From fa9a6cdb1eade68c258eed7297f5a8a8a5329ac6 Mon Sep 17 00:00:00 2001
From: Flute <41096447+fluteink@users.noreply.github.com>
Date: 星期三, 01 十月 2025 14:44:28 +0800
Subject: [PATCH] 更新文档和运行脚本，修复文档拼写错误 (#2688)
---
funasr/utils/load_utils.py | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index 072b578..d208f7d 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
@@ -240,10 +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