File size: 1,188 Bytes
35aaf1e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import logging
logging.getLogger('numba').setLevel(logging.WARNING)
import IPython.display as ipd
import torch
import commons
import utils
import ONNXVITS_infer
from text import text_to_sequence

def get_text(text, hps):
    text_norm = text_to_sequence(text, hps.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

hps = utils.get_hparams_from_file("../vits/pretrained_models/uma87.json")

net_g = ONNXVITS_infer.SynthesizerTrn(
    len(hps.symbols),
    hps.data.filter_length // 2 + 1,
    hps.train.segment_size // hps.data.hop_length,
    n_speakers=hps.data.n_speakers,
    **hps.model)
_ = net_g.eval()

_ = utils.load_checkpoint("../vits/pretrained_models/uma_1153000.pth", net_g)

text1 = get_text("γŠγ―γ‚ˆγ†γ”γ–γ„γΎγ™γ€‚", hps)
stn_tst = text1
with torch.no_grad():
    x_tst = stn_tst.unsqueeze(0)
    x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
    sid = torch.LongTensor([0])
    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()
print(audio)