From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/bin/tokenize_text.py | 10 +++-------
1 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/funasr/bin/tokenize_text.py b/funasr/bin/tokenize_text.py
index 0ecf2f6..8c2aae0 100755
--- a/funasr/bin/tokenize_text.py
+++ b/funasr/bin/tokenize_text.py
@@ -133,7 +133,7 @@
if not write_vocabulary:
return
-
+
## FIXME
## del duplicate add_symbols in counter
for symbol_and_id in add_symbol:
@@ -197,12 +197,8 @@
help="The verbose level of logging",
)
- parser.add_argument(
- "--input", "-i", required=True, help="Input text. - indicates sys.stdin"
- )
- parser.add_argument(
- "--output", "-o", required=True, help="Output text. - indicates sys.stdout"
- )
+ parser.add_argument("--input", "-i", required=True, help="Input text. - indicates sys.stdin")
+ parser.add_argument("--output", "-o", required=True, help="Output text. - indicates sys.stdout")
parser.add_argument(
"--field",
"-f",
--
Gitblit v1.9.1