Spaces:
Running
need more info on this assertion error
Hi,
I'm running a local gradio demo of this project, but whenever i load a audiofile i get this error:
File "/home/hari/enclap_env/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/hari/enclap/enclap/inference.py", line 78, in infer_from_audio
encodec_frames = self.encodec.encode(encodec_audio)
File "/home/hari/enclap_env/lib/python3.9/site-packages/encodec/model.py", line 130, in encode
assert x.dim() == 3
AssertionError
i'm passing a .wav file as input
also when i checked for the dimension of x it was 4
Hello! Sorry for the late reply.
The error seems to occur during the audio preprocessing for the EnCodec model.
EnCodec model supports .wav files with mono or stereo channels. I think you might provided audio files with more channels.