multilingual bert in spark nlp

232 views Asked by At

I was wondering if pre-trained multilingual Bert is available in sparknlp? As you know Bert is pre-trained for 109 languages. I was wondering if all of these languages are in spark bert too?

Thanks

1

There are 1 answers

0
Elidor00 On

As you can see from the spark nlp documentation:

Models
Spark NLP offers more than 250 pre-trained models in 46 languages.

List of languages: Afrikaans, Arabic, Armenian, Basque, Bengali, Breton, Bulgarian, Catalan, Czech, Dutch, English, Esperanto, Finnish, French, Galician, German, Greek, Hausa, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Latin, Latvian, Marathi, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Somali, Southern Sotho, Spanish, Swahili, Swedish, Tswana, Turkish, Ukrainian, Zulu

Also there is this repository which keeps the pre-trained versions of pipelines and models for the Spark NLP library.