Skip to content

GitLab

Unverified Commit bb044462 authored by Guillem García Subies's avatar Guillem García Subies Committed by GitHub
Browse files

Update tokenization_openai.py

parent bfd75056
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
pytorch_transformers/tokenization_openai.py
View file @ bb044462
...@@ -89,9 +89,9 @@ class OpenAIGPTTokenizer(PreTrainedTokenizer): ...@@ -89,9 +89,9 @@ class OpenAIGPTTokenizer(PreTrainedTokenizer):
try: try:
import ftfy import ftfy
import spacy from spacy.lang.en import English
self.nlp = spacy.load('en', disable=['parser', 'tagger', 'ner', 'textcat']) _nlp = English()
self.fix_text = ftfy.fix_text self.nlp = nlp.Defaults.create_tokenizer(_nlp)
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.")
self.nlp = BasicTokenizer(do_lower_case=True) self.nlp = BasicTokenizer(do_lower_case=True)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment