fairseq
fairseq copied to clipboard
mBART large 50 many to many model giving incorrect long and repetitive output in Portuguese->Eng , Spanish->Eng
I am using hugging face facebook/mbart-large-50-many-to-many-mmt model for translating text to English. I observed that its giving vague and incorrect output in many instances. Few example below
Hello ! I have the same problem on en-fr dataset. Hace you been able to fix it. Thanks :)