Could not get the file at http://www.quest.dcs.shef.ac.uk/wmt16_files_mmt/training.tar.gz. [RequestException] None.
The error above showed up after calling the
vocab_src = build_vocab_from_iterator(
yield_tokens(train + val + test, tokenize_de, index=0),
specials=["<s>", "</s>", "<blank>", "<unk>"],
I am using Google colab to run notebook on this repo. Link to notebook: Google Colab
Thank you in advance.
The problem is from the dataset multi30k (source url: “http://www.quest.dcs.shef.ac.uk/wmt16_files_mmt/training.tar.gz”) that is not accessible right now.
torchtext.vocab.build_vocab_from_iterator() on the Google Colab notebook above is calling this dataset. (Sorry for not being specific in describing the problem)
I’m experiencing the same problem for some time, and can’t seem to find a solution to it.
I think you could use other datasets instead.