From 25de54910e7b48552bdba2dd655fbcd64a07668e Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 19:24:23 +0800
Subject: [PATCH] update
---
funasr/datasets/large_datasets/utils/hotword_utils.py | 3 ++-
funasr/datasets/large_datasets/utils/tokenize.py | 1 -
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/hotword_utils.py b/funasr/datasets/large_datasets/utils/hotword_utils.py
index fccfea6..73f8bdd 100644
--- a/funasr/datasets/large_datasets/utils/hotword_utils.py
+++ b/funasr/datasets/large_datasets/utils/hotword_utils.py
@@ -6,7 +6,8 @@
sample_rate,
double_rate,
pre_prob,
- pre_index=None):
+ pre_index=None,
+ pre_hwlist=None):
if length < hotword_min_length:
return [-1]
if random.random() < sample_rate:
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 3bff172..c16e1dc 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -63,7 +63,6 @@
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