I faced the following error during the inference. Any idea how to fix it
file "/content/QuickVC-VoiceConversion/convert.py", line 62, in
mel_tgt = mel_spectrogram_torch(
File "/content/QuickVC-VoiceConversion/mel_processing.py", line 114, in mel_spectrogram_torch
spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (80x641 and 1x641)
I faced the following error during the inference. Any idea how to fix it
file "/content/QuickVC-VoiceConversion/convert.py", line 62, in
mel_tgt = mel_spectrogram_torch(
File "/content/QuickVC-VoiceConversion/mel_processing.py", line 114, in mel_spectrogram_torch
spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (80x641 and 1x641)