From 2ddf9637fcaec3cd4057cfcbd8616f26ba567c36 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 17:36:07 +0800
Subject: [PATCH] update
---
funasr/datasets/large_datasets/utils/tokenize.py | 3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 68f6f49..53f0536 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -56,10 +56,9 @@
if 'hw_tag' in data:
if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
# enable preset hotword detect in sampling
- import pdb; pdb.set_trace()
pre_index = None
for hw in hw_config['pre_hwlist']:
- _find = text.find(hw)
+ _find = data['text'].find(hw)
if _find != -1:
_find = text[:_find].count(" ") # bpe sometimes
pre_index = [_find, _find + max(hw.count(" "), 1)]
--
Gitblit v1.9.1