fairseq_simplifier in Mem

facebookresearch / access

Code to reproduce the experiments from the paper.

Other

101 stars 36 forks source link

fairseq_simplifier in Mem #6

Closed igormis closed 4 years ago

igormis commented 4 years ago

I am currently using the generate.py script in order to paraphrase sentences in a given input file. However, I was wondering is there a way to use the code (fairseq_simplifier) in an API-fashion, that is sentence by sentence, where the best model will be always in RAM so the output will be faster?

louismartin commented 4 years ago

Hello Igormis,

Sorry this is not implemented at the time, you would need to adapt code from fairseq/interactive.py to do that.

igormis commented 4 years ago

OK, tnx. Hope to see this feature in near time... Tnx again