Hugging Face's logo

Spaces:
reha
/
Stick_Tech
Running

App Files Community
1
Stick_Tech
File size: 2,982 Bytes 
14cdbd7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import io

import gradio as gr
import librosa
import numpy as np
import soundfile
import torch
from inference.infer_tool import Svc
import logging

logging.getLogger('numba').setLevel(logging.WARNING)

model_name = "logs/32k/G_98000.pth"
config_name = "configs/config.json"

svc_model = Svc(model_name, config_name)
sid_map = {
    "Ztech": "Ztech"
}


def vc_fn(sid, input_audio, vc_transform):
    if input_audio is None:
        return "You need to upload an audio", None
    sampling_rate, audio = input_audio
    # print(audio.shape,sampling_rate)
    duration = audio.shape[0] / sampling_rate
    if duration > 45:
        return "请上传小于45s的音频，需要转换长音频请本地进行转换", None
    audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
    if len(audio.shape) > 1:
        audio = librosa.to_mono(audio.transpose(1, 0))
    if sampling_rate != 16000:
        audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
    print(audio.shape)
    out_wav_path = io.BytesIO()
    soundfile.write(out_wav_path, audio, 16000, format="wav")
    out_wav_path.seek(0)

    sid = sid_map[sid]
    out_audio, out_sr = svc_model.infer(sid, vc_transform, out_wav_path)
    _audio = out_audio.cpu().numpy()
    return "Success", (32000, _audio)


app = gr.Blocks()
with app:
    with gr.Tabs():
        with gr.TabItem("Basic"):
            gr.Markdown(value="""
                这是sovits 3.0 32khz版本ai粘连科技的在线demo

                人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人人

                在使用此模型前请阅读[AI粘连科技模型使用协议](https://huggingface.co/spaces/reha/Stick_Tech/blob/main/terms.md)

                YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY

                粘连科技Official@bilibili：[点击关注](https://space.bilibili.com/248582596)
                
                如果要在本地使用该demo，请使用git lfs clone 该仓库，安装requirements.txt后运行app.py即可
                
                项目改写基于 https://huggingface.co/spaces/innnky/nyaru-svc-3.0
                
                本地合成可以删除26、27两行代码以解除合成45s长度限制""")
            sid = gr.Dropdown(label="音色", choices=["Ztech"], value="Ztech")
            vc_input3 = gr.Audio(label="上传音频（长度小于45秒）")
            vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
            vc_submit = gr.Button("转换", variant="primary")
            vc_output1 = gr.Textbox(label="Output Message")
            vc_output2 = gr.Audio(label="Output Audio")
        vc_submit.click(vc_fn, [sid, vc_input3, vc_transform], [vc_output1, vc_output2])

    app.launch()