This repository has been archived on 2025-08-26. You can view files and clone it, but cannot push or open issues or pull requests.
Files
enginex-mr_series-sherpa-onnx/sherpa-onnx/csrc/offline-tts-vits-model-config.h
Fangjun Kuang 9efe69720d Support VITS VCTK models (#367)
* Support VITS VCTK models

* Release v1.8.1
2023-10-16 17:22:30 +08:00

49 lines
1.3 KiB
C++

// sherpa-onnx/csrc/offline-tts-vits-model-config.h
//
// Copyright (c) 2023 Xiaomi Corporation
#ifndef SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_CONFIG_H_
#define SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_CONFIG_H_
#include <string>
#include "sherpa-onnx/csrc/parse-options.h"
namespace sherpa_onnx {
struct OfflineTtsVitsModelConfig {
std::string model;
std::string lexicon;
std::string tokens;
float noise_scale = 0.667;
float noise_scale_w = 0.8;
float length_scale = 1;
// used only for multi-speaker models, e.g, vctk speech dataset.
// Not applicable for single-speaker models, e.g., ljspeech dataset
OfflineTtsVitsModelConfig() = default;
OfflineTtsVitsModelConfig(const std::string &model,
const std::string &lexicon,
const std::string &tokens,
float noise_scale = 0.667,
float noise_scale_w = 0.8, float length_scale = 1)
: model(model),
lexicon(lexicon),
tokens(tokens),
noise_scale(noise_scale),
noise_scale_w(noise_scale_w),
length_scale(length_scale) {}
void Register(ParseOptions *po);
bool Validate() const;
std::string ToString() const;
};
} // namespace sherpa_onnx
#endif // SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_CONFIG_H_