File size: 3,007 Bytes
879cbd2
 
5422b18
 
 
 
 
 
 
 
879cbd2
 
 
 
5220ea7
 
 
 
 
 
 
879cbd2
 
 
 
 
 
 
 
 
5422b18
879cbd2
 
 
 
 
 
5220ea7
 
 
 
 
 
 
879cbd2
 
 
 
5220ea7
 
 
 
 
 
 
879cbd2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
import sys

import torch
from transformers import AutoModelForMaskedLM, AutoTokenizer

from config import config

LOCAL_PATH = "./bert/chinese-roberta-wwm-ext-large"

tokenizer = AutoTokenizer.from_pretrained(LOCAL_PATH)

models = dict()


def get_bert_feature(
    text,
    word2ph,
    device=config.bert_gen_config.device,
    style_text=None,
    style_weight=0.7,
):
    if (
        sys.platform == "darwin"
        and torch.backends.mps.is_available()
        and device == "cpu"
    ):
        device = "mps"
    if not device:
        device = "cuda"
    if device not in models.keys():
        models[device] = AutoModelForMaskedLM.from_pretrained(LOCAL_PATH).to(device)
    with torch.no_grad():
        inputs = tokenizer(text, return_tensors="pt")
        for i in inputs:
            inputs[i] = inputs[i].to(device)
        res = models[device](**inputs, output_hidden_states=True)
        res = torch.cat(res["hidden_states"][-3:-2], -1)[0].cpu()
        if style_text:
            style_inputs = tokenizer(style_text, return_tensors="pt")
            for i in style_inputs:
                style_inputs[i] = style_inputs[i].to(device)
            style_res = models[device](**style_inputs, output_hidden_states=True)
            style_res = torch.cat(style_res["hidden_states"][-3:-2], -1)[0].cpu()
            style_res_mean = style_res.mean(0)
    assert len(word2ph) == len(text) + 2
    word2phone = word2ph
    phone_level_feature = []
    for i in range(len(word2phone)):
        if style_text:
            repeat_feature = (
                res[i].repeat(word2phone[i], 1) * (1 - style_weight)
                + style_res_mean.repeat(word2phone[i], 1) * style_weight
            )
        else:
            repeat_feature = res[i].repeat(word2phone[i], 1)
        phone_level_feature.append(repeat_feature)

    phone_level_feature = torch.cat(phone_level_feature, dim=0)

    return phone_level_feature.T


if __name__ == "__main__":
    word_level_feature = torch.rand(38, 1024)  # 12个词,每个词1024维特征
    word2phone = [
        1,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        2,
        1,
        1,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        1,
    ]

    # 计算总帧数
    total_frames = sum(word2phone)
    print(word_level_feature.shape)
    print(word2phone)
    phone_level_feature = []
    for i in range(len(word2phone)):
        print(word_level_feature[i].shape)

        # 对每个词重复word2phone[i]次
        repeat_feature = word_level_feature[i].repeat(word2phone[i], 1)
        phone_level_feature.append(repeat_feature)

    phone_level_feature = torch.cat(phone_level_feature, dim=0)
    print(phone_level_feature.shape)  # torch.Size([36, 1024])