From 3bc564c28e4ca816a3da4f7b0b595e27b28ac812 Mon Sep 17 00:00:00 2001 From: svlandeg Date: Tue, 5 Sep 2023 13:24:17 +0200 Subject: [PATCH] fix BertWordPieceTokenizer constructor call --- website/docs/usage/linguistic-features.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/usage/linguistic-features.mdx b/website/docs/usage/linguistic-features.mdx index 90f305ada..6c84762f6 100644 --- a/website/docs/usage/linguistic-features.mdx +++ b/website/docs/usage/linguistic-features.mdx @@ -1301,7 +1301,7 @@ correct type. @spacy.registry.tokenizers("bert_word_piece_tokenizer") def create_whitespace_tokenizer(vocab_file: str, lowercase: bool): def create_tokenizer(nlp): - return BertWordPieceTokenizer(nlp.vocab, vocab_file, lowercase) + return BertWordPieceTokenizer(vocab_file, lowercase=lowercase) return create_tokenizer ```