File size: 7,164 Bytes
668a7d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
208
209
210
211
212
213
214
215
216
"""
v1
runtime\python.exe myinfer-v2-0528.py 0 "E:\codes\py39\RVC-beta\todo-songs" "E:\codes\py39\logs\mi-test\added_IVF677_Flat_nprobe_7.index" harvest "E:\codes\py39\RVC-beta\output" "E:\codes\py39\test-20230416b\weights\mi-test.pth" 0.66 cuda:0 True 3 0 1 0.33
v2
runtime\python.exe myinfer-v2-0528.py 0 "E:\codes\py39\RVC-beta\todo-songs" "E:\codes\py39\test-20230416b\logs\mi-test-v2\aadded_IVF677_Flat_nprobe_1_v2.index" harvest "E:\codes\py39\RVC-beta\output_v2" "E:\codes\py39\test-20230416b\weights\mi-test-v2.pth" 0.66 cuda:0 True 3 0 1 0.33
"""
import os, sys, pdb, torch

now_dir = os.getcwd()
sys.path.append(now_dir)
import sys
import torch
import tqdm as tq
from multiprocessing import cpu_count


class Config:
    def __init__(self, device, is_half):
        self.device = device
        self.is_half = is_half
        self.n_cpu = 0
        self.gpu_name = None
        self.gpu_mem = None
        self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()

    def device_config(self) -> tuple:
        if torch.cuda.is_available():
            i_device = int(self.device.split(":")[-1])
            self.gpu_name = torch.cuda.get_device_name(i_device)
            if (
                ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
                or "P40" in self.gpu_name.upper()
                or "1060" in self.gpu_name
                or "1070" in self.gpu_name
                or "1080" in self.gpu_name
            ):
                print("16系/10系显卡和P40强制单精度")
                self.is_half = False
                for config_file in ["32k.json", "40k.json", "48k.json"]:
                    with open(f"configs/{config_file}", "r") as f:
                        strr = f.read().replace("true", "false")
                    with open(f"configs/{config_file}", "w") as f:
                        f.write(strr)
                with open("trainset_preprocess_pipeline_print.py", "r") as f:
                    strr = f.read().replace("3.7", "3.0")
                with open("trainset_preprocess_pipeline_print.py", "w") as f:
                    f.write(strr)
            else:
                self.gpu_name = None
            self.gpu_mem = int(
                torch.cuda.get_device_properties(i_device).total_memory
                / 1024
                / 1024
                / 1024
                + 0.4
            )
            if self.gpu_mem <= 4:
                with open("trainset_preprocess_pipeline_print.py", "r") as f:
                    strr = f.read().replace("3.7", "3.0")
                with open("trainset_preprocess_pipeline_print.py", "w") as f:
                    f.write(strr)
        elif torch.backends.mps.is_available():
            print("没有发现支持的N卡, 使用MPS进行推理")
            self.device = "mps"
        else:
            print("没有发现支持的N卡, 使用CPU进行推理")
            self.device = "cpu"
            self.is_half = True

        if self.n_cpu == 0:
            self.n_cpu = cpu_count()

        if self.is_half:
            # 6G显存配置
            x_pad = 3
            x_query = 10
            x_center = 60
            x_max = 65
        else:
            # 5G显存配置
            x_pad = 1
            x_query = 6
            x_center = 38
            x_max = 41

        if self.gpu_mem != None and self.gpu_mem <= 4:
            x_pad = 1
            x_query = 5
            x_center = 30
            x_max = 32

        return x_pad, x_query, x_center, x_max


f0up_key = sys.argv[1]
input_path = sys.argv[2]
index_path = sys.argv[3]
f0method = sys.argv[4]  # harvest or pm
opt_path = sys.argv[5]
model_path = sys.argv[6]
index_rate = float(sys.argv[7])
device = sys.argv[8]
is_half = bool(sys.argv[9])
filter_radius = int(sys.argv[10])
resample_sr = int(sys.argv[11])
rms_mix_rate = float(sys.argv[12])
protect = float(sys.argv[13])
print(sys.argv)
config = Config(device, is_half)
now_dir = os.getcwd()
sys.path.append(now_dir)
from vc_infer_pipeline import VC
from lib.infer_pack.models import (
    SynthesizerTrnMs256NSFsid,
    SynthesizerTrnMs256NSFsid_nono,
    SynthesizerTrnMs768NSFsid,
    SynthesizerTrnMs768NSFsid_nono,
)
from my_utils import load_audio
from fairseq import checkpoint_utils
from scipy.io import wavfile

hubert_model = None


def load_hubert():
    global hubert_model
    models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
        ["hubert_base.pt"],
        suffix="",
    )
    hubert_model = models[0]
    hubert_model = hubert_model.to(device)
    if is_half:
        hubert_model = hubert_model.half()
    else:
        hubert_model = hubert_model.float()
    hubert_model.eval()


def vc_single(sid, input_audio, f0_up_key, f0_file, f0_method, file_index, index_rate):
    global tgt_sr, net_g, vc, hubert_model, version
    if input_audio is None:
        return "You need to upload an audio", None
    f0_up_key = int(f0_up_key)
    audio = load_audio(input_audio, 16000)
    times = [0, 0, 0]
    if hubert_model == None:
        load_hubert()
    if_f0 = cpt.get("f0", 1)
    # audio_opt=vc.pipeline(hubert_model,net_g,sid,audio,times,f0_up_key,f0_method,file_index,file_big_npy,index_rate,if_f0,f0_file=f0_file)
    audio_opt = vc.pipeline(
        hubert_model,
        net_g,
        sid,
        audio,
        input_audio,
        times,
        f0_up_key,
        f0_method,
        file_index,
        index_rate,
        if_f0,
        filter_radius,
        tgt_sr,
        resample_sr,
        rms_mix_rate,
        version,
        protect,
        f0_file=f0_file,
    )
    print(times)
    return audio_opt


def get_vc(model_path):
    global n_spk, tgt_sr, net_g, vc, cpt, device, is_half, version
    print("loading pth %s" % model_path)
    cpt = torch.load(model_path, map_location="cpu")
    tgt_sr = cpt["config"][-1]
    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
    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=is_half)
        else:
            net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
    elif version == "v2":
        if if_f0 == 1:  #
            net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=is_half)
        else:
            net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
    del net_g.enc_q
    print(net_g.load_state_dict(cpt["weight"], strict=False))  # 不加这一行清不干净,真奇葩
    net_g.eval().to(device)
    if is_half:
        net_g = net_g.half()
    else:
        net_g = net_g.float()
    vc = VC(tgt_sr, config)
    n_spk = cpt["config"][-3]
    # return {"visible": True,"maximum": n_spk, "__type__": "update"}


get_vc(model_path)
audios = os.listdir(input_path)
for file in tq.tqdm(audios):
    if file.endswith(".wav"):
        file_path = input_path + "/" + file
        wav_opt = vc_single(
            0, file_path, f0up_key, None, f0method, index_path, index_rate
        )
        out_path = opt_path + "/" + file
        wavfile.write(out_path, tgt_sr, wav_opt)