I'm running this implementation of WaveNet which uses librosa, which uses audioread. From python train.py --data_dir=corpus
Traceback (most recent call last):
File "C:\Users\Skylar\AppData\Local\Programs\Python\Python36\lib\threading.py", line 916, in _bootstrap_inner
self.run()
File "C:\Users\Skylar\AppData\Local\Programs\Python\Python36\lib\threading.py", line 864, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\Skylar\Documents\WaveNet-Playground\wavenet\audio_reader.py", line 158, in thread_main
for audio, filename, category_id in iterator:
File "C:\Users\Skylar\Documents\WaveNet-Playground\wavenet\audio_reader.py", line 59, in load_generic_audio
audio, _ = librosa.load(filename, sr=sample_rate, mono=True)
File "C:\Users\Skylar\AppData\Local\Programs\Python\Python36\lib\site-packages\librosa\core\audio.py", line 112, in load
with audioread.audio_open(os.path.realpath(path)) as input_file:
File "C:\Users\Skylar\AppData\Local\Programs\Python\Python36\lib\site-packages\audioread\__init__.py", line 116, in audio_open
raise NoBackendError()
audioread.NoBackendError
Hi,
I'm running this implementation of WaveNet which uses librosa, which uses audioread. From
python train.py --data_dir=corpus
Here's ffmpeg -version
I'm on Windows 10 64-bit using python 3.6.2, librosa 0.6.0, and audioread 2.1.5.
Other tests include
So, things seem to be working well in the libraries, perhaps it's a bug in the forked code?