# Japanese Text Processing

This is a Japanese sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional vector space, suitable for tasks like clustering and semantic search.

A BERT model pretrained on Japanese text using character-level tokenization, suitable for Japanese natural language processing tasks.

This is a Japanese-specific sentence embedding model based on the BERT architecture, designed to generate semantic vector representations of sentences and calculate sentence similarity.

Japanese RoBERTa model pre-trained on Aozora Bunko texts, supporting masked language modeling tasks

A customized Japanese slim version based on bert-base-multilingual-cased, maintaining original accuracy