Using pretrained En-De model?

Support
1

I am using the pretrained En-De model with the following command,

python translate.py -model …/opennmt-pretrained/averaged-10-epoch.pt -src data/train-context.txt -output data-translated/train-context-de.txt -replace_unk -verbose

However, the generated results look very weird. I am wondering if I am using the wrong command or missed some parameter to generate the translations. Any advice?

2

Did you preprocess the data using the SentencePiece model included in the model archive? This has been discussed many times on the forum.