File size: 6,041 Bytes
20d05ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from vc_infer_pipeline import VC
from myutils import Audio
from infer_pack.models import (
    SynthesizerTrnMs256NSFsid,
    SynthesizerTrnMs256NSFsid_nono,
    SynthesizerTrnMs768NSFsid,
    SynthesizerTrnMs768NSFsid_nono,
)
from fairseq import checkpoint_utils
from config import Config
import torch
import numpy as np
import traceback
import os
import sys
import warnings

now_dir = os.getcwd()
sys.path.append(now_dir)
os.makedirs(os.path.join(now_dir, "audios"), exist_ok=True)
os.makedirs(os.path.join(now_dir, "audio-outputs"), exist_ok=True)
os.makedirs(os.path.join(now_dir, "weights"), exist_ok=True)
warnings.filterwarnings("ignore")
torch.manual_seed(114514)

config = Config()

hubert_model = None
weight_root = "weights"

def load_hubert():
    # Determinar si existe una tarjeta N que pueda usarse para entrenar y acelerar la inferencia.
    global hubert_model
    models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
        ["hubert_base.pt"],
        suffix="",
    )
    hubert_model = models[0]
    hubert_model = hubert_model.to(config.device)
    if config.is_half:
        hubert_model = hubert_model.half()
    else:
        hubert_model = hubert_model.float()
    hubert_model.eval()

def vc_single(
    sid,
    input_audio_path0,
    input_audio_path1,
    f0_up_key,
    f0_file,
    f0_method,
    file_index,
    file_index2,
    # file_big_npy,
    index_rate,
    filter_radius,
    resample_sr,
    rms_mix_rate,
    protect,
    crepe_hop_length,
):
    global tgt_sr, net_g, vc, hubert_model, version
    if input_audio_path0 is None or input_audio_path0 is None:
        return "You need to upload an audio", None
    f0_up_key = int(f0_up_key)
    try:
        if input_audio_path0 == "":
            audio = Audio.load_audio(input_audio_path1, 16000)
        else:
            audio = Audio.load_audio(input_audio_path0, 16000)

        audio_max = np.abs(audio).max() / 0.95
        if audio_max > 1:
            audio /= audio_max
        times = [0, 0, 0]
        if not hubert_model:
            load_hubert()
        if_f0 = cpt.get("f0", 1)
        file_index = (
            (
                file_index.strip(" ")
                .strip('"')
                .strip("\n")
                .strip('"')
                .strip(" ")
                .replace("trained", "added")
            )
            if file_index != ""
            else file_index2
        )

        audio_opt = vc.pipeline(
            hubert_model,
            net_g,
            sid,
            audio,
            input_audio_path1,
            times,
            f0_up_key,
            f0_method,
            file_index,
            # file_big_npy,
            index_rate,
            if_f0,
            filter_radius,
            tgt_sr,
            resample_sr,
            rms_mix_rate,
            version,
            protect,
            crepe_hop_length,
            f0_file=f0_file,
        )
        if tgt_sr != resample_sr >= 16000:
            tgt_sr = resample_sr
        index_info = (
            "Using index:%s." % file_index
            if os.path.exists(file_index)
            else "Index not used."
        )
        print(index_info)
        return "Success.\n %s\nTime:\n npy:%ss, f0:%ss, infer:%ss" % (
            index_info,
            times[0],
            times[1],
            times[2],
        ), (tgt_sr, audio_opt)
    except:
        info = traceback.format_exc()
        print(info)
        return info, (None, None)

def get_vc(model_name):
    global tgt_sr, net_g, vc, cpt, version

    # Comprobar si se pasó uno o varios modelos
    if model_name == "" or model_name == []:
        global hubert_model
        if hubert_model is not None:  # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
            print("Limpiar caché")
            del net_g, vc, hubert_model, tgt_sr  # ,cpt
            hubert_model = net_g = vc = hubert_model = tgt_sr = None

            # Si hay una GPU disponible, libera la memoria de la GPU
            if torch.cuda.is_available():
                torch.cuda.empty_cache()

            # Bloque de abajo no limpia completamente
            if_f0 = cpt.get("f0", 1)
            version = cpt.get("version", "v1")
            if version == "v1":
                if if_f0 == 1:
                    net_g = SynthesizerTrnMs256NSFsid(
                        *cpt["config"], is_half=config.is_half
                    )
                else:
                    net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
            elif version == "v2":
                if if_f0 == 1:
                    net_g = SynthesizerTrnMs768NSFsid(
                        *cpt["config"], is_half=config.is_half
                    )
            else:
                net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])

            del net_g, cpt
            if torch.cuda.is_available():
                torch.cuda.empty_cache()
            cpt = None
        return {"success": False, "message": "No se proporcionó un sid"}

    person = "%s/%s" % (weight_root, model_name)
    print("Cargando %s" % person)
    cpt = torch.load(person, map_location="cpu")
    tgt_sr = cpt["config"][-1]
    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]
    if_f0 = cpt.get("f0", 1)
    version = cpt.get("version", "v1")

    if version == "v1":
        if if_f0 == 1:
            net_g = SynthesizerTrnMs256NSFsid(
                *cpt["config"], is_half=config.is_half)
        else:
            net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
    elif version == "v2":
        if if_f0 == 1:
            net_g = SynthesizerTrnMs768NSFsid(
                *cpt["config"], is_half=config.is_half)
    else:
        net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
    del net_g.enc_q

    print(net_g.load_state_dict(cpt["weight"], strict=False))
    net_g.eval().to(config.device)
    if config.is_half:
        net_g = net_g.half()
    else:
        net_g = net_g.float()
    vc = VC(tgt_sr, config)