Function main

examples/quantize/main.cpp:60–100

}

int main(int argc, char** argv) {
    if (argc != 4) {
        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
        ggml_print_ftypes(stderr);
        return 1;
    }

    // needed to initialize f16 tables
    {
        struct ggml_init_params params = {0, NULL, false};
        struct ggml_context* ctx = ggml_init(params);
        ggml_free(ctx);
    }

    const char* fname_inp = argv[1];
    const char* fname_out = argv[2];

    const ggml_ftype ftype = ggml_parse_ftype(argv[3]);

    const int64_t t_main_start_us = ggml_time_us();

    int64_t t_quantize_us = 0;

    // load the model
    {
        const int64_t t_start_us = ggml_time_us();
        bark_model_quantize(fname_inp, fname_out, ggml_ftype(ftype));
        t_quantize_us = ggml_time_us() - t_start_us;
    }

    // report timing
    {
        const int64_t t_main_end_us = ggml_time_us();

        printf("\n");
        printf("%s: quantize time = %8.2f ms\n", __func__, t_quantize_us / 1000.0f);
        printf("%s:    total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us) / 1000.0f);
    }

    return 0;
}