From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
funasr/datasets/large_datasets/utils/tokenize.py | 16 ++++++++++++----
1 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index f0f0c66..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -46,17 +46,25 @@
text = data["text"]
token = []
vad = -2
-
if bpe_tokenizer is not None:
- text = bpe_tokenizer.text2tokens("".join(text))
-
+ text = bpe_tokenizer.text2tokens(" ".join(text))
if seg_dict is not None:
assert isinstance(seg_dict, dict)
text = seg_tokenize(text, seg_dict)
length = len(text)
if 'hw_tag' in data:
- hotword_indxs = sample_hotword(length, **hw_config)
+ pre_index = None
+ if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
+ # enable preset hotword detect in sampling
+ 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)]
+ break
+ hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
data['hotword_indxs'] = hotword_indxs
del data['hw_tag']
for i in range(length):
--
Gitblit v1.9.1