[Info] Can this package be used for bert based models like RoBerta or m-Bert?

[geeky-programer]

Cool package.

Wanted to try this with better and newer models

[R1j1t]

Thanks @geeky-programer. You should be able to use newer packages similar to example here:

contextualSpellCheck/examples/ja_example.py

Lines 6 to 12 in dfca557

	nlp.add_pipe(
	"contextual spellchecker",
	config={
	"model_name": "cl-tohoku/bert-base-japanese-whole-word-masking",
	"max_edit_dist": 2,
	},
	)

Let me know if you face any issues. I will try my best to resolve them if any.