voice_audio_multi/include/engine/models/index_tts2/style_encoder.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

34 lines
869 B
C++

#pragma once
#include "engine/framework/modules/speaker_encoders/campplus_encoder.h"
#include "engine/models/index_tts2/assets.h"
#include <memory>
#include <vector>
namespace engine::models::index_tts2 {
struct IndexTTS2StyleEmbedding {
std::vector<float> values;
int64_t dims = 0;
};
class IndexTTS2CampplusStyleEncoder {
public:
IndexTTS2CampplusStyleEncoder(
std::shared_ptr<const IndexTTS2Assets> assets,
core::BackendConfig backend,
engine::assets::TensorStorageType weight_storage_type);
IndexTTS2StyleEmbedding embed_fbank(
const std::vector<float> & features,
int64_t frames,
int64_t dims) const;
void release_graph();
private:
std::shared_ptr<const IndexTTS2Assets> assets_;
engine::modules::CampplusEncoderComponent component_;
};
} // namespace engine::models::index_tts2