diff --git a/funasr/datasets/large_datasets/utils/hotword_utils.py b/funasr/datasets/large_datasets/utils/hotword_utils.py
index fccfea696..73f8bdd90 100644
--- a/funasr/datasets/large_datasets/utils/hotword_utils.py
+++ b/funasr/datasets/large_datasets/utils/hotword_utils.py
@@ -6,7 +6,8 @@ def sample_hotword(length,
                    sample_rate,
                    double_rate,
                    pre_prob,
-                   pre_index=None):
+                   pre_index=None,
+                   pre_hwlist=None):
         if length < hotword_min_length:
             return [-1]
         if random.random() < sample_rate:
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 3bff172a8..c16e1dc7e 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -63,7 +63,6 @@ def tokenize(data,
                 if _find != -1:
                     # _find = text[:_find].count(" ")  # bpe sometimes
                     pre_index = [_find, _find + max(hw.count(" "), 1)]
-                    # import pdb; pdb.set_trace()
                     break
         hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
         data['hotword_indxs'] = hotword_indxs