Sudachi Language Resources

Japanese dictionaries and pre-trained models (word embeddings and language models) for natural language processing. [SudachiDict](https://github.com/WorksApplications/SudachiDict) is the dictionary for a Japanese tokenizer (morphological analyzer) [Sudachi](https://github.com/WorksApplications/Sudachi). [chiVe](https://github.com/WorksApplications/chiVe) is Japanese pretrained word embeddings (word vectors), trained using the ultra-large-scale web corpus NWJC by National Institute for Japanese Language and Linguistics, analyzed by Sudachi. [chiTra](https://github.com/WorksApplications/SudachiTra) is a library for using large-scale pre-trained language models with the Japanese tokenizer SudachiPy.