From bbea0265f160b0180df5e7cf9ce1bc6492f06d3a Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 19:17:26 +0800
Subject: [PATCH] update
---
funasr/datasets/large_datasets/utils/tokenize.py | 4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 53f0536..6ecfb2b 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -58,10 +58,12 @@
# enable preset hotword detect in sampling
pre_index = None
for hw in hw_config['pre_hwlist']:
- _find = data['text'].find(hw)
+ hw = " ".join(seg_tokenize(hw, seg_dict))
+ _find = " ".join(text).find(hw)
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
--
Gitblit v1.9.1