fairseq-zh-en

fairseq-zh-en copied to clipboard

thanks for your sharing, but I have a problem when I process the data to get bpe data. I run wmt17_prepare.sh but I get something wrong in the test dataset,...

zhao1402072392

Pretrained model can not be loaded?

5

> [root@localhost fairseq-zh-en]# ./wmt17_generate.sh optimizing fconv for decoding decoding to tmp/wmt17_en_zh/fconv_test /root/torch/install/bin/luajit: .../install/share/lua/5.1/fairseq/models/ensemble_model.lua:134: inconsistent tensor size, expected r_ [10 x 33859], t [10 x 33859] and src [10 x 20490]...

airxiechao

could you share the pretrained model?

1

could you share the pretrained model? thanks

snakecy

Hi, did you get the reported result by only training on the News Commentary v12 dataset (0.2 million pairs)? Because I saw your preprocess script only download the news dataset....

Adoni