import sherpa_onnx
import soundfile as sf

config = sherpa_onnx.OfflineTtsConfig(
    model=sherpa_onnx.OfflineTtsModelConfig(
        matcha=sherpa_onnx.OfflineTtsMatchaModelConfig(
            acoustic_model="matcha-icefall-zh-en/model-steps-3.onnx",
            vocoder="vocos-16khz-univ.onnx",
            lexicon="matcha-icefall-zh-en/lexicon.txt",
            tokens="matcha-icefall-zh-en/tokens.txt",
            data_dir="matcha-icefall-zh-en/espeak-ng-data",
        ),
        num_threads=2,
        debug=True, # set it False to disable debug output
    ),
    max_num_sentences=1,
    rule_fsts="matcha-icefall-zh-en/phone-zh.fst,matcha-icefall-zh-en/date-zh.fst,matcha-icefall-zh-en/number-zh.fst",
)

if not config.validate():
    raise ValueError("Please check your config")

tts = sherpa_onnx.OfflineTts(config)
text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。在这次vocation中，我们计划去Paris欣赏埃菲尔铁塔和卢浮宫的美景。某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。开始数字测试。2025年12月4号，拨打110或者189202512043。123456块钱。在这个快速发展的时代，人工智能技术正在改变我们的生活方式。语音合成作为人工智能的重要应用之一，让机器能够用自然流畅的语音与人类进行交流。"


audio = tts.generate(text, sid=0, speed=1.0)

sf.write(
    "./test.mp3",
    audio.samples,
    samplerate=audio.sample_rate,
)

#include <stdio.h>
#include <string.h>

#include "sherpa-onnx/c-api/c-api.h"

int main() {
  SherpaOnnxOfflineTtsConfig config;
  memset(&config, 0, sizeof(config));

  config.model.matcha.acoustic_model = "matcha-icefall-zh-en/model-steps-3.onnx";
  config.model.matcha.vocoder = "vocos-16khz-univ.onnx";
  config.model.matcha.lexicon = "matcha-icefall-zh-en/lexicon.txt";
  config.model.matcha.tokens = "matcha-icefall-zh-en/tokens.txt";
  config.model.matcha.data_dir = "matcha-icefall-zh-en/espeak-ng-data";
  config.model.num_threads = 1;

  // If you want to see debug messages, please set it to 1
  config.model.debug = 0;
  config.rule_fsts = "matcha-icefall-zh-en/phone-zh.fst,matcha-icefall-zh-en/date-zh.fst,matcha-icefall-zh-en/number-zh.fst";

  const SherpaOnnxOfflineTts *tts = SherpaOnnxCreateOfflineTts(&config);

  int sid = 0; // speaker id
  const char *text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。在这次vocation中，我们计划去Paris欣赏埃菲尔铁塔和卢浮宫的美景。某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。开始数字测试。2025年12月4号，拨打110或者189202512043。123456块钱。在这个快速发展的时代，人工智能技术正在改变我们的生活方式。语音合成作为人工智能的重要应用之一，让机器能够用自然流畅的语音与人类进行交流。";

  const SherpaOnnxGeneratedAudio *audio =
      SherpaOnnxOfflineTtsGenerate(tts, text, sid, 1.0);

  SherpaOnnxWriteWave(audio->samples, audio->n, audio->sample_rate,
                      "./test.wav");

  // You need to free the pointers to avoid memory leak in your app
  SherpaOnnxDestroyOfflineTtsGeneratedAudio(audio);
  SherpaOnnxDestroyOfflineTts(tts);

  printf("Saved to ./test.wav\n");

  return 0;
}

#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.matcha.acoustic_model = "matcha-icefall-zh-en/model-steps-3.onnx";
  config.model.matcha.vocoder = "vocos-16khz-univ.onnx";
  config.model.matcha.lexicon = "matcha-icefall-zh-en/lexicon.txt";
  config.model.matcha.tokens = "matcha-icefall-zh-en/tokens.txt";
  config.model.matcha.data_dir = "matcha-icefall-zh-en/espeak-ng-data";
  config.model.num_threads = 1;

  // If you want to see debug messages, please set it to 1
  config.model.debug = 0;
  config.rule_fsts = "matcha-icefall-zh-en/phone-zh.fst,matcha-icefall-zh-en/date-zh.fst,matcha-icefall-zh-en/number-zh.fst";

  std::string filename = "./test.wav";
  std::string text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。在这次vocation中，我们计划去Paris欣赏埃菲尔铁塔和卢浮宫的美景。某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。开始数字测试。2025年12月4号，拨打110或者189202512043。123456块钱。在这个快速发展的时代，人工智能技术正在改变我们的生活方式。语音合成作为人工智能的重要应用之一，让机器能够用自然流畅的语音与人类进行交流。";

  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;
}