File size: 1,150 Bytes
295a0ef |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
# import sengiri
import re
import torch
import commons
import utils
from models import SynthesizerTrn
from text.symbols import symbols
from text import text_to_sequence
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(f"pretrained_model/arona_ms_istft_vits_config.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(f"pretrained_model/arona_ms_istft_vits.pth", net_g, None)
text = '物語は嘘から始まる。'
SPEECH_SPEED = 1
stn_tst = get_text(text, hps)
with torch.no_grad():
x_tst = stn_tst.cuda().unsqueeze(0)
x_tst_lengths = torch.LongTensor([stn_tst.size(0)]).cuda()
audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=1/SPEECH_SPEED)[0][0,0].data.cpu().float().numpy()
|