I don’t think the English model would work too well for another language. Unfortunately, training a T5 model from scratch is, generally speaking, far too resource hungry for anyone without access to Google levels of compute resources.

Also, I don’t think there are any datasets for other languages of the same scale as the C4 dataset used to train T5.

Your best bet would probably be to use a pretrained multilingual model or a pretrained model for a particular language.

AI researcher, avid reader, fantasy and Sci-Fi geek, and fan of the Oxford comma. www.linkedin.com/in/t-rajapakse/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store