From 11f0ed89afb2ec16e022cef0ce50d11c534fe028 Mon Sep 17 00:00:00 2001
From: lyblsgo <lyblsgo@163.com>
Date: 星期一, 08 五月 2023 10:56:18 +0800
Subject: [PATCH] fix wavhead reader; modify punc input to int32; add vad/punc/offline-stream apis; modify option parser
---
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