# Multi-script support

NLLB-200 distilled version with 600M parameters, supporting machine translation tasks for 200 languages

This is a Serbian (Cyrillic and Latin scripts) RoBERTa model pretrained on srWaC, suitable for downstream task fine-tuning.

An English-Japanese translation model based on the transformer-align architecture, utilizing standardized and SentencePiece preprocessing, released by the Helsinki-NLP team.

This is a Japanese-to-Hungarian machine translation model based on the transformer-align architecture, released by the Tatoeba-Challenge project.

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