You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using jupetenotebook and trying to reproduce google colab notebook on my machine with the small changes I need.
Python 3.8.1.7.
I spend much time to prepare my env correct but every new cell have a new issue. When the time came to pre-resample, face a new barrier that I couldn't get around with either with help Google or chatgpt.
I am trying to resample audio files with !svc pre-resample , but got an error with every file :
WARNING [04:35:16] Failed to load preprocess_resample.py:67
dataset_raw\singer\vocals_016.wav
due to Invalid file:
WindowsPath('dataset_raw/singer/v
ocals_016.wav')
In the specified file "preprocess_resample.py: line67" I found
#except Exception as e:
# Failure due to attempting to load a file that is not audio, so return early
LOG.warning(f"Failed to load {input_path} due to {e}")
return
I don't know how my env or so-vits not recognizing audio files. Btw few steps ago, i am succesfully manipulate my audio source and sliced them ok.
To understand what the error is , I experimented !svc pre-config and got output
ValueError: too few files in dataset\44k\singer (expected at least 5).
So I began to suspect that the files are not recognized at all
I have ~ 60 slices of wav audio format. I tested they are not broken and playable.
Maybe someone had a similar error or guess what's the matter. I would appreciate any advice and recommendations . I know that it is possible to run sovits even with a GUI. However, I am interested in the implementation in jupeternotebook on my local machine. Thanks for reading.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi! Thanks much for your time .
I am using jupetenotebook and trying to reproduce google colab notebook on my machine with the small changes I need.
Python 3.8.1.7.
I spend much time to prepare my env correct but every new cell have a new issue. When the time came to pre-resample, face a new barrier that I couldn't get around with either with help Google or chatgpt.
I am trying to resample audio files with !svc pre-resample , but got an error with every file :
In the specified file "preprocess_resample.py: line67" I found
I don't know how my env or so-vits not recognizing audio files. Btw few steps ago, i am succesfully manipulate my audio source and sliced them ok.
To understand what the error is , I experimented !svc pre-config and got output
So I began to suspect that the files are not recognized at all
I have ~ 60 slices of wav audio format. I tested they are not broken and playable.
Maybe someone had a similar error or guess what's the matter. I would appreciate any advice and recommendations . I know that it is possible to run sovits even with a GUI. However, I am interested in the implementation in jupeternotebook on my local machine. Thanks for reading.
Beta Was this translation helpful? Give feedback.
All reactions