voice_audio_multi/include/engine/models/kugelaudio/assets.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

37 lines
874 B
C++

#pragma once
#include "engine/models/kugelaudio/ar.h"
#include "engine/models/kugelaudio/codec.h"
#include "engine/models/kugelaudio/diffusion.h"
#include "engine/framework/model_spec/package.h"
#include <filesystem>
#include <memory>
#include <string>
#include <unordered_map>
#include <vector>
namespace engine::models::kugelaudio {
struct ModelConfig {
ArConfig ar;
DiffusionConfig diffusion;
CodecConfig codec;
int inference_steps = 20;
};
struct VoiceFeatures {
std::vector<float> mean;
float std = 0.5F;
};
struct ModelAssets {
assets::ResourceBundle resources;
ModelConfig config;
std::shared_ptr<const assets::TensorSource> weights;
std::unordered_map<std::string, VoiceFeatures> voices;
};
std::shared_ptr<const ModelAssets> load_assets(const std::filesystem::path & path);
} // namespace engine::models::kugelaudio