AIDA-X Model Trainer | Step 1.3 error | "The truth value of an array with more than one element is ambiguous." [SOLVED]

Our guitarist made an input and output file based on the model and settings he uses in our mixes.
all went well until Step 1.3 in the Workbook

Step 1.3 of the collab workbook procress gives me this error.
I used my own files, they are the same size (sample size), the names are correct.
I first though a space in the folder name could be the issue so I tried renaming the Drive oflder and refreshing.

I do notice that the path copied differs slightly from the example

example was: /content/drive/My Drive/training-data-folder
and my DATA_DIR: /content/drive/MyDrive/LDV-AIDA/Blackstar-plugin

I have no idea how to continue

Input file name: /content/drive/MyDrive/LDV-AIDA/Blackstar-plugin/input.wav
Target file name: /content/drive/MyDrive/LDV-AIDA/Blackstar-plugin/target.wav
Input rate: 44100 length: 6314898 [samples]
Target rate: 44100 length: 6314898 [samples]
Converting audio sample rate to 48kHz.
ValueError                                Traceback (most recent call last)
<ipython-input-15-4a09de855873> in <cell line: 33>()
     32 file_name = os.path.split(DATA_DIR)[-1]
---> 33 prep_audio([os.path.join(DATA_DIR, "input.wav"),os.path.join(DATA_DIR, "target.wav")],
     34           file_name=file_name)

1 frames
/usr/local/lib/python3.9/dist-packages/librosa/core/ in resample(y, orig_sr, target_sr, res_type, fix, scale, axis, **kwargs)
    634     util.valid_audio(y, mono=False)
--> 636     if orig_sr == target_sr:
    637         return y

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
1 Like

the input and output have to be recorded or at least exported in 48khz. Yours are 44.1khz


and/or make sure the tracks are mono.

1 Like

Went to 48000 mono and now it’s working, thanks!