anhnh2002
commented
4 days ago It may come from the fact that your data is not clean, such as containing redundant sounds at the end of the audio
Open developeranalyser opened 5 days ago
anhnh2002
commented
4 days ago It may come from the fact that your data is not clean, such as containing redundant sounds at the end of the audio
When the model misreads a word, how many sentences containing the correct word are needed to use for finetune to correct it? The problem that occurs is that after fine tuning, it adds extra things to the end of sounds and sentences, if penalty is not used, why?