From 1eacb8ae811a7e68c296523e6a8b4e72eb024aa2 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期五, 10 三月 2023 20:48:41 +0800
Subject: [PATCH] Update iterable_dataset.py
---
funasr/utils/postprocess_utils.py | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py
index 575fb90..2475548 100644
--- a/funasr/utils/postprocess_utils.py
+++ b/funasr/utils/postprocess_utils.py
@@ -6,7 +6,7 @@
def isChinese(ch: str):
- if '\u4e00' <= ch <= '\u9fff' or '\u0030' <= ch <= '\u0039':
+ if '\u4e00' <= ch <= '\u9fff' or '\u0030' <= ch <= '\u0039' or ch == '@':
return True
return False
@@ -17,6 +17,8 @@
cur = i.replace(' ', '')
cur = cur.replace('</s>', '')
cur = cur.replace('<s>', '')
+ cur = cur.replace('<unk>', '')
+ cur = cur.replace('<OOV>', '')
word_lists.append(cur)
if len(word_lists) == 0:
@@ -34,6 +36,8 @@
cur = i.replace(' ', '')
cur = cur.replace('</s>', '')
cur = cur.replace('<s>', '')
+ cur = cur.replace('<unk>', '')
+ cur = cur.replace('<OOV>', '')
word_lists.append(cur)
if len(word_lists) == 0:
@@ -144,7 +148,7 @@
else:
word = i.decode('utf-8')
- if word in ['<s>', '</s>', '<unk>']:
+ if word in ['<s>', '</s>', '<unk>', '<OOV>']:
continue
else:
middle_lists.append(word)
--
Gitblit v1.9.1