Update tokenization_openai.py
This commit is contained in:
committed by
GitHub
parent
562b998366
commit
f5e2ed0fd8
@@ -91,7 +91,7 @@ class OpenAIGPTTokenizer(PreTrainedTokenizer):
|
|||||||
import ftfy
|
import ftfy
|
||||||
from spacy.lang.en import English
|
from spacy.lang.en import English
|
||||||
_nlp = English()
|
_nlp = English()
|
||||||
self.nlp = nlp.Defaults.create_tokenizer(_nlp)
|
self.nlp = _nlp.Defaults.create_tokenizer(_nlp)
|
||||||
self.fix_text = ftfy.fix_text
|
self.fix_text = ftfy.fix_text
|
||||||
except ImportError:
|
except ImportError:
|
||||||
logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
|
logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
|
||||||
|
|||||||
Reference in New Issue
Block a user