Running speaker diarization on a 5 minute audio example fails

[mflage]

$ python audioAnalysis.py speakerDiarization -i /home/marius/input.wav --num 0
didn't find file
Traceback (most recent call last):
  File "audioAnalysis.py", line 611, in <module>
    speakerDiarizationWrapper(args.input, args.num, args.flsd)
  File "audioAnalysis.py", line 233, in speakerDiarizationWrapper
    aS.speakerDiarization(inputFile, numSpeakers, lda_dim=0, plot_res=True)
  File "/usr/local/lib/python2.7/dist-packages/pyAudioAnalysis/audioSegmentation.py", line 779, in speakerDiarization
    [classifier_1, MEAN1, STD1, classNames1, mtWin1, mtStep1, stWin1, stStep1, computeBEAT1] = aT.load_model_knn(os.path.join(os.path.dirname(os.path.realpath(__file__)), "data", "knnSpeakerAll"))
TypeError: 'NoneType' object is not iterable

ffprobe identifies the file:

  Duration: 00:05:00.00, bitrate: 1411 kb/s
    Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, 2 channels, s16, 1411 kb/s