Dictionary and Corpus are added for Bangla

[taeefnajib]

Bangla dictionary bn_dict.txt has been added to ppocr/utils/dict and corpus bn_corpus.txt has been added to ppocr/utils/corpus Details about Bangla language can be found here and here. bn_corpus.txt file contains 454788 words and bn_dict.txt file contains all the numbers, vowels, consonants, punctuation, special characters and joint letters. I would love to get your feedback on this PR. Adding Bangla to PaddleOCR is very important for me to work on Bangla text detection related projects. Thanks.

[paddle-bot[bot]]

Thanks for your contribution!

[CLAassistant]

All committers have signed the CLA.

[taeefnajib]

Any feedback from you guys?

[taeefnajib]

I thought it'd be nice to have multi-language support in PaddleOCR

[taeefnajib]

@shiyutang any feedback from you?

[alimify]

Hi there, any update on it ?

[taeefnajib]

No! They didn't merge the branch

[GreatV]

hi @taeefnajib, Would it be possible to recommit this pr to the main branch and we will merge into that branch.

[taeefnajib]

Hi @GreatV I will recommit this pr to the main branch. I think the language code for Bangladesh should be bn instead of bg (which is the code for Bulgarian) in this post. I don't see a corpus folder inside ppocr/utils. However I'll add bn_dict.txt

[taeefnajib]

@alimify I created a new PR #13373