# Large-scale corpus training

Multilingual RoBERTa large model trained on Nordic corpora, supporting Swedish, Norwegian, Danish, and English

A multilingual machine translation model based on the T5 architecture, supporting 400+ languages, trained with 250 billion tokens

RoBERTa base model pre-trained on Turkish, trained with 38GB of Turkish corpus

This is a neural machine translation model for translating from Lithuanian to English, part of the OPUS-MT project.

This is a neural machine translation model for translating Serbian-Croatian (sh) to English (en), part of the OPUS-MT project.

This is a neural machine translation model for translating from North Germanic languages (gmq) to English (en), part of the OPUS-MT project.

English-to-Spanish neural machine translation model provided by the OPUS-MT project, based on transformer-big architecture

This is a neural machine translation model for English to Italian translation, part of the OPUS-MT project, using transformer-big architecture.

This is a neural machine translation model for translating from English to North Germanic languages (including Danish, Faroese, Icelandic, Norwegian Bokmål, Norwegian Nynorsk, and Swedish), part of the OPUS-MT project.

This is a neural machine translation model for translating from English to Catalan, Occitan, and Spanish, part of the OPUS-MT project.

This is a neural machine translation model for translating from German to East Slavic languages (Belarusian, Russian, Ukrainian), part of the OPUS-MT project.

BARThez is a French sequence-to-sequence pre-trained model based on the BART architecture, particularly suitable for generative tasks such as abstractive summarization.

NorBERT is a BERT model optimized for Norwegian, developed by the Language Technology Group at the University of Oslo. It is part of the NorLM initiative, aiming to provide high-quality language models for Norwegian.

Icelandic masked language model trained on RoBERTa-base architecture using 16GB of Icelandic text data

AraBERT is an Arabic pre-trained language model based on the BERT architecture, specifically optimized for Arabic language understanding tasks.

A RoBERTa model developed for Tagalog (Filipino), trained using the TLUnified corpus, supporting Filipino NLP tasks

AraBERT is an Arabic pre-trained language model based on Google's BERT architecture, specifically designed for Arabic natural language understanding tasks.

mT5 is a multilingual text-to-text transformation model launched by Google, supporting 101 languages, pretrained on the mC4 dataset, and suitable for various NLP tasks.

This is a Transformer-based multilingual-to-English machine translation model supporting over 100 languages.

This is a Transformer-based neural machine translation model from English to multiple languages, supporting translation tasks for over 100 target languages.

SloBERTa is a monolingual BERT-like model specifically optimized for the Slovenian language, developed based on the Camembert architecture.

This is a Transformer-based multilingual machine translation model supporting translation tasks from English to multiple Indo-European languages.

This model is a fine-tuned version of the mBART-50 large model on the opus100 dataset for English to Portuguese translation tasks, supporting high-quality bilingual translation.