Support language selection (For example, Russian). about happy-transformer HOT 6 CLOSED

Example
My sentence: Мой кот ... (My cat ...)
3 word is ест (eat)
List of possible words: ест (eat), поглощает (absorb), глотает (swallow), кушают (eats) etc.
I need to determine the probabilities of each word from the given list in the context of the phrase and make the most correct sentence.
Output: Мой кот ест (My cat eat).

from happy-transformer.

Hi @svk-man , I am taking a look at this

from happy-transformer.

Hi @adamfillion , I hope it will help you:
https://github.com/vlomme/Russian-gpt-2
https://github.com/vlarine/transformers-ru

from happy-transformer.

@svk-man A pull request is open that will handle multi-lingual support.

For now, if you use model = HappyBERT(''bert-base-multilingual-cased") then you should be able to do masked word prediction with the language of your choice (question answering may not work as intended).

from happy-transformer.

Added in #195. Now you can use any model available on Hugging Face's model distribution network for text classification, word prediction, next sentence prediction, question answering and token classification.

New release coming soon.

from happy-transformer.

It's now available in version 2.1.0 that's published to PyPi.

from happy-transformer.