mirror of
https://github.com/k2-fsa/sherpa-onnx.git
synced 2026-01-09 07:41:06 +08:00
77 lines
2.3 KiB
C++
77 lines
2.3 KiB
C++
// cxx-api-examples/kokoro-tts-zh-en-cxx-api.cc
|
|
//
|
|
// Copyright (c) 2025 Xiaomi Corporation
|
|
|
|
// This file shows how to use sherpa-onnx CXX API
|
|
// for Chinese + English TTS with Kokoro.
|
|
//
|
|
// clang-format off
|
|
/*
|
|
Usage
|
|
|
|
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-multi-lang-v1_0.tar.bz2
|
|
tar xf kokoro-multi-lang-v1_0.tar.bz2
|
|
rm kokoro-multi-lang-v1_0.tar.bz2
|
|
|
|
./kokoro-tts-zh-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.kokoro.model = "./kokoro-multi-lang-v1_0/model.onnx";
|
|
config.model.kokoro.voices = "./kokoro-multi-lang-v1_0/voices.bin";
|
|
config.model.kokoro.tokens = "./kokoro-multi-lang-v1_0/tokens.txt";
|
|
config.model.kokoro.data_dir = "./kokoro-multi-lang-v1_0/espeak-ng-data";
|
|
config.model.kokoro.dict_dir = "./kokoro-multi-lang-v1_0/dict";
|
|
config.model.kokoro.lexicon =
|
|
"./kokoro-multi-lang-v1_0/lexicon-us-en.txt,./kokoro-multi-lang-v1_0/"
|
|
"lexicon-zh.txt";
|
|
|
|
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-kokoro-zh-en-cxx.wav";
|
|
std::string text =
|
|
"中英文语音合成测试。This is generated by next generation Kaldi using "
|
|
"Kokoro without Misaki. 你觉得中英文说的如何呢？";
|
|
|
|
auto tts = OfflineTts::Create(config);
|
|
int32_t sid = 50;
|
|
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;
|
|
}
|