voice_audio_multi/include/engine/community_models/parakeet_tdt/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

38 lines
993 B
C++

#pragma once
#include "engine/framework/audio/nemo_mel_frontend.h"
#include "engine/framework/runtime/session.h"
#include "engine/community_models/parakeet_tdt/assets.h"
#include <cstdint>
#include <memory>
#include <vector>
namespace engine::community_models::parakeet_tdt {
struct ParakeetFrontendFeatures {
std::vector<float> values;
int64_t frames = 0;
int64_t valid_frames = 0;
int64_t feature_dim = 0;
};
class WindowFrontend {
public:
virtual ~WindowFrontend() = default;
virtual ParakeetFrontendFeatures extract(const runtime::AudioBuffer & window, int64_t start_sample) = 0;
virtual void reset() = 0;
};
class ParakeetFrontend {
public:
explicit ParakeetFrontend(std::shared_ptr<const ParakeetTDTAssets> assets);
ParakeetFrontendFeatures extract(
const engine::runtime::AudioBuffer & audio,
bool center) const;
private:
engine::audio::NemoMelFrontend frontend_;
};
} // namespace engine::community_models::parakeet_tdt