Fix ascii decode error

Author: Guanheng Zhang

beginner_source/torchtext_translation_tutorial.py

@@ -45,6 +45,7 @@
 from torchtext.vocab import Vocab
 from torchtext.utils import download_from_url, extract_archive
 import io
+from torchtext.utils import unicode_csv_reader
 
 url_base = 'https://raw.githubusercontent.com/multi30k/dataset/master/data/task1/raw/'
 train_urls = ('train.de.gz', 'train.en.gz')
@@ -61,8 +62,8 @@
 def build_vocab(filepath, tokenizer):
   counter = Counter()
   with io.open(filepath, encoding="utf8") as f:
-    for string_ in f:
-      counter.update(tokenizer(string_))
+    for string_ in unicode_csv_reader(f):
+      counter.update(tokenizer(" ".join(string_)))
   return Vocab(counter, specials=['<unk>', '<pad>', '<bos>', '<eos>'])
 
 de_vocab = build_vocab(train_filepaths[0], de_tokenizer)