Closed Vibha111094 closed 5 years ago
As I understand this involves mapping the hypotheses ids to the words in the vocabulary . Is this understanding correct?
I was able to convert it into words ,however the bert'svocabulary itself has Wordpiece representations . Anyway to solve this ?
" ". Join(hwords).replace(" ##", "")
What additional changes are required in the code so that I can see the actual summary produced for a given paragraph.