|
MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
|
|
inlinenodiscard |
One nn_frame_audio dispatch: cut a sample stream into overlapping frames, reflect padded on the right.
samples holds context + chunks * chunk_size values. Frame n is the context + chunk_size values starting at n * chunk_size, followed by pad values that mirror the frame about its last value without repeating it. pad must be smaller than context + chunk_size.
| samples | Device address of the samples. |
| frames | Device address of the frames, [chunks, frame_audio_length]. |
| std::invalid_argument | When chunks or chunk_size is 0 or pad is a frame or more. |
Definition at line 267 of file Stages.hpp.
References element_workgroup, frame_audio_length(), frame_audio_shader, MayaFlux::Yantra::TensorKernels::detail::groups_for(), MayaFlux::Yantra::TensorKernels::detail::make_stage(), and MayaFlux::Yantra::TensorKernels::detail::refuse().
Referenced by MayaFlux::Yantra::SileroVadModel::Impl::run().