Real-Time-Voice-Cloning icon indicating copy to clipboard operation
Real-Time-Voice-Cloning copied to clipboard

Published 20 hours ago • verified publisher icon CorentinJ

demo_cli melspectrogram error

Open Noobos100 opened this issue 1 year ago • 1 comments

I get this error when running demo_cli.py:

` File "/home/carlos/Downloads/Real-Time-Voice-Cloning-master/encoder/audio.py", line 58, in wav_to_mel_spectrogram frames = librosa.feature.melspectrogram(

TypeError: melspectrogram() takes 0 positional arguments but 2 positional arguments (and 2 keyword-only arguments) were given`

Any ideas as to why that may be? Thanks

Noobos100 avatar May 14 '23 19:05 Noobos100

I think its a librosa version issue. Make sure you create a virtual environment with python3.7 and then install ffmpeg, torch, and then the requirements in that order. Specifically make sure you have librosa==0.8.1

raws84 avatar May 17 '23 07:05 raws84