运行main.py遇到兼容性问题 #1
Comments
|
能提供您的config.yaml模版和ffmpeg的版本吗？ |
|
“RuntimeError: open file failed because of errno 2 on fopen: No such file or directory, file path: silero_vad\data\silero_vad.jit |
|
谢谢，是中文路径名的问题。 现在server.py和main.py都运行起来了，但一直显示加载中
|
|
解决了，因该是windows路径的斜杠问题。作者开发应该是基于MACOS的 |
这个怎么解决的？ |
应该是我修改了的代码问题。和斜杠关系不大 |
|
windows下 ffmpeg识别的问题 |
Failed to load FFmpeg6 extension。这个问题我实测不会影响到使用。 |
|
非常感谢，现在就是开启Rag后，会异常退出。。。其他都没啥问题了 |
我的不是退出，是要等5分钟左右，然后就正常运行了 |
我现在用的是ffmpeg6.1.1。
我的config.yaml配置如下：
name: 百聆（bailing）
version: 1.0
logging:
level: debug
interrupt: false
具体处理时选择的模块
selected_module:
Recorder: RecorderPyAudio
ASR: FunASR
VAD: SileroVAD
LLM: OpenAILLM
TTS: MacTTS
Player: CmdPlayer
Recorder:
RecorderPyAudio:
output_file: tmp/
ASR:
FunASR:
# model_dir: models/SenseVoiceSmall
model_dir: FunAudioLLM/SenseVoiceSmall
output_file: tmp/
VAD:
SileroVAD:
sampling_rate: 16000
threshold: 0.5
min_silence_duration_ms: 200
LLM:
OpenAILLM:
model_name: deepseek-chat
url: https://api.deepseek.com
api_key: sk-************************
TTS:
MacTTS:
voice: Tingting
output_file: tmp/
EdgeTTS:
voice: zh-CN-XiaoxiaoNeural
output_file: tmp/
GTTS:
lang: zh
output_file: tmp/
CosyvoiceTTS:
output_file: tmp/
CHATTTS:
output_file: tmp/
Player:
CmdPlayer: null
PyaudioPlayer: null
我已经用huggingface-cli命令登录了hf，运行main.py报错：
Microsoft Windows [版本 10.0.19045.4894]
(c) Microsoft Corporation。保留所有权利。
(bailing.env) C:\LLM-CLASS\开源项目测试\bailing>python main.py
2024-09-21 12:34:30,016 - torio._extension.utils - DEBUG - Loading FFmpeg6
2024-09-21 12:34:30,021 - torio._extension.utils - DEBUG - Failed to load FFmpeg6 extension.
Traceback (most recent call last):
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 116, in _find_ffmpeg_extension
ext = _find_versionsed_ffmpeg_extension(ffmpeg_ver)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 108, in _find_versionsed_ffmpeg_extension
_load_lib(lib)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 94, in load_lib
torch.ops.load_library(path)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torch_ops.py", line 1295, in load_library
ctypes.CDLL(path)
File "C:\Python312\Lib\ctypes_init.py", line 379, in init
self._handle = _dlopen(self._name, mode)
^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: Could not find module 'C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio\lib\libtorio_ffmpeg6.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
2024-09-21 12:34:30,027 - torio._extension.utils - DEBUG - Loading FFmpeg5
2024-09-21 12:34:30,078 - torio._extension.utils - DEBUG - Failed to load FFmpeg5 extension.
Traceback (most recent call last):
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 116, in _find_ffmpeg_extension
ext = _find_versionsed_ffmpeg_extension(ffmpeg_ver)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 108, in _find_versionsed_ffmpeg_extension
_load_lib(lib)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 94, in load_lib
torch.ops.load_library(path)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torch_ops.py", line 1295, in load_library
ctypes.CDLL(path)
File "C:\Python312\Lib\ctypes_init.py", line 379, in init
self._handle = _dlopen(self._name, mode)
^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: Could not find module 'C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio\lib\libtorio_ffmpeg5.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
2024-09-21 12:34:30,085 - torio._extension.utils - DEBUG - Loading FFmpeg4
2024-09-21 12:34:30,137 - torio._extension.utils - DEBUG - Failed to load FFmpeg4 extension.
Traceback (most recent call last):
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 116, in _find_ffmpeg_extension
ext = _find_versionsed_ffmpeg_extension(ffmpeg_ver)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 108, in _find_versionsed_ffmpeg_extension
_load_lib(lib)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 94, in load_lib
torch.ops.load_library(path)
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torch_ops.py", line 1295, in load_library
ctypes.CDLL(path)
File "C:\Python312\Lib\ctypes_init.py", line 379, in init
self._handle = _dlopen(self._name, mode)
^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: Could not find module 'C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio\lib\libtorio_ffmpeg4.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
2024-09-21 12:34:30,144 - torio._extension.utils - DEBUG - Loading FFmpeg
2024-09-21 12:34:30,145 - torio._extension.utils - DEBUG - Failed to load FFmpeg extension.
Traceback (most recent call last):
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 116, in _find_ffmpeg_extension
ext = _find_versionsed_ffmpeg_extension(ffmpeg_ver)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torio_extension\utils.py", line 106, in _find_versionsed_ffmpeg_extension
raise RuntimeError(f"FFmpeg{version} extension is not available.")
RuntimeError: FFmpeg extension is not available.
2024-09-21 12:34:37,859 - root - INFO - new registry table has been added: preprocessor_classes
2024-09-21 12:34:39,060 - root - INFO - new registry table has been added: adaptor_classes
2024-09-21 12:34:39,699 - root - INFO - new registry table has been added: lid_predictor_classes
{'model_dir': 'FunAudioLLM/SenseVoiceSmall', 'output_file': 'tmp/'}
funasr version: 1.1.6.
2024-09-21 12:34:43,423 - root - INFO - download models from model hub: hf
2024-09-21 12:34:43,432 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2024-09-21 12:34:44,153 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "GET /api/models/FunAudioLLM/SenseVoiceSmall/revision/main HTTP/11" 200 1665
Fetching 29 files: 100%|█████████████████████████████████████████████████████████| 29/29 [00:00<00:00, 2901.80it/s]
Detect model requirements, begin to install it: C:\Users\mhl.cache\huggingface\hub\models--FunAudioLLM--SenseVoiceSmall\snapshots\3eb3b4eeffc2f2dde6051b853983753db33e35c3\requirements.txt
install model requirements successfully
2024-09-21 12:37:08,137 - root - INFO - Loading pretrained params from C:\Users\mhl.cache\huggingface\hub\models--FunAudioLLM--SenseVoiceSmall\snapshots\3eb3b4eeffc2f2dde6051b853983753db33e35c3\model.pt
2024-09-21 12:37:08,156 - root - INFO - ckpt: C:\Users\mhl.cache\huggingface\hub\models--FunAudioLLM--SenseVoiceSmall\snapshots\3eb3b4eeffc2f2dde6051b853983753db33e35c3\model.pt
C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\funasr\train_utils\load_pretrained_model.py:38: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the defaultpickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for
weights_onlywill be flipped toTrue. This limits the functions that couldbe executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via
torch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.src_state = torch.load(path, map_location=map_location)
2024-09-21 12:37:09,109 - root - INFO - scope_map: ['module.', 'None']
2024-09-21 12:37:09,110 - root - INFO - excludes: None
2024-09-21 12:37:09,243 - root - INFO - Loading ckpt: C:\Users\mhl.cache\huggingface\hub\models--FunAudioLLM--SenseVoiceSmall\snapshots\3eb3b4eeffc2f2dde6051b853983753db33e35c3\model.pt, status:
2024-09-21 12:37:09,263 - httpx - DEBUG - load_ssl_context verify=True cert=None trust_env=True http2=False
2024-09-21 12:37:09,265 - httpx - DEBUG - load_verify_locations cafile='C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\certifi\cacert.pem'
SileroVAD {'sampling_rate': 16000, 'threshold': 0.5, 'min_silence_duration_ms': 200}
Traceback (most recent call last):
File "C:\LLM-CLASS\开源项目测试\bailing\main.py", line 59, in
robot = robot.Robot(config_path)
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing\robot.py", line 49, in init
self.vad = vad.create_instance(
^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing\vad.py", line 70, in create_instance
return cls(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing\vad.py", line 27, in init
self.model = load_silero_vad()
^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\silero_vad\model.py", line 23, in load_silero_vad
model = init_jit_model(model_file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\silero_vad\utils_vad.py", line 171, in init_jit_model
model = torch.jit.load(model_path, map_location=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\LLM-CLASS\开源项目测试\bailing\bailing.env\Lib\site-packages\torch\jit_serialization.py", line 163, in load
cpp_module = torch._C.import_ir_module(cu, os.fspath(f), map_location, _extra_files, _restore_shapes) # type: ignore[call-arg]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: open file failed because of errno 2 on fopen: No such file or directory, file path: C:\LLM-CLASS\开源
项目测试\bailing\bailing.env\Lib\site-packages\silero_vad\data\silero_vad.jit
The text was updated successfully, but these errors were encountered: