sherpa-onnx-wasm-main-tts.cc
3.4 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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
// wasm/sherpa-onnx-wasm-main-tts.cc
//
// Copyright (c) 2024 Xiaomi Corporation
#include <stdio.h>
#include <algorithm>
#include <memory>
#include "sherpa-onnx/c-api/c-api.h"
// see also
// https://emscripten.org/docs/porting/connecting_cpp_and_javascript/Interacting-with-code.html
extern "C" {
static_assert(sizeof(SherpaOnnxOfflineTtsVitsModelConfig) == 8 * 4, "");
static_assert(sizeof(SherpaOnnxOfflineTtsMatchaModelConfig) == 8 * 4, "");
static_assert(sizeof(SherpaOnnxOfflineTtsKokoroModelConfig) == 7 * 4, "");
static_assert(sizeof(SherpaOnnxOfflineTtsModelConfig) ==
sizeof(SherpaOnnxOfflineTtsVitsModelConfig) +
sizeof(SherpaOnnxOfflineTtsMatchaModelConfig) +
sizeof(SherpaOnnxOfflineTtsKokoroModelConfig) + 3 * 4,
"");
static_assert(sizeof(SherpaOnnxOfflineTtsConfig) ==
sizeof(SherpaOnnxOfflineTtsModelConfig) + 3 * 4,
"");
void MyPrint(SherpaOnnxOfflineTtsConfig *tts_config) {
auto tts_model_config = &tts_config->model;
auto vits_model_config = &tts_model_config->vits;
auto matcha_model_config = &tts_model_config->matcha;
auto kokoro = &tts_model_config->kokoro;
fprintf(stdout, "----------vits model config----------\n");
fprintf(stdout, "model: %s\n", vits_model_config->model);
fprintf(stdout, "lexicon: %s\n", vits_model_config->lexicon);
fprintf(stdout, "tokens: %s\n", vits_model_config->tokens);
fprintf(stdout, "data_dir: %s\n", vits_model_config->data_dir);
fprintf(stdout, "noise scale: %.3f\n", vits_model_config->noise_scale);
fprintf(stdout, "noise scale w: %.3f\n", vits_model_config->noise_scale_w);
fprintf(stdout, "length scale: %.3f\n", vits_model_config->length_scale);
fprintf(stdout, "dict_dir: %s\n", vits_model_config->dict_dir);
fprintf(stdout, "----------matcha model config----------\n");
fprintf(stdout, "acoustic_model: %s\n", matcha_model_config->acoustic_model);
fprintf(stdout, "vocoder: %s\n", matcha_model_config->vocoder);
fprintf(stdout, "lexicon: %s\n", matcha_model_config->lexicon);
fprintf(stdout, "tokens: %s\n", matcha_model_config->tokens);
fprintf(stdout, "data_dir: %s\n", matcha_model_config->data_dir);
fprintf(stdout, "noise scale: %.3f\n", matcha_model_config->noise_scale);
fprintf(stdout, "length scale: %.3f\n", matcha_model_config->length_scale);
fprintf(stdout, "dict_dir: %s\n", matcha_model_config->dict_dir);
fprintf(stdout, "----------kokoro model config----------\n");
fprintf(stdout, "model: %s\n", kokoro->model);
fprintf(stdout, "voices: %s\n", kokoro->voices);
fprintf(stdout, "tokens: %s\n", kokoro->tokens);
fprintf(stdout, "data_dir: %s\n", kokoro->data_dir);
fprintf(stdout, "length scale: %.3f\n", kokoro->length_scale);
fprintf(stdout, "dict_dir: %s\n", kokoro->dict_dir);
fprintf(stdout, "lexicon: %s\n", kokoro->lexicon);
fprintf(stdout, "----------tts model config----------\n");
fprintf(stdout, "num threads: %d\n", tts_model_config->num_threads);
fprintf(stdout, "debug: %d\n", tts_model_config->debug);
fprintf(stdout, "provider: %s\n", tts_model_config->provider);
fprintf(stdout, "----------tts config----------\n");
fprintf(stdout, "rule_fsts: %s\n", tts_config->rule_fsts);
fprintf(stdout, "rule_fars: %s\n", tts_config->rule_fars);
fprintf(stdout, "max num sentences: %d\n", tts_config->max_num_sentences);
}
void CopyHeap(const char *src, int32_t num_bytes, char *dst) {
std::copy(src, src + num_bytes, dst);
}
}