Abkhaz-NLP-Data-Pipeline icon indicating copy to clipboard operation
Abkhaz-NLP-Data-Pipeline copied to clipboard

Published 20 hours ago • verified publisher icon danielinux7

Fine-tune a NLLB-200 model for translating

Open Bachstelze opened this issue 1 year ago • 2 comments

It is possible to use a pretrained translation model like NLLB and add the vocabulary for Abkhaz and then train it with the parallel data: https://cointegrated.medium.com/how-to-fine-tune-a-nllb-200-model-for-translating-a-new-language-a37fc706b865

Bachstelze avatar Apr 10 '24 10:04 Bachstelze

It's interesting, I assigned this issue to you. Let me know how it goes.

danielinux7 avatar Apr 10 '24 12:04 danielinux7

I am currently researching about language modeling.

Bachstelze avatar Apr 10 '24 13:04 Bachstelze