offline-tts-vits-model-config.h
1.7 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
// 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;
// If data_dir is given, lexicon is ignored
// data_dir is for piper-phonemize, which uses espeak-ng
std::string data_dir;
// Used for Chinese TTS models using jieba
std::string dict_dir;
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,
const std::string &data_dir,
const std::string &dict_dir,
float noise_scale = 0.667,
float noise_scale_w = 0.8, float length_scale = 1)
: model(model),
lexicon(lexicon),
tokens(tokens),
data_dir(data_dir),
dict_dir(dict_dir),
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_