From 561bdbdfc0f8fd6234c5130fdc8631bf8e294bd8 Mon Sep 17 00:00:00 2001
From: 王梦迪 <73778524+di-osc@users.noreply.github.com>
Date: 星期四, 22 五月 2025 11:27:01 +0800
Subject: [PATCH] 通过缓存seg_dict，加快seaco_paraformer推理 (#2520)
---
funasr/utils/load_utils.py | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 072b578..c38f1d9 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -107,7 +107,8 @@
data_or_path_or_list
).squeeze() # [n_samples,]
elif data_type == "text" and tokenizer is not None:
- data_or_path_or_list = tokenizer.encode(data_or_path_or_list)
+ with open(data_or_path_or_list, "r") as f:
+ data_or_path_or_list = tokenizer.encode(f.read().strip())
elif data_type == "image": # undo
pass
elif data_type == "video": # undo
--
Gitblit v1.9.1