search

CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
52.78k stars 8.8k forks source link

audioread.exceptions.NoBackendError #22

Closed sdx0112 closed 5 years ago

sdx0112 commented 5 years ago

Traceback (most recent call last): File "D:\sdx\DeepFake\voice\Real-Time-Voice-Cloning\toolbox__init.py", line 70, in func = lambda: self.load_from_browser(self.ui.browse_file()) File "D:\sdx\DeepFake\voice\Real-Time-Voice-Cloning\toolbox__init__.py", line 110, in load_from_browser wav = Synthesizer.load_preprocess_wav(fpath) File "D:\sdx\DeepFake\voice\Real-Time-Voice-Cloning\synthesizer\inference.py", line 111, in load_preprocess_wav wav = librosa.load(fpath, hparams.sample_rate)[0] File "C:\ProgramData\Anaconda3\lib\site-packages\librosa\core\audio.py", line 119, in load with audioread.audio_open(os.path.realpath(path)) as input_file: File "C:\ProgramData\Anaconda3\lib\site-packages\audioread\init__.py", line 116, in audio_open raise NoBackendError() audioread.exceptions.NoBackendError

I have installed ffmpeg, but still get this error.

fazlekarim commented 5 years ago

You need to set the paths and all of that correctly. Type "ffmpeg -version" on your cmd prompt. If that is running then you installed ffmpeg correctly. Installing ffmpeg on windows in annoying.

sdx0112 commented 5 years ago

Issue solved. Thanks for your advice.