File size: 1,675 Bytes
de332ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
## LJSpeech
import torch

import commons
import utils
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


CONFIG_PATH = "./configs/vits2_ljs_nosdp.json"
MODEL_PATH = "./logs/G_114000.pth"
TEXT = "VITS-2 is Awesome!"
OUTPUT_WAV_PATH = "sample_vits2.wav"

hps = utils.get_hparams_from_file(CONFIG_PATH)

if (
    "use_mel_posterior_encoder" in hps.model.keys()
    and hps.model.use_mel_posterior_encoder == True
):
    print("Using mel posterior encoder for VITS2")
    posterior_channels = 80  # vits2
    hps.data.use_mel_posterior_encoder = True
else:
    print("Using lin posterior encoder for VITS1")
    posterior_channels = hps.data.filter_length // 2 + 1
    hps.data.use_mel_posterior_encoder = False

net_g = SynthesizerTrn(
    len(symbols),
    posterior_channels,
    hps.train.segment_size // hps.data.hop_length,
    **hps.model
).cuda()
_ = net_g.eval()

_ = utils.load_checkpoint(MODEL_PATH, net_g, None)

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=0.667, noise_scale_w=0.8, length_scale=1
        )[0][0, 0]
        .data.cpu()
        .float()
        .numpy()
    )

write(data=audio, rate=hps.data.sampling_rate, filename=OUTPUT_WAV_PATH)