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
86 lines
2.8 KiB
C++
86 lines
2.8 KiB
C++
#pragma once
|
|
|
|
#include "engine/community_models/sanotts/config.h"
|
|
|
|
#include "engine/framework/assets/resource_bundle.h"
|
|
#include "engine/framework/assets/tensor_source.h"
|
|
|
|
#include <array>
|
|
#include <cstdint>
|
|
#include <filesystem>
|
|
#include <memory>
|
|
#include <string>
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
|
|
namespace engine::models::sanotts {
|
|
|
|
enum class SanoTtsGraph {
|
|
Nano, // mel-100 -> ConvNeXt-1D -> iSTFT, noise-fed (heart, heart-nano)
|
|
Piperlite, // 192-ch latent -> 3-stage ConvTranspose1d, deterministic (amy, ...)
|
|
};
|
|
|
|
struct SanoTtsPiperConfig {
|
|
std::string voice;
|
|
std::string language; // short code the session validates against: en, vi, id
|
|
std::string espeak_voice;
|
|
int64_t sample_rate = 22050;
|
|
double duration_length_scale = 1.0;
|
|
|
|
int64_t duration_vocab = 0;
|
|
int64_t duration_hidden = 0;
|
|
int64_t duration_depth = 0;
|
|
int64_t duration_kernel = 5;
|
|
int64_t duration_max_tokens = 0;
|
|
int64_t duration_max_frames = 0;
|
|
|
|
int64_t acoustic_vocab = 0;
|
|
int64_t acoustic_hidden = 0;
|
|
int64_t acoustic_depth = 0;
|
|
int64_t acoustic_token_depth = 0;
|
|
int64_t acoustic_kernel = 5;
|
|
int64_t acoustic_out_channels = 0;
|
|
|
|
/**
|
|
* Output adapter of a `calibrated` acoustic student: a latent calibration
|
|
* layer trained onto an already-finished token_context body, so a voice
|
|
* either carries one or omits it entirely. Modes match the reference
|
|
* exporter; `None` is the case where the config has no `adapter` key.
|
|
*/
|
|
enum class AdapterMode { None = 0, Affine = 1, Depthwise = 2, LowRank = 3, DepthwiseLowRank = 4 };
|
|
AdapterMode adapter_mode = AdapterMode::None;
|
|
int64_t adapter_kernel = 0;
|
|
int64_t adapter_rank = 0;
|
|
|
|
bool adapter_has_depthwise() const {
|
|
return adapter_mode == AdapterMode::Depthwise ||
|
|
adapter_mode == AdapterMode::DepthwiseLowRank;
|
|
}
|
|
bool adapter_has_lowrank() const {
|
|
return adapter_mode == AdapterMode::LowRank ||
|
|
adapter_mode == AdapterMode::DepthwiseLowRank;
|
|
}
|
|
|
|
std::array<int64_t, 4> channels = {0, 0, 0, 0};
|
|
std::array<std::vector<int64_t>, 3> stage_branches;
|
|
int64_t post_filter_channels = 0;
|
|
int64_t post_filter_layers = 0;
|
|
int64_t post_filter_kernel = 9;
|
|
double post_filter_scale = 0.0;
|
|
|
|
/** Piper phoneme_id_map: one UTF-8 codepoint -> id. */
|
|
std::unordered_map<std::string, int32_t> phoneme_id_map;
|
|
};
|
|
|
|
struct SanoTtsAssets {
|
|
assets::ResourceBundle resources;
|
|
SanoTtsGraph graph = SanoTtsGraph::Nano;
|
|
SanoTtsConfig config; // valid when graph == Nano
|
|
SanoTtsPiperConfig piper; // valid when graph == Piperlite
|
|
std::shared_ptr<const assets::TensorSource> weights;
|
|
};
|
|
|
|
std::shared_ptr<const SanoTtsAssets> load_sanotts_assets(
|
|
const std::filesystem::path & model_path);
|
|
|
|
} // namespace engine::models::sanotts
|