nguyenlm comments

Repositories
Issues
Comments

Results 23 comments of


                                            nguyenlm

Pad audio fragment

Hi @Alexey322 I think the author used padding for doing `stft` (aka fast fourier transform) on all frames of the input audio segment. ```python spec = torch.stft(y, n_fft, hop_length=hop_size, win_length=win_size,...

mandrain support?

@yl4579 I have the same question as @yihuitang. What is the reasonable `prod_embd`? And How to use it in training?

AttributeError: module 'omegaconf._utils' has no attribute 'is_primitive_type'. Did you mean: 'is_primitive_dict'?

For anyone who is facing this issue, try to replace `is_primitive_type` with `is_primitive_type_annotation`