A questions about decoder in seq2seq-torch

https://github.com/graykode/nlp-tutorial/blob/6e171b914ed28eb04dc9176916a99e9a996a7951/4-1.Seq2Seq/Seq2Seq-Torch.py#L92
Hi,I‘m a nlp rookie.I want to ask you a question.I read the seq2seq's paper,which use t-1 output as the t input in decoder. Your code in this line use 'SPPPPP' as the decoder input.So,is this way harm to the result?
If you see this issues, please answer me in your free time.
Although my english is poor, I still want to express my gratitude to you.

Read Seq2Seq-Torch.py around line 92 and compare the decoder-input description in the referenced seq2seq paper. Done means documenting whether the example's decoder-input handling is intentional and how it relates to the paper's training procedure.

Escrito por el modelo de indexación a partir del texto del issue.