whisper.cpp
whisper.cpp copied to clipboard
Fix for fft sizes in whisper.cpp
fft_out
needs to be twice the frame_size
, not the frame_step
. It is resized in fft()
anyway, but this change prevents an unnecessary reallocation.
n_fft
must match the mel filter size, so it is best not to calculate it from frame_size
.
We only need to get the magnitudes for half the spectrum since the other half is a mirror and not used in the mel filter loop later.