voice_audio_multi/include/engine/models/seed_vc/whisper_content.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

38 lines
1.3 KiB
C++

#pragma once
#include "engine/framework/assets/tensor_source.h"
#include "engine/framework/core/backend.h"
#include "engine/framework/modules/speech_encoders/whisper_frontend.h"
#include <cstdint>
#include <memory>
#include <vector>
namespace engine::models::seed_vc {
std::vector<float> compute_whisper_log_mel(const std::vector<float> & waveform_16k, size_t threads);
class SeedVcWhisperContentEncoder {
public:
SeedVcWhisperContentEncoder() = default;
SeedVcWhisperContentEncoder(
std::shared_ptr<const engine::assets::TensorSource> source,
engine::core::BackendConfig backend,
engine::assets::TensorStorageType storage_type);
~SeedVcWhisperContentEncoder();
SeedVcWhisperContentEncoder(SeedVcWhisperContentEncoder &&) noexcept;
SeedVcWhisperContentEncoder & operator=(SeedVcWhisperContentEncoder &&) noexcept;
SeedVcWhisperContentEncoder(const SeedVcWhisperContentEncoder &) = delete;
SeedVcWhisperContentEncoder & operator=(const SeedVcWhisperContentEncoder &) = delete;
int64_t channels() const noexcept;
std::vector<float> extract_16k_mono(
const std::vector<float> & waveform_16k,
size_t threads) const;
private:
engine::modules::WhisperFrontendComponent frontend_;
};
} // namespace engine::models::seed_vc