thu-spmi / CAT

A CRF-based ASR Toolkit
Apache License 2.0
326 stars 74 forks source link

decode error #76

Closed jasonyong closed 1 year ago

jasonyong commented 1 year ago

hi, when I run the decode process, some error happens:

==================== Stage 4 Decode ==================== Decode: set 'inference:infer:option:resume' -> /home/test/hd1/work/CAT/egs/aishell/exp/char_ctc-crf-cuside/check/checkpoint.1e1000s.pt Decode: set 'inference:infer:option:output_dir' -> exp/char_ctc-crf-cuside/decode/{} Decode: test: set 'output_dir' -> exp/char_ctc-crf-cuside/decode/test Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Traceback (most recent call last): File "/home/test/hd1/work/CAT/egs/aishell/utils/pipeline/asr.py", line 464, in interface.main(parse_args_from_var( File "/home/test/hd1/work/CAT/cat/ctc/cal_logit.py", line 54, in main mp.spawn(worker, nprocs=world_size, args=(args, q, model)) File "/home/test/miniconda3/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 240, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "/home/test/miniconda3/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 198, in start_processes while not context.join(): File "/home/test/miniconda3/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 149, in join raise ProcessExitedException( torch.multiprocessing.spawn.ProcessExitedException: process 0 terminated with exit code 1 Traceback (most recent call last): File "", line 1, in File "/home/test/miniconda3/lib/python3.10/multiprocessing/spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "/home/test/miniconda3/lib/python3.10/multiprocessing/spawn.py", line 126, in _main self = reduction.pickle.load(from_parent) File "/home/test/miniconda3/lib/python3.10/multiprocessing/synchronize.py", line 110, in setstate self._semlock = _multiprocessing.SemLock._rebuild(*state) FileNotFoundError: [Errno 2] No such file or directory

Can you figure out the problems? thanks

maxwellzh commented 1 year ago

This is probably a bug related to numpy version. Can you try

# upgrade the numpy to latest 
pip install -U numpy
# if upgrade doesn't work, try to install the specific version 
pip install numpy==1.23.1
maxwellzh commented 1 year ago

See also https://github.com/pytorch/pytorch/issues/37377#issuecomment-629530272

Feel free to re-open this issue if you have any question.