| import matplotlib.pyplot as plt | |
| import IPython.display as ipd | |
| 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 | |
| from scipy.io.wavfile import write | |
| def get_text(text, hps): | |
| text_norm = text_to_sequence(text, 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 | |
| hps = utils.get_hparams_from_file("./configs/yuzu.json") | |
| net_g = SynthesizerTrn( | |
| len(symbols), | |
| hps.data.filter_length // 2 + 1, | |
| hps.train.segment_size // hps.data.hop_length, | |
| n_speakers=hps.data.n_speakers, | |
| **hps.model).cuda() | |
| _ = net_g.eval() | |
| _ = utils.load_checkpoint("pretrained_models/yuzu.pth", net_g, None) |