From 28ccfbfc51068a663a80764e14074df5edf2b5ba Mon Sep 17 00:00:00 2001
From: kongdeqiang <kongdeqiang960204@163.com>
Date: 星期五, 13 三月 2026 17:41:41 +0800
Subject: [PATCH] 提交
---
funasr/utils/load_utils.py | 16 ++++++++++++++--
1 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 1d80fcf..d208f7d 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
@@ -238,10 +241,19 @@
# This launches a subprocess to decode audio while down-mixing
# and resampling as necessary. Requires the ffmpeg CLI in PATH.
# fmt: off
+ pcm_params = []
+ if file.lower().endswith('.pcm'):
+ pcm_params = [
+ "-f", "s16le",
+ "-ar", str(sr),
+ "-ac", "1"
+ ]
+
cmd = [
"ffmpeg",
"-nostdin",
"-threads", "0",
+ *pcm_params, # PCM files need input format specified before -i since PCM is raw data without headers
"-i", file,
"-f", "s16le",
"-ac", "1",
--
Gitblit v1.9.1