I installed birdvoxdetect via pip and have been trying it to process some .wav files, but this always results in error. Full error mesage at the end of this message.
From what I can tell from looking at the code is that the default detector "birdvoxdetect_pcen_cnn" will always result in this error (since it causes has_context is to be False, which causes concat_deque not to be set). Switching the detector does not seem possible using the command line interface. I got the system finally working by changing the detector name in core.py to "birdvoxdetect_pcen_cnn_adaptive-threshold-T1800".
Traceback (most recent call last):
File "/usr/local/bin/birdvoxdetect", line 8, in <module>
sys.exit(main())
File "/usr/local/lib/python3.5/dist-packages/birdvoxdetect/cli.py", line 193, in main
logger_level=logger_level)
File "/usr/local/lib/python3.5/dist-packages/birdvoxdetect/cli.py", line 88, in run
logger_level=logger_level)
File "/usr/local/lib/python3.5/dist-packages/birdvoxdetect/core.py", line 240, in process_file
concat_deque = np.concatenate(deque, axis=1, out=concat_deque)
UnboundLocalError: local variable 'concat_deque' referenced before assignment
Exception ignored in: <object repr() failed>
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/soundfile.py", line 797, in __del__
File "/usr/local/lib/python3.5/dist-packages/soundfile.py", line 1236, in close
File "/usr/local/lib/python3.5/dist-packages/soundfile.py", line 1230, in flush
AttributeError: 'NoneType' object has no attribute 'sf_write_sync'
I installed birdvoxdetect via pip and have been trying it to process some .wav files, but this always results in error. Full error mesage at the end of this message.
From what I can tell from looking at the code is that the default detector "birdvoxdetect_pcen_cnn" will always result in this error (since it causes
has_context
is to be False, which causesconcat_deque
not to be set). Switching the detector does not seem possible using the command line interface. I got the system finally working by changing the detector name in core.py to "birdvoxdetect_pcen_cnn_adaptive-threshold-T1800".