退出代码-1073741819 (0xC0000005)

[standyyyy]

代码一运行过会就停止了，尝试过网络上那些更改h5py版本办法 ，但是还是不行 。

代码：
asr_executor = ASRExecutor()
text = asr_executor(
model='conformer_wenetspeech',
lang='zh',
sample_rate=16000,
config=None, # Set config and ckpt_path to None to use pretrained model.
ckpt_path=None,
audio_file='F:\github\py_speech_seg-master/1234.wav',
force_yes=False,
device=paddle.get_device())
print('ASR Result: \n{}'.format(text))
用的是windows 。

[zh794390558]

demos 里提供的音频能正常运行吗？

[standyyyy]

是可以正常播放的 。

[zh794390558]

asr可以正常运行？那就check下是否是输入音频的问题。

[standyyyy]

抱歉 ，理解错了，我以为你是资讯我所使用的音频是否可以正常播放 ，Demo里面的zh.wav也无法正常使用 。

以下是全部报错情况 。
D:\Anaconda3\lib\site-packages\numpy\_distributor_init.py:32: UserWarning: loaded more than 1 DLL from .libs: D:\Anaconda3\lib\site-packages\numpy\.libs\libopenblas.QVLO2T66WEPI7JZ63PS3HMOHFEY472BC.gfortran-win_amd64.dll D:\Anaconda3\lib\site-packages\numpy\.libs\libopenblas.XWYDX2IKJW2NMTWSFYNGFUWKQU3LYTCZ.gfortran-win_amd64.dll stacklevel=1) D:\Anaconda3\lib\site-packages\socks.py:58: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working from collections import Callable D:\Anaconda3\lib\site-packages\numba\types\__init__.py:110: DeprecationWarning: np.longis a deprecated alias fornp.compat.long. To silence this warning, use np.compat.longby itself. In the likely event your code does not need to work on Python 2 you can use the builtinintfor whichnp.compat.longis itself an alias. Doing this will not modify any behaviour and is safe. When replacingnp.long, you may wish to use e.g. np.int64ornp.int32to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations long_ = _make_signed(np.long) D:\Anaconda3\lib\site-packages\numba\types\__init__.py:111: DeprecationWarning:np.longis a deprecated alias fornp.compat.long. To silence this warning, use np.compat.longby itself. In the likely event your code does not need to work on Python 2 you can use the builtinintfor whichnp.compat.longis itself an alias. Doing this will not modify any behaviour and is safe. When replacingnp.long, you may wish to use e.g. np.int64ornp.int32to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations ulong = _make_unsigned(np.long) C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\librosa\core\constantq.py:1059: DeprecationWarning:np.complexis a deprecated alias for the builtincomplex. To silence this warning, use complexby itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, usenp.complex128here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations dtype=np.complex, D:\Anaconda3\lib\site-packages\nltk\decorators.py:70: DeprecationWarning:formatargspecis deprecated since Python 3.5. Usesignatureand theSignature` object directly
formatvalue=lambda value: "")[1:-1]
D:\Anaconda3\lib\site-packages\matplotlib_init_.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import MutableMapping
D:\Anaconda3\lib\site-packages\matplotlib\rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Iterable, Mapping
D:\Anaconda3\lib\site-packages\matplotlib\colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Sized
D:\Anaconda3\lib\site-packages\matplotlib_init_.py:179: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
a = distutils.version.LooseVersion(a)
D:\Anaconda3\lib\site-packages\matplotlib_init_.py:180: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
b = distutils.version.LooseVersion(b)
[2022-04-18 15:32:33,559] [ INFO] - checking the audio file format......
[2022-04-18 15:32:33,560] [ INFO] - The sample rate is 16000
[2022-04-18 15:32:33,560] [ INFO] - The audio file format is right
[2022-04-18 15:32:33,575] [ INFO] - File C:\Users\Administrator.paddlespeech\models\conformer_wenetspeech-zh-16k\asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar.gz md5 checking...
[2022-04-18 15:32:37,946] [ INFO] - Use pretrained model stored in: C:\Users\Administrator.paddlespeech\models\conformer_wenetspeech-zh-16k\asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar
[2022-04-18 15:32:37,946] [ INFO] - C:\Users\Administrator.paddlespeech\models\conformer_wenetspeech-zh-16k\asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar
[2022-04-18 15:32:37,946] [ INFO] - C:\Users\Administrator.paddlespeech\models\conformer_wenetspeech-zh-16k\asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar\model.yaml
[2022-04-18 15:32:37,946] [ INFO] - C:\Users\Administrator.paddlespeech\models\conformer_wenetspeech-zh-16k\asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar\exp/conformer/checkpoints/wenetspeech.pdparams
2022-04-18 15:32:38.259 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:229 - BLANK id: 0
2022-04-18 15:32:38.259 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:230 - UNK id: 1
2022-04-18 15:32:38.260 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:231 - EOS id: 5536
2022-04-18 15:32:38.260 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:232 - SOS id: 5536
2022-04-18 15:32:38.260 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:233 - SPACE id: -1
2022-04-18 15:32:38.260 | INFO | paddlespeech.s2t.frontend.featurizer.text_featurizer:_load_vocabulary_from_file:234 - MASKCTC id: -1
WARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.
Please see pypa/pip#5599 for advice on fixing the underlying issue.
To avoid this problem you can invoke Python with '-m pip' instead of running pip directly.
WARNING: Ignoring invalid distribution -ip (d:\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -ip (d:\anaconda3\lib\site-packages)
Looking in indexes: http://mirrors.aliyun.com/pypi/simple
ERROR: Could not find a version that satisfies the requirement paddlespeech_ctcdecoders (from versions: none)
ERROR: No matching distribution found for paddlespeech_ctcdecoders
WARNING: Ignoring invalid distribution -ip (d:\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -ip (d:\anaconda3\lib\site-packages)
2022-04-18 15:32:40.374 | INFO | paddlespeech.s2t.modules.ctc::43 - paddlespeech_ctcdecoders not installed!
2022-04-18 15:32:40.414 | INFO | paddlespeech.s2t.models.u2.u2:_init_from_config:829 - U2 Encoder type: conformer
2022-04-18 15:32:45.825 | INFO | paddlespeech.s2t.modules.loss:init:41 - CTCLoss Loss reduction: sum, div-bs: True
2022-04-18 15:32:45.825 | INFO | paddlespeech.s2t.modules.loss:init:42 - CTCLoss Grad Norm Type: None
2022-04-18 15:32:45.826 | INFO | paddlespeech.s2t.modules.loss:init:73 - CTCLoss() kwargs:{'norm_by_times': False}, not support: {'norm_by_batchsize': False, 'norm_by_total_logits_len': False}
[2022-04-18 15:32:48,447] [ INFO] - Preprocess audio_file:F:\Aawant\jinzhuan\zh.wav
[2022-04-18 15:32:48,447] [ INFO] - get the preprocess conf
[2022-04-18 15:32:49,323] [ INFO] - read the audio file
[2022-04-18 15:32:49,323] [ INFO] - audio shape: (79949,)
[2022-04-18 15:32:49,854] [ INFO] - audio feat shape: [1, 498, 80]

进程已结束,退出代码-1073741819 (0xC0000005)
`

[Jackwaterveg]

请问 直接 paddlespeech asr --input xxx.wav 可以运行吗？ @standyyyy

[standyyyy]

尝试了一下，是可以的，库版本冲突的问题估计 。