Filipp Ozinov

[email protected]

Currently it don't expect special tokens inside words. You can try to replace all tokens inside words to some character - in this case it should start to correct them....

> Another workaround I'm thinking but don't know if will work is to re-train the model adding to the alphabet txt the symbols so it recognize when doing the spellchecking....

Thanks for report! Currently I'm setting locale "en_US.UTF-8" and ignore system locale. Apparently this is wrong, I'll try to fix, meanwhile you can try to install "en_US.UTF-8" locale to your...

It is possible, haven't tested it on so long words. Are you trying to spell-check RNA?

What word are you trying to fix? Is it a regular word without spaces?

Посмотрите так же на `Pro` версию, она включает в себя большую модель (~2 Гб. данных) обученную на википедии, новостях, субтитрах (не только из taiga, но и из opensubtitles.org), литературе. Исходные...

Currently I haven't checked it on windows, only linux+mac. But i'll try to fix it.

Unfortunately no win support for now. I'll try to look at it this weekend.

Uploaded to pip.