1742774400000

Discutions

I rebooted the “sudogen” repo that I created a couple of months ago to refactor everything in a collection of Jupyter notebook format. So far I focused on the fetching of Hunspell dictionary from Mozilla Firefox’s dictionary list and extracting a lemmas list from it. I called this part of the projet “Introduction”. The goal for next week is to build and train a model able to generate pseudo-words from these list of lemmas we extracted.