Natural Language Processing
pemistahl/lingua-rs🔥 active
The most accurate natural language detection library for Rust, suitable for short text and mixed-language text
RustApache-2.0updated Nov 5, 2026
🏆 #1,289 overall#503 of 1,077 in Natural Language Processing🔥 active this week
togatoga /karukan
Japanese Input Method System for Linux, macOS, Neural Kana-Kanji Conversion Engine
$ git clone https://github.com/togatoga/karukan.gitStars
757
757
Forks
64
64
Language
Rust
License
Apache-2.0
Created
Aug 11, 2024
2.2 years old
Last push
Nov 7, 2026
🔥 this week
Categories
More in Natural Language Processing
Natural Language Processing
metasequoiaime/chinese-ime-lm🔥 active
面向中文输入法的语言模型：语料、n-gram 统计、字级神经模型，以及判断它们好坏的评测集
🤖 Language Models
PythonGPL-3.0updated Nov 8, 2026
Natural Language Processing
daac-tools/vibrato
🎤 vibrato: Viterbi-based accelerated tokenizer
✂️ Tokenization & Preprocessing
RustApache-2.0updated Oct 25, 2026
Natural Language Processing
taishi-i/nagisa🔥 active
A Japanese tokenizer based on recurrent neural networks
✂️ Tokenization & Preprocessing
PythonMITupdated Nov 3, 2026
Natural Language Processing
daac-tools/vaporetto🔥 active
🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer
✂️ Tokenization & Preprocessing
RustApache-2.0updated Nov 3, 2026
Natural Language Processing
hankcs/HanLP🔥 active
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
🏷️ Named Entity Recognition🗂️ Text Classification
PythonApache-2.0updated Nov 7, 2026
Data from GitHub · snapshot Nov 9, 2026