Comment

Comment by krisoft

> Now I'm wondering if it was trained on (imperfectly) OCRed data too...

Or perhaps they inserted typos automatically in the training set as data augmentation. Tactics like that is known to increase the roboustness of some models, so why not?

parent krisoft 2 years ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton