From c2e4e3c2e9be855277d9f4fa9cd0544892ff829a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 30 八月 2023 09:57:30 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/datasets/large_datasets/utils/tokenize.py | 5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 6ecfb2b..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -54,16 +54,15 @@
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)
if _find != -1:
- _find = text[:_find].count(" ") # bpe sometimes
+ # _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