Deploying Kaldi Chain Models with Online Decoding: A Practical Guide
Deploy Kaldi’s chain models with online decoding: a step‑by‑step guide covering feature extraction, i‑vector adaptation, endpointing, and common pitfalls.
Loading…
ReadMeFeed / Community knowledge
#chain-models
Real questions. Useful conversations. Find the people who know your stack.
kaldiChoosing LF-MMI Chain Training in Kaldi: What Actually Changes in Your Recipe
Kaldi's chain models use LF-MMI with a single compiled denominator FST instead of per-utterance lattices or frame-level alignments. Here's what the pipeline actually looks like and how to verify it.
Kaldi Chain Models: Why LF-MMI and a 3x Slower Frame Rate Changed ASR Training
Kaldi's chain models train neural networks directly with lattice-free MMI at one label per 30 ms. Here's why the reduced frame rate and denominator FST design matter, and how to set up the workflow.