voice_audio_multi/include/engine/models/hviske_asr/session.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

69 lines
2.8 KiB
C++

#pragma once
#include "engine/framework/model_spec/metadata.h"
#include "engine/framework/runtime/model.h"
#include "engine/framework/runtime/session_base.h"
#include "engine/models/hviske_asr/assets.h"
#include "engine/models/hviske_asr/decoder.h"
#include "engine/models/hviske_asr/encoder.h"
#include "engine/models/hviske_asr/frontend.h"
#include "engine/models/hviske_asr/weights.h"
#include <cstddef>
#include <memory>
#include <string>
#include <unordered_map>
#include <vector>
namespace engine::models::hviske_asr {
std::shared_ptr<runtime::IVoiceModelLoader> make_hviske_asr_loader();
class HviskeASRSession final
: public runtime::RuntimeSessionBase
, public runtime::IOfflineVoiceTaskSession {
public:
HviskeASRSession(
runtime::TaskSpec task,
runtime::SessionOptions options,
std::shared_ptr<const HviskeASRAssets> assets,
std::shared_ptr<const engine::model_spec::ModelContract> contract);
~HviskeASRSession() override;
std::string family() const override;
runtime::VoiceTaskKind task_kind() const override;
runtime::RunMode run_mode() const override;
void prepare(const runtime::SessionPreparationRequest & request) override;
runtime::TaskResult run(const runtime::TaskRequest & request) override;
private:
struct Segment {
runtime::AudioBuffer audio;
};
std::vector<Segment> prepare_segments(
const runtime::AudioBuffer & audio,
const std::unordered_map<std::string, std::string> & options) const;
std::string language_for_request(
const runtime::TaskRequest & request,
const std::unordered_map<std::string, std::string> & options) const;
bool punctuation_for_request(const std::unordered_map<std::string, std::string> & options) const;
HviskeDecodingOptions decoding_options_for_request(
const std::unordered_map<std::string, std::string> & options) const;
runtime::TaskSpec task_;
std::shared_ptr<const HviskeASRAssets> assets_;
std::shared_ptr<const engine::model_spec::ModelContract> contract_;
std::shared_ptr<const HviskeWeights> weights_;
size_t weight_context_bytes_ = 32ull * 1024ull * 1024ull;
size_t encoder_graph_arena_bytes_ = 512ull * 1024ull * 1024ull;
size_t decoder_prefill_graph_arena_bytes_ = 512ull * 1024ull * 1024ull;
size_t decoder_decode_graph_arena_bytes_ = 512ull * 1024ull * 1024ull;
engine::assets::TensorStorageType matmul_weight_storage_type_ = engine::assets::TensorStorageType::Native;
engine::assets::TensorStorageType conv_weight_storage_type_ = engine::assets::TensorStorageType::Native;
HviskeFrontend frontend_;
std::unique_ptr<HviskeConformerEncoderRuntime> encoder_;
std::unique_ptr<HviskeDecoderRuntime> decoder_;
};
} // namespace engine::models::hviske_asr