voice_audio_multi/include/engine/models/hviske_asr/frontend.h
Fabio c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
Initial import: audio.cpp with Orange Pi documentation
2026-11-04 19:05:22 +01:00

30 lines
703 B
C++

#pragma once
#include "engine/framework/audio/nemo_mel_frontend.h"
#include "engine/framework/runtime/session.h"
#include "engine/models/hviske_asr/assets.h"
#include <cstdint>
#include <memory>
#include <vector>
namespace engine::models::hviske_asr {
struct HviskeFrontendFeatures {
std::vector<float> values;
int64_t feature_dim = 0;
int64_t frames = 0;
int64_t valid_frames = 0;
};
class HviskeFrontend {
public:
explicit HviskeFrontend(std::shared_ptr<const HviskeASRAssets> assets);
HviskeFrontendFeatures extract(const engine::runtime::AudioBuffer & audio) const;
private:
engine::audio::NemoMelFrontend frontend_;
};
} // namespace engine::models::hviske_asr