FunASR
FunASR copied to clipboard
Published
4 months ago
•
modelscope
modelscope
Syntax error: Bad for loop variable
我运行alimeeting diarization 的 run.sh遇到错误，先是utils/parse_options.sh不存在。
我参考别的档案补上../../../aishell/transformer/utils/之后遇到run.sh: 34: utils/parse_options.sh: Syntax error: Bad for loop variable，不确定这个错误如何修復。
请问能协助我修正这个错误吗？
我跳过执行. utils/parse_options.sh || exit 1;在 run.sh#33遇到错误No such file or directory: 'sond.pb'，我改成绝对路径指向speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond.pth遇到以下错误:
AttributeError: module 'numpy' has no attribute 'int'.
`np.int` was a deprecated alias for the builtin `int`. To avoid this error in existing code, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use
e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
我修復了numpy的错误，之后卡在以下错误:
2024-01-08 13:45:13,471 (build_model_from_file:56) INFO: model_file is /mnt/HDD/HDD2/DTDwind/FunASR/egs/alimeeting/diarization/sond/speech_diarization_sond-zh-cn-alimeeting-16k-n16k4-pytorch/sond.pth
Traceback (most recent call last):
File "infer_alimeeting_test.py", line 24, in <module>
main()
File "infer_alimeeting_test.py", line 13, in main
pipeline = inference_launch(
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/bin/diar_inference_launch.py", line 338, in inference_launch
return inference_sond(mode=mode, **kwargs)
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/bin/diar_inference_launch.py", line 110, in inference_sond
speech2diar = Speech2DiarizationSOND(**speech2diar_kwargs)
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/bin/diar_infer.py", line 135, in __init__
diar_model, diar_train_args = build_model_from_file(
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/build_utils/build_model_from_file.py", line 72, in build_model_from_file
model_dict = torch.load(model_file, map_location=device)
File "/home/DTDwind/.conda/envs/funasr/lib/python3.8/site-packages/torch/serialization.py", line 1028, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/DTDwind/.conda/envs/funasr/lib/python3.8/site-packages/torch/serialization.py", line 1246, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, 'v'.
Traceback (most recent call last):
File "local/convert_label_to_rttm.py", line 132, in <module>
my_runner.run()
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/utils/job_runner.py", line 96, in run
task_list, shared_param, args = self.prepare(parser)
File "local/convert_label_to_rttm.py", line 26, in prepare
utt2labels = load_scp_as_list(args.label_txt, 'list')
File "/mnt/HDD/HDD2/DTDwind/FunASR/funasr/utils/misc.py", line 39, in load_scp_as_list
with io.open(scp_path, 'r', encoding='utf8') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'outputs/labels.txt'
Scoring...
Loading speaker turns from reference RTTMs...
Loading speaker turns from system RTTMs...
ERROR: Unable to open RTTM file: outputs/prediction_sm_83.rttm
OS: linux Python/C++ Version：Python 3.8.18 Package Version： torch 2.1.2 、torchaudio 2.1.1、modelscope 1.10.0、funasr 0.8.8 、 numpy 1.24.4
