voice_audio_multi/include/engine/community_models/kitten_tts2/decoder.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

23 lines
735 B
C++

#pragma once
#include <cstdint>
#include <filesystem>
#include <memory>
#include <vector>
#include "engine/framework/assets/tensor_source.h"
#include "engine/framework/core/execution_context.h"
namespace engine::community_models::kitten_tts2 {
class WaveformDecoder {
public:
WaveformDecoder(std::shared_ptr<const assets::TensorSource> source,
const core::ExecutionContext & execution, bool neon_vocoder = false);
~WaveformDecoder();
std::vector<float> decode(const std::vector<int32_t> & codes,
const std::vector<int64_t> & prompt_tokens, const std::vector<float> & prompt_mel,
const std::vector<float> & embedding, uint64_t seed);
private:
struct Impl;
std::unique_ptr<Impl> impl_;
};
}