From f6a710efb23150b8117d27f088b2082d37ce97f9 Mon Sep 17 00:00:00 2001 From: kinghuin Date: Wed, 20 Nov 2019 16:14:29 +0800 Subject: [PATCH] debug ernie tiny reader --- paddlehub/reader/tokenization.py | 1 + 1 file changed, 1 insertion(+) diff --git a/paddlehub/reader/tokenization.py b/paddlehub/reader/tokenization.py index e65fb480..b7ee1bc5 100644 --- a/paddlehub/reader/tokenization.py +++ b/paddlehub/reader/tokenization.py @@ -183,6 +183,7 @@ class WSSPTokenizer(object): if not matched: i = 1 words.append(unk_token) + print(chars[idx]) idx += i return words -- GitLab