taishi-i / awesome-japanese-nlp-resources
A curated list of resources dedicated to Python libraries, LLMs, dictionaries, and corpora of NLP for Japanese
☆810Updated this week
Alternatives and similar repositories for awesome-japanese-nlp-resources
Users that are interested in awesome-japanese-nlp-resources are comparing it to the libraries listed below
Sorting:
- Python version of Sudachi, a Japanese tokenizer.☆406Updated 2 years ago
- 日本語LLMまとめ - Overview of Japanese LLMs☆1,165Updated this week
- A Japanese NLP Library using spaCy as framework based on Universal Dependencies☆791Updated last year
- Pure-Python Japanese character interconverter for Hiragana, Katakana, Hankaku, and Zenkaku☆327Updated 4 months ago
- A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.☆442Updated 4 months ago
- A Japanese tokenizer based on recurrent neural networks☆399Updated last week
- BERT models for Japanese text.☆533Updated last year
- mecab-python. you can find original version here//taku910.github.io/mecab/☆557Updated 6 months ago
- Sudachi in Rust 🦀 and new generation of SudachiPy☆355Updated 2 weeks ago
- 🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.☆249Updated 2 weeks ago
- Juman++ (a Morphological Analyzer Toolkit)☆388Updated last year
- JGLUE: Japanese General Language Understanding Evaluation☆316Updated last month
- Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)☆190Updated last year
- Unidic packaged for installation via pip.☆95Updated 2 months ago
- A Japanese Tokenizer for Business☆845Updated 3 months ago
- Japanese GPT2 Generation Model☆317Updated last year
- Code for producing Japanese pretrained models provided by rinna Co., Ltd.☆581Updated 2 years ago
- 日本語OCR☆237Updated 3 years ago
- A lexicon for Sudachi☆252Updated 3 months ago
- OCR system for recognizing modern Japanese magazines☆144Updated last year
- An integrated Japanese analyzer based on foundation models☆131Updated last week
- Japanese word embedding with Sudachi and NWJC 🌿☆165Updated last year
- 📝 A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm information☆130Updated 2 years ago
- Japanese morphological analysis engine written in pure Python☆876Updated 2 months ago
- This repository is archived! The maintained MeCab can be found https://github.com/shogo82148/mecab☆256Updated 7 months ago
- JavaScript implementation of Japanese morphological analyzer☆904Updated last year
- Japanese text normalizer for mecab-neologd☆279Updated 2 months ago
- 🎤 vibrato: Viterbi-based accelerated tokenizer☆357Updated last month
- ☆817Updated this week
- BERT with SentencePiece for Japanese text.☆497Updated 4 years ago