MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches

◆ share_recording()

template<ComputeData InputType = std::vector<Kakshya::DataVariant>, ComputeData OutputType = Eigen::MatrixXd>
void MayaFlux::Yantra::VadAnalyzer< InputType, OutputType >::share_recording ( std::shared_ptr< GpuDispatchRecorder > recording)
inline

Append to a recording the caller shares with other work.

With a shared recording the network goes to the device in the same submission as the work recorded around it, and analyze_speech submits and waits for all of it. Call it before the first analysis or record. The recording must be compute isolated.

Exceptions
std::logic_errorwhen the network has already been created.

Definition at line 171 of file VadAnalyzer.hpp.

172 {
173 if (m_model) {
175 std::source_location::current(), "The recording can only be shared before the network starts");
176 }
178 }
std::shared_ptr< GpuDispatchRecorder > m_recording
std::unique_ptr< SileroVadModel > m_model
Whether each 32 ms chunk of a mono 16 kHz stream is voice activity, from a learned network.