Italian to East Slavic languages translation model translate-tc-big-it-zle

pip install transformers sentencepiece torch

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

repo = "WindyTranslate/translate-tc-big-it-zle"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSeq2SeqLM.from_pretrained(repo)

# Several target languages: start each input with a target token such as >>xxx<<.
# The valid tokens are listed in the upstream model card.
batch = tok([">>xxx<< <Italian text>"], return_tensors="pt", padding=True)
print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True)[0])

This product uses the model WindyTranslate/translate-tc-big-it-zle
(https://huggingface.co/WindyTranslate/translate-tc-big-it-zle), published by Windstorm Labs (https://windstormlabs.com).
Based on OPUS-MT model Helsinki-NLP/opus-mt-tc-big-it-zle by Helsinki-NLP (Language Technology Research Group, University of Helsinki). Licensed CC-BY-4.0.
Windstorm Labs modified the upstream weights; the model card describes what was changed.
Licensed under Creative Commons Attribution 4.0 International: https://creativecommons.org/licenses/by/4.0/