AudioFrameLoader Error
Hi folks, me again. So...I am working towards using the classifier as a detector and my goal is to run it on a set of test files. I am running into an issue at the audio_loader step (from tutorial) using this bit of code:
audio_loader = AudioFrameLoader(path='./Detection_Test_Files/', step=1.5, repres=spec_cfg_BOEM)
It produces the following error but I don't see a specification of duration as an argument in this function which is what I'm expecting given this error:
Traceback (most recent call last): File "C:\Users\eferg.conda\envs\ketos_env\lib\site-packages\IPython\core\interactiveshell.py", line 3444, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "", line 1, in audio_loader = AudioFrameLoader(path='./Detection_Test_Files/', step=1.5, repres=spec_cfg_BOEM) File "C:\Users\eferg.conda\envs\ketos_env\lib\site-packages\ketos\audio\audio_loader.py", line 502, in init assert 'duration' in r0.keys() or frame is not None, 'duration must be specified either via the frame argument or the duration item of the repres dictionary' AssertionError: duration must be specified either via the frame argument or the duration item of the repres dictionary
Ultimately I would like to just batch run it on a set of wav files (that are in the folder), but looks like I need to get through this step first. Thanks for help!