sudachi-b-imitator-transformers 0.2.1

Imitate Japanese morphological analysis of Sudachi SplitMode.B and SudachiDict-full with a small transformers model.

Sudachi B Imitator Transformers

This package imitates Japanese morphological analysis of Sudachi SplitMode.B and SudachiDict-full with a small transformers model.
You can add tokenization and part-of-speech estimation to your environment
with only 4MB additoinal disk space if you already have transrofmers in your environment.

Installation

$ pip install sudachi_b_imitator_transformers

Usage Examples

>>> import sudachi_b_imitator_transformers
>>> tagger = sudachi_b_imitator_transformers.Tagger()
>>> sample_text = '使い方のサンプルです。'
>>> tagger.parse(sample_text)
[('使い方', '名詞'), ('の', '助詞'), ('サンプル', '名詞'), ('です', '助動詞'), ('。', '補助記号')]

Input string length must be 256 or less.