https://github.com/Sovichea/khmer_segmenter

A zero-dependency, high-performance Khmer word segmenter using the Viterbi algorithm. Optimized for dictionary accuracy, ultra-low memory footprint, and edge deployment.

c-language dictionary-based khmer khmer-language khmer-nlp lightweight nlp portable python tokenization viterbi-algorithm word-segmentation zero-dependency zig-build-system

Last synced: 14 Jan 2026