import ONNXVITS_models
import utils
from text.symbols import symbols
from text import text_to_sequence
import torch
import commons

def get_text(text, hps):
    text_norm = text_to_sequence(text, symbols, hps.data.text_cleaners)
    if hps.data.add_blank:
        text_norm = commons.intersperse(text_norm, 0)
    text_norm = torch.LongTensor(text_norm)
    return text_norm

def get_label(text, label):
    if f'[{label}]' in text:
        return True, text.replace(f'[{label}]', '')
    else:
        return False, text

hps_ms = utils.get_hparams_from_file("/content/drive/MyDrive/moe/config.json")
net_g_ms = ONNXVITS_models.SynthesizerTrn(
    len(symbols),
    hps_ms.data.filter_length // 2 + 1,
    hps_ms.train.segment_size // hps_ms.data.hop_length,
    n_speakers=hps_ms.data.n_speakers,
    **hps_ms.model)
_ = net_g_ms.eval()

_ = utils.load_checkpoint("/content/drive/MyDrive/moe/G_909000.pth", net_g_ms)

text1 = get_text("[JA]ありがとうございます。[JA]", hps_ms)
stn_tst = text1
with torch.no_grad():
    x_tst = stn_tst.unsqueeze(0)
    x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
    sid = torch.tensor([0])
    o = net_g_ms(x_tst, x_tst_lengths, sid=sid, noise_scale=.667, noise_scale_w=0.8, length_scale=1)