This is a GPT2 model of Italian regional languages trained on collections of Italian "dialect poetry" by Luigi Bonaffini.

This is a multilingual model. Italians use the word "dialect" to describe their regional languages, but they are separate languages. And there's a lot of English in this dataset too.

The challenge of this project is to train a model to write the languages of Italy.

For those who do not know Italian, here's some (lowercase) text that you can type into the API box:

  • oggi si parla il dialetto
  • la sua poesia viene di
  • ma non sempre trova
Downloads last month
Hosted inference API
Text Generation
This model can be loaded on the Inference API on-demand.