akaza-im/akaza
Yet another Japanese IME for IBus/Linux
This tool helps Linux users type Japanese by converting kana (phonetic Japanese characters) into kanji (logographic Chinese characters) and other Japanese script. You type in kana, and it suggests the most likely kanji and other forms based on statistical models and your past usage. This is for anyone who writes Japanese on a Linux system and wants a customizable input method.
247 stars.
Use this if you need a flexible and hackable Japanese input method (IME) on Linux that allows you to generate your own language models and customize dictionaries.
Not ideal if you require an IME with extensive coverage of highly colloquial or specialized business Japanese, as its primary training data is limited to Wikipedia and Aozora Bunko.
Stars
247
Forks
10
Language
Rust
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/akaza-im/akaza"
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