# Multilingual text processing

Historical multilingual and monolingual ByT5 base model, currently supporting English (British Library corpus - books).

This is a Polish sentence embedding model based on sentence-transformers, capable of mapping text to a 768-dimensional vector space, suitable for tasks such as semantic similarity calculation.

This is a Slovak fill-mask model based on the RoBERTa architecture, suitable for processing Slovak text tasks.

A Vietnamese sentence embedding model based on sentence-transformers, mapping text to a 768-dimensional vector space, suitable for semantic search and clustering tasks.

This is a Japanese-to-Polish machine translation model based on the transformer-align architecture, developed by the Helsinki-NLP team.

A Yoruba automatic tone restoration model fine-tuned on mT5-base, trained on JW300 and Menyo-20k datasets

This is a Japanese-to-Italian machine translation model based on the transformer-align architecture, developed by the Helsinki-NLP team.

This is a compact version of distilbert-base-multilingual-cased, supporting 25 languages while maintaining the original model's accuracy.