From 52b36291e1a6bdac7f7f067b9e28e79b24de4c62 Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 17 七月 2023 14:24:42 +0800
Subject: [PATCH] fix hotword tokenize

---
 funasr/datasets/large_datasets/utils/tokenize.py |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index c16e1dc..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -54,9 +54,9 @@
 
     length = len(text)
     if 'hw_tag' in data:
+        pre_index = None
         if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
             # enable preset hotword detect in sampling
-            pre_index = None
             for hw in hw_config['pre_hwlist']:
                 hw = " ".join(seg_tokenize(hw, seg_dict))
                 _find = " ".join(text).find(hw)

--
Gitblit v1.9.1