From d2a7c86dc33d6def6dba44f6ed2b71e8a1644130 Mon Sep 17 00:00:00 2001 From: Malte Date: Mon, 22 Jun 2020 17:09:05 +0200 Subject: [PATCH] Check if `text` is set to avoid IndexError (#4209) Fix for https://github.com/huggingface/transformers/issues/3809 --- src/transformers/tokenization_roberta.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/transformers/tokenization_roberta.py b/src/transformers/tokenization_roberta.py index 837639eac4..381ab2b5a6 100644 --- a/src/transformers/tokenization_roberta.py +++ b/src/transformers/tokenization_roberta.py @@ -236,7 +236,7 @@ class RobertaTokenizer(GPT2Tokenizer): add_prefix_space = kwargs["add_prefix_space"] else: add_prefix_space = add_special_tokens - if add_prefix_space and not text[0].isspace(): + if add_prefix_space and len(text) > 0 and not text[0].isspace(): text = " " + text return text