Subword Text Encoding for other languages than English

Hi team,

I want to know, can I use Subword Text Encoding in other languages, for example Spanish? to create an ecoder I understand I must use the SubwordTextEncoder class, but where to specify the language? or tensorflow knows how to find the subwords? I think prefix and sufix of the words. Any clue or example to ? I want to apply this to a Spanish dataset.

Thank you! :grinning:

The assignment expects you to use a word level tokenizer for the english language.

Please move your topic to General Discussions for questions outside the course material to improve odds of getting a response. Hereโ€™s the community user guide to get started.

thank y:grinning:u Balaji Ambresh