Balancing Latency and Flexibility: Static vs. Dynamic Decoding in Kaldi
Explore the trade‑offs between Static and Dynamic decoding in Kaldi. Learn how HCLG graphs impact ASR latency, memory usage, and grammar flexibility.
Loading…
ReadMeFeed / Community knowledge
#speech-recognition
Real questions. Useful conversations. Find the people who know your stack.
kaldiUsing Kaldi’s Online Decoder for Real‑Time Speech Recognition
Learn how to set up Kaldi’s online decoding pipeline, run a worked example with the tedlium2 recipe, and verify latency and accuracy trade-offs.
Choosing Between Hybrid HMM-DNN and End-to-End Architectures in Kaldi
A technical guide on choosing between Hybrid HMM-DNN and End-to-End architectures in Kaldi, focusing on data requirements, vocabulary flexibility, and WER validation.
Taming the HCLG Graph: Balancing Grammar Size and Decoding Speed in Kaldi
Learn how to balance the G (Grammar) component of Kaldi's HCLG graph to optimize the trade‑off between Word Error Rate (WER) and memory consumption during decoding.
Does weight pushing in HCLG graphs affect filler model transition weights?
In Kaldi's FST-based decoding architecture, the composition of H, C, L, and G transducers results in a search graph where weight pushing is applied to optimize pruning during the Viterbi beam search. This process is intended to move weights as far forward as possible toward the start of the graph. There is a specific design consideration regarding how this o
HMM Graph Compatibility Transition to End-to-End Neural Architectures
Kaldi maintains a distinct boundary between legacy HMM-based models and modern end-to-end neural architectures. Each approach requires a specific graph-processing pipeline to ensure that the feature extractor and the decoder are aligned. When transitioning a deployment from HMM-based decoding to neural architectures, the configuration of the scf file and the