voice_audio_multi/include/engine/models/sam_audio/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

29 lines
841 B
C++

#pragma once
#include <cstdint>
#include <cstddef>
#include <filesystem>
#include <vector>
namespace engine::models::sam_audio {
struct DecodedFrame {
double time = 0.0;
std::vector<uint8_t> rgb;
};
struct SourceVideo {
int64_t width = 0;
int64_t height = 0;
std::vector<DecodedFrame> frames;
};
SourceVideo load_video_frames(const std::filesystem::path & path);
std::vector<size_t> select_video_frames(const SourceVideo & video, int64_t frames,
int64_t hop, int sample_rate);
// Matches torchvision's antialiased bicubic RGB resize and [-1,1] normalization.
std::vector<float> prepare_video_frame(const std::vector<uint8_t> & rgb, int width, int height);
std::vector<float> load_reference_image(const std::filesystem::path & path);
} // namespace engine::models::sam_audio