Update tokenization_xlm.py
This commit is contained in:
committed by
GitHub
parent
f5e2ed0fd8
commit
388e3251fa
@@ -126,7 +126,7 @@ class XLMTokenizer(PreTrainedTokenizer):
|
||||
import ftfy
|
||||
from spacy.lang.en import English
|
||||
_nlp = English()
|
||||
self.nlp = nlp.Defaults.create_tokenizer(_nlp)
|
||||
self.nlp = _nlp.Defaults.create_tokenizer(_nlp)
|
||||
self.fix_text = ftfy.fix_text
|
||||
except ImportError:
|
||||
logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
|
||||
|
||||
Reference in New Issue
Block a user