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/utils/load_utils.py | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 1d80fcf..c38f1d9 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -86,8 +86,10 @@
): # download url to local file
data_or_path_or_list = download_from_url(data_or_path_or_list)
- if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file
+ if (isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list)) or hasattr(data_or_path_or_list, 'read'): # local file or bytes io
if data_type is None or data_type == "sound":
+ if hasattr(data_or_path_or_list, "read") and hasattr(data_or_path_or_list, "seek"):
+ data_or_path_or_list.seek(0)
# if use_ffmpeg:
# data_or_path_or_list = _load_audio_ffmpeg(data_or_path_or_list, sr=fs)
# data_or_path_or_list = torch.from_numpy(data_or_path_or_list).squeeze() # [n_samples,]
@@ -105,7 +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