SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

strip decoded outputs

Browse Source
This commit is contained in:
thomwolf
2019-02-04 17:35:05 +01:00
parent 01a3966bc6
commit 850da1cc36
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch_pretrained_bert/tokenization_openai.py
View File

@@ -228,5 +228,5 @@ class OpenAIGPTTokenizer(object):
def decode(self, ids, skip_special_tokens=False): def decode(self, ids, skip_special_tokens=False):
"""Converts a sequence of ids in a string.""" """Converts a sequence of ids in a string."""
tokens = self.convert_ids_to_tokens(ids, skip_special_tokens=skip_special_tokens) tokens = self.convert_ids_to_tokens(ids, skip_special_tokens=skip_special_tokens)
out_string = ''.join(tokens).replace('</w>', ' ') out_string = ''.join(tokens).replace('</w>', ' ').strip()
return out_string return out_string