Editorial question20.3K views1,551 votes0 answers3,063 following
AI-generatedChain model training diverges after switching from lattice-free MMI to standard MMI in Kaldi nnet3
We run Kaldi nnet3 chain training on a mid-size corpus and are evaluating the two documented MMI variants: lattice-free MMI (the default in most chain recipes) and standard MMI with pre-generated lattices. After switching the training objective while keeping the same acoustic model topology, iVector input, and learning-rate schedule, the objective function o
kaldi