Retrieval-based-Voice-Conversion-WebUI/infer/modules/uvr5/modules.py at d28f7d24df9aaa76a498c645c969a9ac7a474769 · RVC-Project/Retrieval-based-Voice-Conversion-WebUI · GitHub

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
import os
import traceback
import logging

logger = logging.getLogger(__name__)

import ffmpeg
import torch

from configs.config import Config
from infer.modules.uvr5.mdxnet import MDXNetDereverb
from infer.modules.uvr5.vr import AudioPre, AudioPreDeEcho

config = Config()


def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format0):
    infos = []
    try:
        inp_root = inp_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        save_root_vocal = (
            save_root_vocal.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        )
        save_root_ins = (
            save_root_ins.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        )
        if model_name == "onnx_dereverb_By_FoxJoy":
            pre_fun = MDXNetDereverb(15, config.device)
        else:
            func = AudioPre if "DeEcho" not in model_name else AudioPreDeEcho
            pre_fun = func(
                agg=int(agg),
                model_path=os.path.join(
                    os.getenv("weight_uvr5_root"), model_name + ".pth"
                ),
                device=config.device,
                is_half=config.is_half,
            )
        is_hp3 = "HP3" in model_name
        if inp_root != "":
            paths = [os.path.join(inp_root, name) for name in os.listdir(inp_root)]
        else:
            paths = [path.name for path in paths]
        for path in paths:
            inp_path = os.path.join(inp_root, path)
            need_reformat = 1
            done = 0
            try:
                info = ffmpeg.probe(inp_path, cmd="ffprobe")
                if (
                    info["streams"][0]["channels"] == 2
                    and info["streams"][0]["sample_rate"] == "44100"
                ):
                    need_reformat = 0
                    pre_fun._path_audio_(
                        inp_path, save_root_ins, save_root_vocal, format0, is_hp3=is_hp3
                    )
                    done = 1
            except Exception:
                need_reformat = 1
                traceback.print_exc()
            if need_reformat == 1:
                tmp_path = "%s/%s.reformatted.wav" % (
                    os.path.join(os.environ["TEMP"]),
                    os.path.basename(inp_path),
                )
                os.system(
                    'ffmpeg -i "%s" -vn -acodec pcm_s16le -ac 2 -ar 44100 "%s" -y'
                    % (inp_path, tmp_path)
                )
                inp_path = tmp_path
            try:
                if done == 0:
                    pre_fun._path_audio_(
                        inp_path, save_root_ins, save_root_vocal, format0
                    )
                infos.append("%s->Success" % (os.path.basename(inp_path)))
                yield "\n".join(infos)
            except Exception:
                try:
                    if done == 0:
                        pre_fun._path_audio_(
                            inp_path, save_root_ins, save_root_vocal, format0
                        )
                    infos.append("%s->Success" % (os.path.basename(inp_path)))
                    yield "\n".join(infos)
                except Exception:
                    infos.append(
                        "%s->%s" % (os.path.basename(inp_path), traceback.format_exc())
                    )
                    yield "\n".join(infos)
    except Exception:
        infos.append(traceback.format_exc())
        yield "\n".join(infos)
    finally:
        try:
            if model_name == "onnx_dereverb_By_FoxJoy":
                del pre_fun.pred.model
                del pre_fun.pred.model_
            else:
                del pre_fun.model
                del pre_fun
        except Exception:
            traceback.print_exc()
        if torch.cuda.is_available():
            torch.cuda.empty_cache()
            logger.info("Executed torch.cuda.empty_cache()")
    yield "\n".join(infos)