From 2ac38adbe5f4e1374a079e032ed4b504351a207c Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 23 四月 2024 18:08:57 +0800
Subject: [PATCH] Dev gzf exp (#1647)
---
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 3bff172..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
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