voice_audio_multi/include/engine/community_models/kitten_tts2/speaker.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

20 lines
692 B
C++

#pragma once
#include "engine/framework/assets/tensor_source.h"
#include "engine/framework/core/execution_context.h"
#include <memory>
#include <vector>
namespace engine::community_models::kitten_tts2 {
// XVectorSincNet identity encoder and Kitten's learned Qwen speaker projection.
class SpeakerEncoder {
public:
SpeakerEncoder(const assets::TensorSource & source, const assets::TensorSource & lm,
const core::ExecutionContext & execution);
~SpeakerEncoder();
std::vector<float> embed(const std::vector<float> & mono_16k) const;
std::vector<float> project(const std::vector<float> & embedding) const;
private:
struct Impl;
std::unique_ptr<Impl> impl_;
};
}