voice_audio_multi/include/engine/models/sam_audio/conditioner.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

32 lines
798 B
C++

#pragma once
#include "engine/framework/assets/tensor_source.h"
#include "engine/framework/core/execution_context.h"
#include <memory>
#include <string>
#include <vector>
namespace engine::models::sam_audio {
struct TextConditioning {
std::vector<int32_t> tokens;
std::vector<float> features;
};
class T5TextEncoder {
public:
T5TextEncoder(std::shared_ptr<const assets::TensorSource> source,
core::ExecutionContext & execution,
const std::filesystem::path & config,
const std::filesystem::path & tokenizer,
int64_t max_length = 512);
~T5TextEncoder();
TextConditioning encode(const std::string & text);
private:
struct Impl;
std::unique_ptr<Impl> impl_;
};
} // namespace engine::models::sam_audio