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/tokenizer/token_id_converter.py | 4 +---
1 files changed, 1 insertions(+), 3 deletions(-)
diff --git a/funasr/tokenizer/token_id_converter.py b/funasr/tokenizer/token_id_converter.py
index 1888d75..c3fc71d 100644
--- a/funasr/tokenizer/token_id_converter.py
+++ b/funasr/tokenizer/token_id_converter.py
@@ -41,9 +41,7 @@
self.unk_symbol = unk_symbol
if self.unk_symbol not in self.token2id:
- raise RuntimeError(
- f"Unknown symbol '{unk_symbol}' doesn't exist in the token_list"
- )
+ raise RuntimeError(f"Unknown symbol '{unk_symbol}' doesn't exist in the token_list")
self.unk_id = self.token2id[self.unk_symbol]
def get_num_vocabulary_size(self) -> int:
--
Gitblit v1.9.1