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

◆ posterior_tensor()

std::shared_ptr< Kakshya::TensorContainer > MayaFlux::Yantra::PhonemeAnalysis::posterior_tensor ( std::string name) const
inlinenodiscard

The probabilities as a frames by classes float32 tensor.

Returns
The container, or nullptr when there are no frames.

Definition at line 109 of file PhonemeAnalyzer.hpp.

110 {
111 return as_tensor(posteriors, HubertPhonemeModel::classes, std::move(name));
112 }
static constexpr uint32_t classes
Scores per frame.
static std::shared_ptr< Kakshya::TensorContainer > as_tensor(const std::vector< float > &values, uint64_t width, std::string name)
std::vector< float > posteriors
Probability of every class on every frame, frame after frame, HubertPhonemeModel::classes values each...

References as_tensor(), MayaFlux::Yantra::HubertPhonemeModel::classes, and posteriors.

Here is the call graph for this function: