Add Catalan to the languages available when pre-processing a document

[Myko-10]

Hello!

I am doing a QA system in spanish and catalan and your preprocess class is really usefull for my research.

I wanted to ask if it would be possible to add catalan to the languages available. I don't know if the languages available are the languages that nltk offers but, if I am not wrong I've seen that there is a catalan pickle too.

Thanks for taking into account this suggestion

[tstadel]

@Myko-10 is the catalan model a custom model that is publicly available? I checked the standard nltk punkt tokenizers and there seems to be no catalan included.

[danielbichuetti]

@Myko-10 It's now possible to use custom trained PunktTokenizer (unsupervised) 3948b99 on haystack.