# import matplotlib.pyplot as plt
import logging
# logger = logging.getLogger(__name__)
import os
import json
import math
import torch
from torch import nn
from torch.nn import functional as F
from torch.utils.data import DataLoader

import commons
import utils
from data_utils import TextAudioLoader, TextAudioCollate, TextAudioSpeakerLoader, TextAudioSpeakerCollate
from models import SynthesizerTrn
from text.symbols import symbols
from text import text_to_sequence
import time

def get_text(text, hps):
    # text_norm = requests.post("http://121.5.171.42:39001/texttosequence?text="+text).json()["text_norm"]
    text_norm = text_to_sequence(text, hps.data.text_cleaners)
    # print(hps.data.text_cleaners)
    # print(text_norm)
    if hps.data.add_blank:
        text_norm = commons.intersperse(text_norm, 0)
    text_norm = torch.LongTensor(text_norm)
    return text_norm

def load_model(config_json, pth_path):
    dev = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    hps_ms = utils.get_hparams_from_file(f"./configs/{config_json}")
    
    global net_g
    net_g = SynthesizerTrn(
        len(symbols),
        hps_ms.data.filter_length // 2 + 1,
        hps_ms.train.segment_size // hps_ms.data.hop_length,
        **hps_ms.model).to(dev)
    _ = net_g.eval()
    _ = utils.load_checkpoint(pth_path, net_g)

    print("load_model:"+pth_path)
    return net_g
    
def local_run(c_id, text):
    stn_tst = get_text(text, hps)
    with torch.no_grad():
        x_tst = stn_tst.to(dev).unsqueeze(0)
        x_tst_lengths = torch.LongTensor([stn_tst.size(0)]).to(dev)
        sid = torch.LongTensor([c_id]).to(dev)
        audio = net_g.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=.667, noise_scale_w=0.8, length_scale=1)[0][0,0].data.cpu().float().numpy()

        return audio
    
CONFIG_FILE = "configs/config.json"

dev = torch.device("cpu")
hps = utils.get_hparams_from_file(CONFIG_FILE)