mekaneeky
mekaneeky
This is definitely interesting. Wonder whether gradient approaches, evolutionary algorithms or plain old linear algebra norms (Spectral, etc) and factorization would be ideal for solving this. A digression: I wonder...
Same error encountered here. Apparently using fariseq version 0.9.0 fixes that. If you want to dig deeper, it seems the fairseq.dataclass.configs lists the default option for print_alignment as False/null which...
It is possible to argue whether this is a bug or a feature, but I think it's quite counter-intuitive and should be set as a regular -foo bar not -foo:bar...
If anybody has a copy as well, please share