OSS Tanbou

GiNZA — analyze Japanese with spaCy and Universal Dependencies

OSS health 81
About these scores

Discovery score is an unbounded weighted, log-compressed index of stars, watchers, forks, and contributors. Growth momentum is its change over the observed period; OSS health is a 0–100 score from available repository recency, Community Health, and release data.

Stars
872
Primary language
Python
License
MIT
Repository last updated
Sep 13, 2026

Overview

GiNZA is a Python library that brings Japanese analysis based on Universal Dependencies to the spaCy framework. A single pipeline spans Sudachi tokenization, parts of speech, lemmatization, dependencies, and named entities, with CoNLL-U and MeCab-like command output.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Cover tokenization, dependencies, and entities in one pipeline

The official README documents annotations for tokenization, parts of speech, morphology, lemmas, dependency parsing, named-entity recognition, and readings. Alongside the spaCy API, the ginza command emits CoNLL-U and ginzame provides MeCab-like output, with standard and transformer models available.

Sources: [1]

For bringing Japanese NLP into the spaCy ecosystem

GiNZA fits Japanese document preprocessing, information extraction, search indexing, corpus analysis, and research prototypes that benefit from spaCy components or Universal Dependencies. Teams can evaluate it at the command line before embedding a Python pipeline.

Sources: [1]

Align Python, model downloads, GPUs, and dataset terms

The README requires Python 3.8 or later and pip and does not recommend Anaconda. For the transformer path, account for the initial model download, compatible PyTorch and CUDA versions, memory, and inference latency. The code is MIT, while models, dictionaries, and training datasets may require separate review.

Sources: [1][2]

Official sources

  1. [1]GiNZA README(2026-09-13)
  2. [2]GiNZA LICENSE(2026-09-13)
Supplemental curator note

Selected for disambiguating a place-like name with the precise combination of Japanese NLP, spaCy, and Universal Dependencies.

Growth

Growth trends · Last 30 days

872 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
37
Open PRs
0

Development activity is still being collected.

Built with

Categories and tags

GitHub data

GitHub dataView detailed GitHub data
Stars
872
Forks
63
Watchers
26
Open issues
7
Primary language
Python
License
MIT
Repository last updated
Sep 13, 2026
Report incorrect information

Tell us if any listing information is incorrect or outdated.

GiNZA Japanese NLP with spaCy | OSS Tanbou