Function main

kleidiai-examples/audiogen/app/audiogen.cpp:429–696

}

int main(int32_t argc, char** argv) {

    // ----- Parse the cmd line arguments
    // ----------------------------------
    // Required arguments
    std::string models_base_path = "";
    std::string prompt           = "";
    std::string audio_input_path = "";
    size_t num_threads           = 0;
    // Optional arguments
    std::string output_file      = "";
    size_t seed                  = k_seed_default;
    size_t num_steps             = k_num_steps_default;
    float audio_len_sec          = static_cast<float>(k_audio_len_sec_default);
    float sigma_max              = static_cast<float>(k_sigma_max);

    int opt;
    while ((opt = getopt(argc, argv, "m:p:t:i:x:s:n:o:l:h")) != -1) {
        switch (opt) {
            case 'm': models_base_path = optarg; break;
            case 'p': prompt           = optarg; break;
            case 't': num_threads      = std::stoull(optarg); break;
            case 'i': audio_input_path = optarg; break;
            case 'x': sigma_max        = static_cast<float>(std::stof(optarg)); break;
            case 's': seed             = std::stoull(optarg); break;
            case 'n': num_steps        = std::stoull(optarg); break;
            case 'o': output_file      = optarg; break;
            case 'l': audio_len_sec    = static_cast<float>(std::stoull(optarg)); break;
            case 'h':
            default:
                print_usage(argv[0]);
                return EXIT_FAILURE;
        }
    }

    // Check the mandatory arguments
    if (models_base_path.empty() || prompt.empty() || num_threads <= 0) {
        fprintf(stderr, "ERROR: Missing required arguments.\n\n");
        print_usage(argv[0]);
        return EXIT_FAILURE;
    }

    if(sigma_max <= 0 || sigma_max >  1) {
        fprintf(stderr, "noise_level (sigma_max) must be between (0,1] \n");
        return EXIT_FAILURE;
    }

    std::string t5_tflite = models_base_path + "/conditioners_float32.tflite";
    std::string dit_tflite = models_base_path + "/dit_model.tflite";
    std::string autoencoder_tflite = models_base_path + "/autoencoder_model.tflite";
    std::string autoencoder_encoder_tflite = models_base_path + "/autoencoder_encoder_model.tflite";
    std::string sentence_model_path = models_base_path + "/spiece.model";

    auto env = get_litert_value(litert::Environment::Create({}));

    // If there is input audio, run the encoder model and release it, to avoid overloading memory
    std::vector<float> encoded_audio;
    if(!audio_input_path.empty()) {