laurieburchell/open-lid-dataset

add probability of the language label

ZeroneBo opened this issue · 1 comments

Hi, it's a great work!

Are there some ways to output the probability of the language label given a label? If not, could you share a script to get the probability of the given label?

Thank you for any helpful suggestions!

You can run fasttext predict-prob rather than fasttext predict. See the fasttext documentation for more details. There's a link to the fasttext documentation in the repo, so I'll leave the provided scripts as is. Hope that helps!