From ed25726d2992f8a395a8d4ed9bd5e85d231c471e Mon Sep 17 00:00:00 2001
From: root <root@localhost.localdomain>
Date: 星期五, 28 四月 2023 17:00:56 +0800
Subject: [PATCH] add offline websocket support
---
funasr/datasets/large_datasets/utils/tokenize.py | 10 +++++++++-
1 files changed, 9 insertions(+), 1 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index 022d321..0d2fd84 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -17,13 +17,21 @@
return word_list
def seg_tokenize(txt, seg_dict):
+ pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
out_txt = ""
for word in txt:
word = word.lower()
if word in seg_dict:
out_txt += seg_dict[word] + " "
else:
- out_txt += "<unk>" + " "
+ if pattern.match(word):
+ for char in word:
+ if char in seg_dict:
+ out_txt += seg_dict[char] + " "
+ else:
+ out_txt += "<unk>" + " "
+ else:
+ out_txt += "<unk>" + " "
return out_txt.strip().split()
def tokenize(data,
--
Gitblit v1.9.1