diff options
| author | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2021-06-27 20:25:25 +0200 |
|---|---|---|
| committer | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2021-06-27 20:25:25 +0200 |
| commit | 442eac315e4b8be19adab80fb7332d29f68c077c (patch) | |
| tree | 1084ff180e7852029918534343ec2a18b6b0485f /text_recognizer/data/iam_preprocessor.py | |
| parent | cafd6b8b10d804b3eee235652cb5218ef4a469b4 (diff) | |
Fixed bug in word pieces
Diffstat (limited to 'text_recognizer/data/iam_preprocessor.py')
| -rw-r--r-- | text_recognizer/data/iam_preprocessor.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/text_recognizer/data/iam_preprocessor.py b/text_recognizer/data/iam_preprocessor.py index b5f72da..506036e 100644 --- a/text_recognizer/data/iam_preprocessor.py +++ b/text_recognizer/data/iam_preprocessor.py @@ -89,9 +89,9 @@ class Preprocessor: self.lexicon = None if self.special_tokens is not None: - self.special_tokens += ("#", "*") - self.tokens += self.special_tokens - self.graphemes += self.special_tokens + special_tokens_ = (*self.special_tokens, "#", "*") + self.tokens += special_tokens_ + self.graphemes += special_tokens_ self.graphemes_to_index = {t: i for i, t in enumerate(self.graphemes)} self.tokens_to_index = {t: i for i, t in enumerate(self.tokens)} |