kitten-tts-en-cxx-api.cc
2.3 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
// cxx-api-examples/kitten-tts-en-cxx-api.cc
//
// Copyright (c) 2025 Xiaomi Corporation
// This file shows how to use sherpa-onnx CXX API
// for English TTS with Kitten.
//
// clang-format off
/*
Usage
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
tar xf kitten-nano-en-v0_1-fp16.tar.bz2
rm kitten-nano-en-v0_1-fp16.tar.bz2
./kitten-tts-en-cxx-api
*/
// clang-format on
#include <cstdint>
#include <cstdio>
#include <string>
#include "sherpa-onnx/c-api/cxx-api.h"
static int32_t ProgressCallback(const float *samples, int32_t num_samples,
float progress, void *arg) {
fprintf(stderr, "Progress: %.3f%%\n", progress * 100);
// return 1 to continue generating
// return 0 to stop generating
return 1;
}
int32_t main(int32_t argc, char *argv[]) {
using namespace sherpa_onnx::cxx; // NOLINT
OfflineTtsConfig config;
config.model.kitten.model = "./kitten-nano-en-v0_1-fp16/model.fp16.onnx";
config.model.kitten.voices = "./kitten-nano-en-v0_1-fp16/voices.bin";
config.model.kitten.tokens = "./kitten-nano-en-v0_1-fp16/tokens.txt";
config.model.kitten.data_dir = "./kitten-nano-en-v0_1-fp16/espeak-ng-data";
config.model.num_threads = 2;
// If you don't want to see debug messages, please set it to 0
config.model.debug = 1;
std::string filename = "./generated-kitten-en-cxx.wav";
std::string text =
"Today as always, men fall into two groups: slaves and free men. Whoever "
"does not have two-thirds of his day for himself, is a slave, whatever "
"he may be: a statesman, a businessman, an official, or a scholar. "
"Friends fell out often because life was changing so fast. The easiest "
"thing in the world was to lose touch with someone.";
auto tts = OfflineTts::Create(config);
int32_t sid = 0;
float speed = 1.0; // larger -> faster in speech speed
#if 0
// If you don't want to use a callback, then please enable this branch
GeneratedAudio audio = tts.Generate(text, sid, speed);
#else
GeneratedAudio audio = tts.Generate(text, sid, speed, ProgressCallback);
#endif
WriteWave(filename, {audio.samples, audio.sample_rate});
fprintf(stderr, "Input text is: %s\n", text.c_str());
fprintf(stderr, "Speaker ID is: %d\n", sid);
fprintf(stderr, "Saved to: %s\n", filename.c_str());
return 0;
}