🎤 vibrato: Viterbi-based accelerated tokenizer

Sudachi in Rust 🦀 and new generation of SudachiPy

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

Japanese Morphological Analysis written in Rust

Viterbi-based accelerated tokenizer (Python wrapper)

🛥 Vaporetto is a fast and lightweight pointwise prediction based tokenizer. This is a Python wrapper for Vaporetto.

Rust bindings for the Voikko library

A compiled mecab-ipadic-neologd dictionary for vibrato

Japanese morph analyzer

Experimental morph-rs bindings for Python.

morphological box - create all combinations

Morphologically biased byte-pair encoding pre-tokenization

Klingonsk automatisk textigenkänning

Rust Klingon NLP library