python Segmentation fault

[DeityBoom]

Hi,
When I executed the script of training conformer_ctc mdoel for aishell , the issue occurred after some epochs. The specific error message is as follows:
Exception ignored in: <function _MultiProcessingDataLoaderIter.__del__ at 0x7f7a0513fb00> Traceback (most recent call last): File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1478, in __del__ self._shutdown_workers() File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1442, in _shutdown_workers w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL) File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/multiprocessing/process.py", line 149, in join res = self._popen.wait(timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/multiprocessing/popen_fork.py", line 40, in wait if not wait([self.sentinel], timeout): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/multiprocessing/connection.py", line 930, in wait ready = selector.select(timeout) ^^^^^^^^^^^^^^^^^^^^^^^^ File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/selectors.py", line 415, in select fd_event_list = self._selector.poll(timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "*/miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/site-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler _error_if_any_worker_fails() RuntimeError: DataLoader worker (pid 2010138) is killed by signal: Aborted. */miniconda3/envs/k2_torch2.0.1_py3.11.5/lib/python3.11/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 8 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

Meanwhile, the data processing script of wenetspeech encountered the following error：
2023-10-27 02:18:46,767 INFO [compute_fbank_wenetspeech_splits.py:133] Splitting cuts into smaller chunks. 2023-10-27 02:18:46,779 INFO [compute_fbank_wenetspeech_splits.py:138] Computing features ^MComputing features in batches: 0it [00:00, ?it/s]2023-10-27 02:20:49,923 WARNING [utils.py:910] [Suppressed AudioLoadingError] Error message: Reading audio from '*/icefall/egs/wenetspeech/ASR/download/WenetSpeech/audio/train/podcast/B00116/X0000029713_197820997.opus' failed. Details: <class 'lhotse.audio.utils.AudioLoadingError'>: Could not determine the number of channels for OPUS file from the following ffmpeg output (shown as bytestring due to avoid possible encoding issues): b'ffmpeg version 4.3 Copyright (c) 2000-2020 the FFmpeg developers\n built with gcc 7.3.0 (crosstool-NG 1.23.0.449-a04d0)\n configuration: --prefix=*/env/miniconda3/envs/k2_torch2.0.1_py3.11.5 --cc=/opt/conda/conda-bld/ffmpeg_1597178665428/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc --disable-doc --disable-openssl --enable-avresample --enable-gnutls --enable-hardcoded-tables --enable-libfreetype --enable-libopenh264 --enable-pic --enable-pthreads --enable-shared --disable-static --enable-version3 --enable-zlib --enable-libmp3lame\n libavutil 56. 51.100 / 56. 51.100\n libavcodec 58. 91.100 / 58. 91.100\n libavformat 58. 45.100 / 58. 45.100\n libavdevice 58. 10.100 / 58. 10.100\n libavfilter 7. 85.100 / 7. 85.100\n libavresample 4. 0. 0 / 4. 0. 0\n libswscale 5. 7.100 / 5. 7.100\n libswresample 3. 7.100 / 3. 7.100\n' The ffmpeg command for which the program failed is: 'ffmpeg -threads 1 -ss 654.18 -t 2.81 -i '*/icefall/egs/wenetspeech/ASR/download/WenetSpeech/audio/train/podcast/B00116/X0000029713_197820997.opus' -ar 16000 -f f32le -threads 1 pipe:1', error code: -11 [extra info] When calling: Recording.load_audio(args=(Recording(id='X0000029713_197820997', sources=[AudioSource(type='file', channels=[0], source='*/icefall/egs/wenetspeech/ASR/download/WenetSpeech/audio/train/podcast/B00116/X0000029713_197820997.opus')], sampling_rate=16000, num_samples=13418240, duration=838.64, channel_ids=[0], transforms=None),) kwargs={'channels': 0, 'offset': 654.18, 'duration': 2.81}) [extra info] When calling: MonoCut.load_audio(args=(MonoCut(id='X0000029713_197820997_S00365', start=654.18, duration=2.81, channel=0, supervisions=[SupervisionSegment(id='X0000029713_197820997_S00365', recording_id='X0000029713_197820997', start=0.0, duration=2.81, channel=0, text='因为我觉得学会了运用不出来是很可惜的事情', language='Chinese', speaker=None, gender=None, custom=None, alignment=None)], features=None, recording=Recording(id='X0000029713_197820997', sources=[AudioSource(type='file', channels=[0], source='*/icefall/egs/wenetspeech/ASR/download/WenetSpeech/audio/train/podcast/B00116/X0000029713_197820997.opus')], sampling_rate=16000, num_samples=13418240, duration=838.64, channel_ids=[0], transforms=None), custom=None),) kwargs={})

Then I encountered this error [Segmentation fault] even I ran the "python" command in the command line without any script.
How can this issue be resolved?