File size: 2,525 Bytes
0372395
 
 
879cbd2
0372395
 
 
879cbd2
 
5422b18
0372395
879cbd2
 
 
5422b18
 
 
 
 
 
 
 
 
879cbd2
 
 
 
 
 
 
dc23363
 
 
 
 
 
879cbd2
5422b18
879cbd2
 
 
 
 
 
 
 
 
 
5422b18
 
879cbd2
 
5422b18
 
 
 
 
 
 
879cbd2
 
 
 
 
 
 
 
5422b18
0372395
5422b18
 
 
879cbd2
5422b18
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
65
66
67
68
69
70
71
72
73
74
75
import argparse
from multiprocessing import Pool, cpu_count

import torch
import torch.multiprocessing as mp
from tqdm import tqdm

import commons
import utils
from config import config
from text import cleaned_text_to_sequence, get_bert


def process_line(line):
    device = config.bert_gen_config.device
    if config.bert_gen_config.use_multi_device:
        rank = mp.current_process()._identity
        rank = rank[0] if len(rank) > 0 else 0
        if torch.cuda.is_available():
            gpu_id = rank % torch.cuda.device_count()
            device = torch.device(f"cuda:{gpu_id}")
        else:
            device = torch.device("cpu")
    wav_path, _, language_str, text, phones, tone, word2ph = line.strip().split("|")
    phone = phones.split(" ")
    tone = [int(i) for i in tone.split(" ")]
    word2ph = [int(i) for i in word2ph.split(" ")]
    word2ph = [i for i in word2ph]
    phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)

    phone = commons.intersperse(phone, 0)
    tone = commons.intersperse(tone, 0)
    language = commons.intersperse(language, 0)
    for i in range(len(word2ph)):
        word2ph[i] = word2ph[i] * 2
    word2ph[0] += 1

    bert_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".bert.pt")

    try:
        bert = torch.load(bert_path)
        assert bert.shape[-1] == len(phone)
    except Exception:
        bert = get_bert(text, word2ph, language_str, device)
        assert bert.shape[-1] == len(phone)
        torch.save(bert, bert_path)


preprocess_text_config = config.preprocess_text_config

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "-c", "--config", type=str, default=config.bert_gen_config.config_path
    )
    parser.add_argument(
        "--num_processes", type=int, default=config.bert_gen_config.num_processes
    )
    args, _ = parser.parse_known_args()
    config_path = args.config
    hps = utils.get_hparams_from_file(config_path)
    lines = []
    with open(hps.data.training_files, encoding="utf-8") as f:
        lines.extend(f.readlines())

    with open(hps.data.validation_files, encoding="utf-8") as f:
        lines.extend(f.readlines())
    if len(lines) != 0:
        num_processes = min(args.num_processes, cpu_count())
        with Pool(processes=num_processes) as pool:
            for _ in tqdm(pool.imap_unordered(process_line, lines), total=len(lines)):
                pass

    print(f"bert生成完毕!, 共有{len(lines)}个bert.pt生成!")