voice_audio_multi/include/engine/models/pocket_tts/mimi_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

32 lines
669 B
C++

#pragma once
#include "ggml-backend.h"
#include <cstddef>
#include <cstdint>
#include <vector>
namespace engine::models::pocket_tts {
struct PocketTTSAssets;
struct PocketTTSBackendWeights;
struct MimiPromptEmbedding {
std::vector<float> values;
int64_t frames = 0;
};
class MimiEncoder {
public:
MimiEncoder() = default;
MimiPromptEmbedding encode_prompt_embedding(
ggml_backend_t backend,
int threads,
const PocketTTSAssets & manifest,
const PocketTTSBackendWeights & weights,
const std::vector<float> & waveform,
size_t graph_context_bytes) const;
};
} // namespace engine::models::pocket_tts