taishi-i/nagisa
▲ +1 ★ this week
A Japanese tokenizer based on recurrent neural networks
A tool for comparing tokenizers
$ git clone https://github.com/taishi-i/toiro.git▲ +1 ★ this week
A Japanese tokenizer based on recurrent neural networks
▲ +1 ★ this week
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.
▲ +6 ★ this week
Japanese Input Method System for Linux, macOS, Neural Kana-Kanji Conversion Engine
PyNLPl, pronounced as 'pineapple', is a Python library for Natural Language Processing. It contains various modules useful for common, and less common, NLP tasks. PyNLPl can be used for basic tasks such as the extraction of n-grams and frequency lists, and to build simple language model. There are also more complex data types and algorithms. Moreover, there are parsers for file formats common in NLP (e.g. FoLiA/Giza/Moses/ARPA/Timbl/CQL). There are also clients to interface with various NLP specific servers. PyNLPl most notably features a very extensive library for working with FoLiA XML (Format for Linguistic Annotation).
🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.
Data from GitHub · snapshot Nov 13, 2026