# Multilingual corpus training

Encoder-decoder transformer model based on bigscience/mt0-small architecture, specializing in English-Italian text translation

HerBERT is a Polish pre-trained language model based on the BERT architecture, trained using dynamic whole word masking and sentence structure objectives.

A T5 model implementation for English-Portuguese translation tasks, utilizing lightweight hardware configurations, improving translation quality through enhanced tokenizers and post-processing workflows

This model is designed for translating legal texts from Swedish to Italian, incorporating multi-task learning scenarios including translation tasks and unsupervised tasks.

This model is designed for translating legal texts from German to English, based on the t5-small architecture, suitable for legal document translation tasks.

opus-mt-ee-en is a machine translation model based on the Transformer architecture, specifically designed for translating Ewe to English.

A Transformer-based machine translation model for translating Seychelles Creole (crs) to English (en)

Transformer-based Spanish(es) to Corsican(csn) machine translation model developed by Helsinki-NLP team, trained using OPUS dataset.

This is a Transformer-based machine translation model for translating from the source language (tll) to the target language (fr).

A small T5 model specialized for French to English legal text translation

This model is designed for translating legal texts from German to Spanish, trained on the t5-small architecture, suitable for professional translation tasks in the legal domain.

A Swedish-to-French machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team and trained using the OPUS dataset.