From 5f3f194ffd459fd5ebe6ea46da5e532820a66060 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 21 七月 2023 11:24:31 +0800
Subject: [PATCH] update
---
funasr/datasets/large_datasets/utils/tokenize.py | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 53f0536..c16e1dc 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -58,9 +58,10 @@
# 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
+ # _find = text[:_find].count(" ") # bpe sometimes
pre_index = [_find, _find + max(hw.count(" "), 1)]
break
hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
--
Gitblit v1.9.1