From 9fcb3cc06b4e324f0913d2f61b89becc2baeef1b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 11 九月 2023 17:40:03 +0800
Subject: [PATCH] Merge pull request #932 from alibaba-damo-academy/dev_lhn
---
funasr/datasets/large_datasets/utils/tokenize.py | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 53f0536..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -54,13 +54,14 @@
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']:
- _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