togatoga/karukan
Japanese Input Method System for Linux, Neural Kana-Kanji Conversion Engine + fcitx5 IME
This project helps Japanese Linux users type more naturally by converting phonetic input (romaji or hiragana) into kanji. It uses AI to understand surrounding text and suggest the most appropriate characters. Users get smarter, more accurate Japanese text input for their documents, messages, and applications.
234 stars.
Use this if you are a Linux user who writes in Japanese and wants an input method that learns your preferences and understands context.
Not ideal if you use operating systems other than Linux or primarily write in languages other than Japanese.
Stars
234
Forks
11
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/togatoga/karukan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
EmilStenstrom/conllu
A CoNLL-U parser that takes a CoNLL-U formatted string and turns it into a nested python dictionary.
OpenPecha/Botok
🏷 བོད་ཏོག [pʰøtɔk̚] Tibetan word tokenizer in Python
zaemyung/sentsplit
A flexible sentence segmentation library using CRF model and regex rules
taishi-i/nagisa
A Japanese tokenizer based on recurrent neural networks
natasha/razdel
Rule-based token, sentence segmentation for Russian language