提交 a710682a 编写于 作者: H Helin Wang

update url for wmt14 dataset

上级 9c7bed83
......@@ -23,7 +23,7 @@ __all__ = ['train', 'test', 'build_dict']
URL_DEV_TEST = 'http://www-lium.univ-lemans.fr/~schwenk/cslm_joint_paper/data/dev+test.tgz'
MD5_DEV_TEST = '7d7897317ddd8ba0ae5c5fa7248d3ff5'
# this is a small set of data for test. The original data is too large and will be add later.
URL_TRAIN = 'http://paddlepaddle.bj.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz'
URL_TRAIN = 'http://paddlepaddle.cdn.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz'
MD5_TRAIN = 'a755315dd01c2c35bde29a744ede23a6'
START = "<s>"
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册