Running musicnn_test.ipynb throws exception

[botkevin]

When taggram, tags = extractor(file_name, model='MTT_musicnn', extract_features=False) is run, this warning is repeated multiple times:

WARNING: Entity <bound method Dropout.call of <tensorflow.python.layers.core.Dropout object at 0x7f9a3e22e240>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: converting <bound method Dropout.call of <tensorflow.python.layers.core.Dropout object at 0x7f9a3e22e240>>: AssertionError: Bad argument number for Name: 3, expecting 4

and am given error:

RuntimeError                              Traceback (most recent call last)
~/.local/lib/python3.6/site-packages/librosa/core/audio.py in load(path, sr, mono, offset, duration, dtype, res_type)
    145     try:
--> 146         with sf.SoundFile(path) as sf_desc:
    147             sr_native = sf_desc.samplerate

~/.local/lib/python3.6/site-packages/soundfile.py in __init__(self, file, mode, samplerate, channels, subtype, endian, format, closefd)
    628                                          format, subtype, endian)
--> 629         self._file = self._open(file, mode_int, closefd)
    630         if set(mode).issuperset('r+') and self.seekable():

~/.local/lib/python3.6/site-packages/soundfile.py in _open(self, file, mode_int, closefd)
   1183         _error_check(_snd.sf_error(file_ptr),
-> 1184                      "Error opening {0!r}: ".format(self.name))
   1185         if mode_int == _snd.SFM_WRITE:

~/.local/lib/python3.6/site-packages/soundfile.py in _error_check(err, prefix)
   1356         err_str = _snd.sf_error_number(err)
-> 1357         raise RuntimeError(prefix + _ffi.string(err_str).decode('utf-8', 'replace'))
   1358 

RuntimeError: Error opening './audio/joram-moments_of_clarity-08-solipsism-59-88.mp3': File contains data in an unknown format.

During handling of the above exception, another exception occurred:

NoBackendError                            Traceback (most recent call last)
<ipython-input-2-f690f5bcff5c> in <module>
      1 from musicnn.extractor import extractor
----> 2 taggram, tags, features = extractor(file_name, model='MTT_musicnn', extract_features=True)

~/Documents/musicnn/musicnn/extractor.py in extractor(file_name, model, input_length, input_overlap, extract_features)
    156     # batching data
    157     print('Computing spectrogram (w/ librosa) and tags (w/ tensorflow)..', end =" ")
--> 158     batch, spectrogram = batch_data(file_name, n_frames, overlap)
    159 
    160     # tensorflow: extract features and tags

~/Documents/musicnn/musicnn/extractor.py in batch_data(audio_file, n_frames, overlap)
     39 
     40     # compute the log-mel spectrogram with librosa
---> 41     audio, sr = librosa.load(audio_file, sr=config.SR)
     42     audio_rep = librosa.feature.melspectrogram(y=audio, 
     43                                                sr=sr,

~/.local/lib/python3.6/site-packages/librosa/core/audio.py in load(path, sr, mono, offset, duration, dtype, res_type)
    161         if isinstance(path, (str, pathlib.PurePath)):
    162             warnings.warn("PySoundFile failed. Trying audioread instead.")
--> 163             y, sr_native = __audioread_load(path, offset, duration, dtype)
    164         else:
    165             raise (exc)

~/.local/lib/python3.6/site-packages/librosa/core/audio.py in __audioread_load(path, offset, duration, dtype)
    185 
    186     y = []
--> 187     with audioread.audio_open(path) as input_file:
    188         sr_native = input_file.samplerate
    189         n_channels = input_file.channels

~/.local/lib/python3.6/site-packages/audioread/__init__.py in audio_open(path, backends)
    114 
    115     # All backends failed!
--> 116     raise NoBackendError()

NoBackendError: 

Based on the FAQ, there seems to be a problem with librosa soundread and audioread

Running the vgg_example yields the same warning, but outputs the correct taggram

However, when I switched musicnn_example to opening filename='./audio/TRWJAZW128F42760DD_test.mp3' from './audio/joram-moments_of_clarity-08-solipsism-59-88.mp3', the warning is still raised, but a taggram does show. Perhaps this is a problem with my version of librosa, because it seems that 'joram...mp3' cannot be opened. Openning 'TRW...mp3' yields me the warning /home/kevin/.local/lib/python3.6/site-packages/librosa/core/audio.py:162: UserWarning: PySoundFile failed. Trying audioread instead. warnings.warn("PySoundFile failed. Trying audioread instead.") which is consistent with the FAQ.

However, the Autgograph warning seems to be a different problem altogether.