File size: 6,451 Bytes
6c9cbc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
"""
版本管理、兼容推理及模型加载实现。
版本说明:
    1. 版本号与github的release版本号对应,使用哪个release版本训练的模型即对应其版本号
    2. 请在模型的config.json中显示声明版本号,添加一个字段"version" : "你的版本号"
特殊版本说明:
    1.1.1-fix: 1.1.1版本训练的模型,但是在推理时使用dev的日语修复
    1.1.1-dev: dev开发
    2.0:当前版本
"""
import torch
import commons
from text import cleaned_text_to_sequence, get_bert
from text.cleaner import clean_text
import utils

from models import SynthesizerTrn
from text.symbols import symbols
from oldVersion.V111.models import SynthesizerTrn as V111SynthesizerTrn
from oldVersion.V111.text import symbols as V111symbols
from oldVersion.V110.models import SynthesizerTrn as V110SynthesizerTrn
from oldVersion.V110.text import symbols as V110symbols
from oldVersion.V101.models import SynthesizerTrn as V101SynthesizerTrn
from oldVersion.V101.text import symbols as V101symbols

from oldVersion import V111, V110, V101

# 当前版本信息
latest_version = "2.0"

# 版本兼容
SynthesizerTrnMap = {
    "1.1.1-fix": V111SynthesizerTrn,
    "1.1.1": V111SynthesizerTrn,
    "1.1": V110SynthesizerTrn,
    "1.1.0": V110SynthesizerTrn,
    "1.0.1": V101SynthesizerTrn,
    "1.0": V101SynthesizerTrn,
    "1.0.0": V101SynthesizerTrn,
}

symbolsMap = {
    "1.1.1-fix": V111symbols,
    "1.1.1": V111symbols,
    "1.1": V110symbols,
    "1.1.0": V110symbols,
    "1.0.1": V101symbols,
    "1.0": V101symbols,
    "1.0.0": V101symbols,
}


def get_net_g(model_path: str, version: str, device: str, hps):
    if version != latest_version:
        net_g = SynthesizerTrnMap[version](
            len(symbolsMap[version]),
            hps.data.filter_length // 2 + 1,
            hps.train.segment_size // hps.data.hop_length,
            n_speakers=hps.data.n_speakers,
            **hps.model,
        ).to(device)
    else:
        # 当前版本模型 net_g
        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,
        ).to(device)
    _ = net_g.eval()
    _ = utils.load_checkpoint(model_path, net_g, None, skip_optimizer=True)
    return net_g


def get_text(text, language_str, hps, device):
    # 在此处实现当前版本的get_text
    norm_text, phone, tone, word2ph = clean_text(text, language_str)
    phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)

    if hps.data.add_blank:
        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 = get_bert(norm_text, word2ph, language_str, device)
    del word2ph
    assert bert.shape[-1] == len(phone), phone

    if language_str == "ZH":
        bert = bert
        ja_bert = torch.zeros(1024, len(phone))
        en_bert = torch.zeros(1024, len(phone))
    elif language_str == "JP":
        bert = torch.zeros(1024, len(phone))
        ja_bert = bert
        en_bert = torch.zeros(1024, len(phone))
    elif language_str == "EN":
        bert = torch.zeros(1024, len(phone))
        ja_bert = torch.zeros(1024, len(phone))
        en_bert = bert
    else:
        raise ValueError("language_str should be ZH, JP or EN")

    assert bert.shape[-1] == len(
        phone
    ), f"Bert seq len {bert.shape[-1]} != {len(phone)}"

    phone = torch.LongTensor(phone)
    tone = torch.LongTensor(tone)
    language = torch.LongTensor(language)
    return bert, ja_bert, en_bert, phone, tone, language


def infer(
    text,
    sdp_ratio,
    noise_scale,
    noise_scale_w,
    length_scale,
    sid,
    language,
    hps,
    net_g,
    device,
):
    # 支持中日双语版本
    inferMap_V2 = {
        "1.1.1-fix": V111.infer_fix,
        "1.1.1": V111.infer,
        "1.1": V110.infer,
        "1.1.0": V110.infer,
    }
    # 仅支持中文版本
    # 在测试中,并未发现两个版本的模型不能互相通用
    inferMap_V1 = {
        "1.0.1": V101.infer,
        "1.0": V101.infer,
        "1.0.0": V101.infer,
    }
    version = hps.version if hasattr(hps, "version") else latest_version
    # 非当前版本,根据版本号选择合适的infer
    if version != latest_version:
        if version in inferMap_V2.keys():
            return inferMap_V2[version](
                text,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                sid,
                language,
                hps,
                net_g,
                device,
            )
        if version in inferMap_V1.keys():
            return inferMap_V1[version](
                text,
                sdp_ratio,
                noise_scale,
                noise_scale_w,
                length_scale,
                sid,
                hps,
                net_g,
                device,
            )
    # 在此处实现当前版本的推理
    bert, ja_bert, en_bert, phones, tones, lang_ids = get_text(
        text, language, hps, device
    )
    with torch.no_grad():
        x_tst = phones.to(device).unsqueeze(0)
        tones = tones.to(device).unsqueeze(0)
        lang_ids = lang_ids.to(device).unsqueeze(0)
        bert = bert.to(device).unsqueeze(0)
        ja_bert = ja_bert.to(device).unsqueeze(0)
        en_bert = en_bert.to(device).unsqueeze(0)
        x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device)
        del phones
        speakers = torch.LongTensor([hps.data.spk2id[sid]]).to(device)
        audio = (
            net_g.infer(
                x_tst,
                x_tst_lengths,
                speakers,
                tones,
                lang_ids,
                bert,
                ja_bert,
                en_bert,
                sdp_ratio=sdp_ratio,
                noise_scale=noise_scale,
                noise_scale_w=noise_scale_w,
                length_scale=length_scale,
            )[0][0, 0]
            .data.cpu()
            .float()
            .numpy()
        )
        del x_tst, tones, lang_ids, bert, x_tst_lengths, speakers
        torch.cuda.empty_cache()
        return audio