Closed rickyweb closed 6 months ago
This is because the word 'no' can sometimes stand for 'number', from the word 'numero'. It is, however, an annoyance since the part of speech tagger struggles to distinguish this, and given how rare the 'numero' meaning is, I've just deleted it.
When transcribing this:
John: No, father.
I get the heteronym "number" <-> "no, father", which doesn't make any sense.
Β·π‘πͺπ―: π―π³π₯ππΌβ¬π―π΄, ππππΌ.
Funnily, its not reproducible if you discard John:
No, father. -> π―π΄, ππππΌ.
It can be reproduced with another proper name
Mr Fisher: No, father. -> Β·π₯πΌ ππ¦ππΌ: π―π³π₯ππΌβ¬π―π΄, ππππΌ.
But not with a non proper word
answers: no, father -> ππ―ππΌπ: π―π΄, ππππΌ.
the boy: no, father -> π ππΆ: π―π΄, ππππΌ.
I also get the same phenomenon if I replace father with mother:
John: No, mother -> Β·π‘πͺπ―: π―π³π₯ππΌβ¬π―π΄, π₯π³ππΌ.