Spaces:
Running
Running
File size: 5,106 Bytes
fe54a29 f7a6ff9 fe54a29 548f1ce fe54a29 f7a6ff9 d5fcf79 f7a6ff9 fe54a29 53ffbb8 548f1ce af94d8d 45a780c f7a6ff9 e67f619 31ed23e 53ffbb8 f7a6ff9 53ffbb8 |
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 |
import gradio as gr
from rvc_infer import download_online_model
import os
import re
import random
from scipy.io.wavfile import write
from scipy.io.wavfile import read
import numpy as np
import yt_dlp
import subprocess
def download_model(url, dir_name):
output_models = download_online_model(url, dir_name)
return dir_name
uvr_models = {
'BS-Roformer-Viperx-1297.ckpt': 'model_bs_roformer_ep_317_sdr_12.9755.ckpt',
'MDX23C-8KFFT-InstVoc_HQ.ckpt': 'MDX23C-8KFFT-InstVoc_HQ.ckpt',
'BS-Roformer-Viperx-1053.ckpt': 'model_bs_roformer_ep_937_sdr_10.5309.ckpt',
'Mel-Roformer-Viperx-1143.ckpt': 'model_mel_band_roformer_ep_3005_sdr_11.4360.ckpt',
'Kim_Vocal_2.onnx': 'Kim_Vocal_2.onnx',
'UVR-De-Echo-Aggressive.pth': 'UVR-De-Echo-Aggressive.pth',
}
output_format = [
'wav',
'flac',
'mp3',
]
mdxnet_overlap_values = [
'0.25',
'0.5',
'0.75',
'0.99',
]
vrarch_window_size_values = [
'320',
'512',
'1024',
]
def download_audio(url):
ydl_opts = {
'format': 'bestaudio/best',
'outtmpl': 'ytdl/%(title)s.%(ext)s',
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'wav',
'preferredquality': '192',
}],
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info_dict = ydl.extract_info(url, download=True)
file_path = ydl.prepare_filename(info_dict).rsplit('.', 1)[0] + '.wav'
sample_rate, audio_data = read(file_path)
audio_array = np.asarray(audio_data, dtype=np.int16)
return sample_rate, audio_array
def roformer_separator(roformer_audio, roformer_model, roformer_output_format, roformer_overlap, roformer_segment_size, mdx23c_denoise, mdxnet_denoise, vrarch_tta, vrarch_high_end_process):
files_list = []
files_list.clear()
directory = "./outputs"
random_id = str(random.randint(10000, 99999))
pattern = f"{random_id}"
os.makedirs("outputs", exist_ok=True)
write(f'{random_id}.wav', roformer_audio[0], roformer_audio[1])
full_roformer_model = roformer_models[roformer_model]
prompt = f"audio-separator {random_id}.wav --model_filename {full_roformer_model} --output_dir=./outputs --output_format={roformer_output_format} --normalization=0.9 --mdxc_overlap={roformer_overlap} --mdxc_segment_size={roformer_segment_size}"
if mdx23c_denoise:
prompt += " --mdx_enable_denoise"
if mdxnet_denoise:
prompt += " --mdx_enable_denoise"
if vrarch_tta:
prompt += " --vr_enable_tta"
if vrarch_high_end_process:
prompt += " --vr_high_end_process"
os.system(prompt)
for file in os.listdir(directory):
if re.search(pattern, file):
files_list.append(os.path.join(directory, file))
stem1_file = files_list[0]
stem2_file = files_list[1]
return stem1_file, stem2_file
CSS = """
"""
with gr.Blocks(theme="Hev832/Applio", fill_width=True, css=CSS) as demo:
with gr.Tabs():
with gr.Tab("inferenece"):
gr.Markdown("in progress")
with gr.Tab("Download model"):
gr.Markdown("## Download Model for infernece")
url_input = gr.Textbox(label="Model URL", placeholder="Enter the URL of the model")
dir_name_input = gr.Textbox(label="Directory Name", placeholder="Enter the directory name")
download_button = gr.Button("Download Model")
download_button.click(download_model, inputs=[url_input, dir_name_input], outputs=url_input)
with gr.Tab("UVR5"):
roformer_model = gr.Dropdown(
label = "Select the Model",
choices=list(uvr_models.keys()),
interactive = True
)
roformer_output_format = gr.Dropdown(
label = "Select the Output Format",
choices = output_format,
interactive = True
)
roformer_overlap = gr.Slider(
minimum = 2,
maximum = 4,
step = 1,
label = "Overlap",
info = "Amount of overlap between prediction windows.",
value = 4,
interactive = True
)
roformer_segment_size = gr.Slider(
minimum = 32,
maximum = 4000,
step = 32,
label = "Segment Size",
info = "Larger consumes more resources, but may give better results.",
value = 256,
interactive = True
)
mdx23c_denoise = gr.Checkbox(
label = "Denoise",
info = "Enable denoising during separation.",
value = False,
interactive = True
)
with gr.Tab(" Credits"):
gr.Markdown(
"""
this project made by [Blane187](https://huggingface.co/Blane187) with Improvements by [John6666](https://huggingfce.co/John6666)
""")
demo.launch(debug=True,show_api=False)
|