接入SenseVoice模型时发生权限错误

[terryoyty]

System Info / 系統信息

Python 3.10.15
anaconda Command line client (version 1.12.3)

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

xinference, version 0.16.3

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local --host 192.168.1.209

Reproduction / 复现过程

1.启动xinference服务

2.加载SenseVoice模型

3.使用dify接入xinference模型

4.点保存发生报错

0%| | 0/1 [00:00<?, ?it/s]2024-12-02 11:25:42,460 xinference.core.model 21868 ERROR [request 1c414af2-b05d-11ef-b60b-0a6225165260] Leave transcriptions, error: Failed to load audio: ffmpeg version 2024-11-28-git-bc991ca048-full_build-www.gyan.dev Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (Rev1, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-liblc3 --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 47.101 / 59. 47.101
libavcodec 61. 26.100 / 61. 26.100
libavformat 61. 9.100 / 61. 9.100
libavdevice 61. 4.100 / 61. 4.100
libavfilter 10. 6.101 / 10. 6.101
libswscale 8. 12.100 / 8. 12.100
libswresample 5. 4.100 / 5. 4.100
libpostproc 58. 4.100 / 58. 4.100
[in#0 @ 00000183e4a00240] Error opening input: Permission denied
Error opening input file C:\Users\Terry\AppData\Local\Temp\tmph19eo8gi.
Error opening input files: Permission denied
, elapsed time: 0 s
Traceback (most recent call last):
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 95, in load_audio_text_image_video
data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\torchaudio_backend\utils.py", line 205, in load
return backend.load(uri, frame_offset, num_frames, normalize, channels_first, format, buffer_size)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\torchaudio_backend\soundfile.py", line 27, in load
return soundfile_backend.load(uri, frame_offset, num_frames, normalize, channels_first, format)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\torchaudio_backend\soundfile_backend.py", line 221, in load
with soundfile.SoundFile(filepath, "r") as file_:
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\soundfile.py", line 658, in init
self._file = self._open(file, mode_int, closefd)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\soundfile.py", line 1216, in _open
raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'C:\Users\Terry\AppData\Local\Temp\tmph19eo8gi': System error.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 242, in _load_audio_ffmpeg
out = run(cmd, capture_output=True, check=True).stdout
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\subprocess.py", line 526, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ffmpeg', '-nostdin', '-threads', '0', '-i', 'C:\Users\Terry\AppData\Local\Temp\tmph19eo8gi', '-f', 's16le', '-ac', '1', '-acodec', 'pcm_s16le', '-ar', '16000', '-']' returned non-zero exit status 4294967283.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\core\utils.py", line 78, in wrapped
ret = await func(*args, **kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\core\model.py", line 832, in transcriptions
return await self._call_wrapper_json(
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\core\model.py", line 549, in _call_wrapper_json
return await self._call_wrapper("json", fn, *args, **kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\core\model.py", line 125, in _async_wrapper
return await fn(*args, **kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\core\model.py", line 573, in _call_wrapper
ret = await asyncio.to_thread(fn, *args, **kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\asyncio\threads.py", line 25, in to_thread
return await loop.run_in_executor(None, func_call)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\concurrent\futures\thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\xinference\model\audio\funasr.py", line 99, in transcriptions
result = self._model.generate( # type: ignore
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\auto\auto_model.py", line 304, in generate
return self.inference_with_vad(input, input_len=input_len, **cfg)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\auto\auto_model.py", line 377, in inference_with_vad
res = self.inference(
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\auto\auto_model.py", line 343, in inference
res = model.inference(**batch, **kwargs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\models\fsmn_vad_streaming\model.py", line 676, in inference
audio_sample_list = load_audio_text_image_video(
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 74, in load_audio_text_image_video
return [
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 75, in
load_audio_text_image_video(
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 99, in load_audio_text_image_video
data_or_path_or_list = _load_audio_ffmpeg(data_or_path_or_list, sr=fs)
File "C:\Environments\anaconda3\envs\ASRServiceEnv\lib\site-packages\funasr\utils\load_utils.py", line 244, in _load_audio_ffmpeg
raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 2024-11-28-git-bc991ca048-full_build-www.gyan.dev Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (Rev1, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-liblc3 --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 47.101 / 59. 47.101
libavcodec 61. 26.100 / 61. 26.100
libavformat 61. 9.100 / 61. 9.100
libavdevice 61. 4.100 / 61. 4.100
libavfilter 10. 6.101 / 10. 6.101
libswscale 8. 12.100 / 8. 12.100
libswresample 5. 4.100 / 5. 4.100
libpostproc 58. 4.100 / 58. 4.100
[in#0 @ 00000183e4a00240] Error opening input: Permission denied
Error opening input file C:\Users\Terry\AppData\Local\Temp\tmph19eo8gi.
Error opening input files: Permission denied

Expected behavior / 期待表现

可以正常使用SenseVoice模型

[terryoyty]

已解决，经查是生成临时文件时发生了问题，我是在win11上部署的Xinference，可以看到官方文档中已给出提示：

delete改为False后可正常运行

[nayaku]

已解决，经查是生成临时文件时发生了问题，我是在win11上部署的Xinference，可以看到官方文档中已给出提示： delete改为False后可正常运行

我也出现这个问题，请问这个要在哪改？

[justwangweimin]

同样的问题，改哪个文件

[restron]

https://docs.python.org/zh-cn/3/library/tempfile.html
tempfile.NamedTemporaryFile
Lib\tempfile.py

[pjkpjpk]

First, confirm your virtual environment.
Within the virtual environment, execute python -c "import tempfile; print(tempfile.file)" to locate the path of the tempfile.py file.
Open the tempfile.py file, and around line 539, find the method named NamedTemporaryFile, then modify the delete parameter to False.

[robin12jbj]

亲测可行，藏的太隐蔽了😂