Write() Unicode error during Data loading about annotated-transformer HOT 2 CLOSED

.data/iwslt/de-en/IWSLT16.TED.tst2012.de-en.en.xml
.data/iwslt/de-en/IWSLT16.TED.tst2013.de-en.de.xml
---------------------------------------------------------------------------
UnicodeEncodeError                        Traceback (most recent call last)
<ipython-input-39-c069794b494b> in <module>()
     23     train, val, test = datasets.IWSLT.splits(
     24         exts=('.de', '.en'), fields=(SRC, TGT),
---> 25         filter_pred=lambda x: len(vars(x)['src']) <= MAX_LEN and
     26             len(vars(x)['trg']) <= MAX_LEN)
     27     MIN_FREQ = 2

/usr/local/lib/python2.7/dist-packages/torchtext-0.2.1-py2.7.egg/torchtext/datasets/translation.py in splits(cls, exts, fields, root, train, validation, test, **kwargs)
    136 
    137         if not os.path.exists(os.path.join(path, train) + exts[0]):
--> 138             cls.clean(path)
    139 
    140         train_data = None if train is None else cls(

/usr/local/lib/python2.7/dist-packages/torchtext-0.2.1-py2.7.egg/torchtext/datasets/translation.py in clean(path)
    156                 for doc in root.findall('doc'):
    157                     for e in doc.findall('seg'):
--> 158                         fd_txt.write(e.text.strip().decode("utf-8") + '\n')
    159 
    160         xml_tags = ['<url', '<keywords', '<talkid', '<description',

/usr/lib/python2.7/encodings/utf_8.pyc in decode(input, errors)
     14 
     15 def decode(input, errors='strict'):
---> 16     return codecs.utf_8_decode(input, errors, True)
     17 
     18 class IncrementalEncoder(codecs.IncrementalEncoder):

UnicodeEncodeError: 'ascii' codec can't encode character u'\xe4' in position 60: ordinal not in range(128)