Skip to content

Fix: Apply clean_up_tokenization_spaces in TokenizersBackend._decode #42916

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Aznix07 wants to merge 1 commit into
base: main
Choose a base branch
from
+14 −1
Open

Fix: Apply clean_up_tokenization_spaces in TokenizersBackend._decode #42916

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion src/transformers/tokenization_utils_tokenizers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -900,8 +900,21 @@ def _decode(

if isinstance(token_ids, int):
token_ids = [token_ids]
return self._tokenizer.decode(token_ids, skip_special_tokens=skip_special_tokens)

text = self._tokenizer.decode(token_ids, skip_special_tokens=skip_special_tokens)

clean_up_tokenization_spaces = (
clean_up_tokenization_spaces
if clean_up_tokenization_spaces is not None
else self.clean_up_tokenization_spaces
)

if clean_up_tokenization_spaces:
import re
text = re.sub(r'\s+([?.!,"])', r'\1', text)

return text

def _save_pretrained(
self,
save_directory: str | os.PathLike,
Expand Down