from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
from torchtext.datasets import multi30k, Multi30k
from typing import Iterable, List
# pip install torchtext -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn
# We need to modify the URLs for the dataset since the links to the original dataset are broken
# Refer to https://github.com/pytorch/text/issues/1756#issuecomment-1163664163 for more info
multi30k.URL["train"] = "https://raw.githubusercontent.com/neychev/small_DL_repo/master/datasets/Multi30k/training.tar.gz"
multi30k.URL["valid"] = "https://raw.githubusercontent.com