From 3c349ac0531b07239f37b81254f8568ab80e3f6a Mon Sep 17 00:00:00 2001
From: Han Zhang <45134013+holazzer@users.noreply.github.com>
Date: 星期二, 18 三月 2025 11:45:37 +0800
Subject: [PATCH] fix: use converted token_ids for alignment for sensevoice model with timestamp output (#2429)
---
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