Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

报错无法解析模型 。 #13

Closed
standyyyy opened this issue Apr 16, 2023 · 6 comments
Closed

报错无法解析模型 。 #13

standyyyy opened this issue Apr 16, 2023 · 6 comments

Comments

@standyyyy
Copy link

下载百度云的模型,然后用的是venv的环境,按照requirements.txt安装的,但是在运行demo.py的时候报错无法解析。

知道是环境问题,但是不知道是哪个库的版本问题,我昨天在mac上可以跑起来,也没报错,但是今天换到了台式机上发现报错。

2 0 2 3 - 0 4 - 1 6 1 8 : 3 3 : 2 4 . 2 7 7 1 1 1 0 [ W : o n n x r u n t i m e : D e f a u l t , o n n x r u n t i m e _ p y b i n d _ s t a t e . c c : 1 6 4 1 o n n x r u n t i m e : : p y t h o n : : C r e a t e I n f e r e n c e P y b i n d S t a t e M o d u l e ] I n i t p r o v i d e r b r i d g e f a i l e d . Traceback (most recent call last): File "F:/语音识别/RapidASR-2.0.0/demo.py", line 7, in <module> paraformer = RapidParaformer() File "F:\语音识别\RapidASR-2.0.0\rapid_paraformer\rapid_paraformer.py", line 28, in __init__ self.ort_infer = OrtInferSession(config['Model']) File "F:\语音识别\RapidASR-2.0.0\rapid_paraformer\utils.py", line 304, in __init__ self.session = InferenceSession(config['model_path'], File "F:\语音识别\RapidASR-2.0.0\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in __init__ self._create_inference_session(providers, provider_options, disabled_optimizers) File "F:\语音识别\RapidASR-2.0.0\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 384, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from F:\语音识别\RapidASR-2.0.0\rapid_paraformer\models\asr_paraformerv2.onnx failed:Protobuf parsing failed.
以上是报错完全信息。
`Package Version


audioread 3.0.0
certifi 2022.12.7
cffi 1.15.1
charset-normalizer 3.1.0
coloredlogs 15.0.1
decorator 5.1.1
onnx 1.13.1
onnxruntime 1.13.1
packaging 23.1
pip 21.3.1
platformdirs 3.2.0
pooch 1.7.0
protobuf 3.20.3
pycparser 2.21
pyreadline3 3.4.1
PyYAML 6.0
requests 2.28.2
resampy 0.4.2
scikit-learn 1.2.2
scipy 1.7.3
setuptools 60.2.0
soundfile 0.12.1
sympy 1.11.1
threadpoolctl 3.1.0
typeguard 2.13.3
typing_extensions 4.5.0
urllib3 1.26.15
wheel 0.37.1
zipp 3.15.0
`
因为我上传不了图片,所以以代码块的形式展示目前这个环境的所有库的版本, 期待大佬指点一下。

@SWHL
Copy link
Member

SWHL commented Apr 17, 2023

验证一下你那边下载模型的md5,确定一下是否一致(模型MD5: 9ca331381a470bc4458cc6c0b0b165de)
怀疑是模型下载有问题

@standyyyy
Copy link
Author

感谢大佬这么会回复,确实是这个问题 ,我重新下载下模型 。
也挺奇怪,这模型是我mac放到阿里云盘然后在下载下来的,下来md5就变了。
还有个问题就是现在长音频不支持吗 ,我尝试放了一首歌进去,识别了一分钟左右,最后出现了一句很短的识别结果,大概5,6个字的那种。

@standyyyy
Copy link
Author

打错字,是感谢大佬这么快回复

@SWHL
Copy link
Member

SWHL commented Apr 17, 2023

长音频这个,需要后期更新一下了。或者你这边可以贡献一下:smile:

@standyyyy
Copy link
Author

倒是想做一些贡献,感觉实力不太够
大佬有没有思路,指点一下看下在哪个环节,我去研究研究看看能不能折腾出来

@SWHL
Copy link
Member

SWHL commented Apr 25, 2023

参考这里 issue15

@SWHL SWHL closed this as completed Aug 21, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants