🏆 #2,801 overall#60 of 178 in Tokenization & Preprocessing

ku-nlp /jumanpp

Juman++ (a Morphological Analyzer Toolkit)

$ git clone https://github.com/ku-nlp/jumanpp.git
GitHub social preview for ku-nlp/jumanpp
Stars
413
413
This week
0 ★
0 this month
Forks
47
47
Language
C++
License
Apache-2.0
Created
Oct 11, 2016
10.1 years old
Last push
Oct 13, 2026

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 413▲ +0★ 413

Categories

GitHub topics

More in Tokenization & Preprocessing

Tokenization & Preprocessing

ikawaha/kagome🔥 active

▲ +1 ★ this week

Self-contained Japanese Morphological Analyzer written in pure Go

🧠 Natural Language Processing
GoMITupdated Nov 11, 2026
GitHub ↗★ 988⑂ 61
Tokenization & Preprocessing

daac-tools/vibrato

▲ +2 ★ this week

🎤 vibrato: Viterbi-based accelerated tokenizer

🧠 Natural Language Processing
RustApache-2.0updated Oct 25, 2026
GitHub ↗★ 430⑂ 27
Tokenization & Preprocessing

taishi-i/nagisa🔥 active

▲ +1 ★ this week

A Japanese tokenizer based on recurrent neural networks

🧠 Natural Language Processing
PythonMITupdated Nov 14, 2026
GitHub ↗★ 424⑂ 24
Tokenization & Preprocessing

daac-tools/vaporetto

▲ +2 ★ this week

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

🧠 Natural Language Processing
RustApache-2.0updated Nov 3, 2026
GitHub ↗★ 302⑂ 12
Tokenization & Preprocessing

ongjin/garu🔥 active

▲ +1 ★ this week

초경량 한국어 형태소 분석기 — 1MB 모델로 브라우저에서 실행(WASM). Ultra-lightweight Korean morphological analyzer in the browser. npm: garu-ko

🧠 Natural Language Processing
TypeScriptApache-2.0updated Nov 16, 2026
GitHub ↗★ 183⑂ 9
Tokenization & Preprocessing

polm/fugashi

▲ +1 ★ this week

A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.

🧠 Natural Language Processing
C++MITupdated Oct 24, 2025
GitHub ↗★ 538⑂ 40

Data from GitHub · snapshot Nov 16, 2026