From 810046e3df4910c8f5c1a90e4b53aca45b3397e8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期一, 01 七月 2024 10:42:58 +0800
Subject: [PATCH] 优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题 (#1861)
---
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