From 2d2bcdcbd31dcf7b2e305d4f8b2eb728f195aae0 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 03 五月 2023 08:15:32 +0800
Subject: [PATCH] Merge pull request #445 from zhuzizyf/main
---
funasr/datasets/large_datasets/utils/tokenize.py | 18 +++++++++++++-----
1 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index d8ceff2..0d2fd84 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -17,12 +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,
@@ -41,14 +50,13 @@
if seg_dict is not None:
assert isinstance(seg_dict, dict)
- txt = forward_segment("".join(text).lower(), seg_dict)
- text = seg_tokenize(txt, seg_dict)
+ text = seg_tokenize(text, seg_dict)
length = len(text)
for i in range(length):
x = text[i]
- if i == length-1 and "punc" in data and text[i].startswith("vad:"):
- vad = x[-1][4:]
+ if i == length-1 and "punc" in data and x.startswith("vad:"):
+ vad = x[4:]
if len(vad) == 0:
vad = -1
else:
--
Gitblit v1.9.1