-generatedKaldi beam & max‑active tuning for low‑traffic cost
For low‑traffic speech‑recognition services using Kaldi’s online decoder ( online2-wav-nnet3-latgen-faster ), the objective is to limit the real‑time factor (RTF) per utterance to a predefined cost threshold—say ≤0.04—while ensuring that the word error rate (WER) does not rise more than 2 % relative to the baseline configuration (beam = 13.0, max‑active = 50
kaldi