jxzhanggg/nonparaSeq2seqVC_code

Redundant code that is the same in "fine-tune" and "pre-train"

jxzhanggg opened this issue · 1 comments

Part of code in both fine-tune and pre-train is the same, for example, the beam search code, decoder,
basic_layers etc. I think the code can be reorganized to be more compact.

too lazy to update this.