MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
MayaFlux::Yantra::PhonemeAnalysis Struct Reference

Analysis result of a PhonemeAnalyzer. More...

#include <PhonemeAnalyzer.hpp>

Collaboration diagram for MayaFlux::Yantra::PhonemeAnalysis:

Public Member Functions

std::shared_ptr< Kakshya::TensorContainer > embedding_tensor (std::string name) const
 The states as a frames by hidden_width float32 tensor.
std::shared_ptr< Kakshya::TensorContainer > posterior_tensor (std::string name) const
 The probabilities as a frames by classes float32 tensor.

Public Attributes

std::vector< uint32_t > best
 Most probable class of each frame.
PhonemeAnalyzerConfig config
 Settings the analysis was produced under.
std::vector< float > embeddings
 State of every frame before the final layer, HubertPhonemeModel::hidden_width values each.
std::vector< PhonemeEvent > events
 The phonemes in order: every frame whose most probable class is a phoneme and differs from the frame before.
std::vector< std::pair< size_t, size_t > > frame_positions
 First and one past the last sample of each frame.
size_t frames { 0 }
 Frames of the utterance.
std::vector< float > posteriors
 Probability of every class on every frame, frame after frame, HubertPhonemeModel::classes values each.

Static Private Member Functions

static std::shared_ptr< Kakshya::TensorContainer > as_tensor (const std::vector< float > &values, uint64_t width, std::string name)

Detailed Description

Analysis result of a PhonemeAnalyzer.

Definition at line 89 of file PhonemeAnalyzer.hpp.


The documentation for this struct was generated from the following file: