Spaces:
Build error
Build error
File size: 8,111 Bytes
1912645 00aa15b ed2622c f6e8343 ed2622c 1912645 ed2622c 1912645 00aa15b ed2622c f6e8343 afe64d9 1912645 ed2622c f6e8343 ed2622c 00aa15b ed2622c 00aa15b ed2622c 00aa15b ed2622c 1912645 945ab77 00aa15b 945ab77 1912645 abc0eca ed2622c 1912645 945ab77 1912645 00aa15b ed2622c 945ab77 1912645 bcd91cb afe64d9 |
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 |
# import os
# import gradio as gr
# from scipy.io.wavfile import write
# import subprocess
# import torch
# from audio_separator import Separator # Ensure this is correctly implemented
# def inference(audio):
# os.makedirs("out", exist_ok=True)
# audio_path = 'test.wav'
# write(audio_path, audio[0], audio[1])
# device = 'cuda' if torch.cuda.is_available() else 'cpu'
# if device=='cuda':
# use_cuda=True
# print(f"Using device: {device}")
# else:
# use_cuda=False
# print(f"Using device: {device}")
# try:
# # Using subprocess.run for better control
# command = f"python3 -m demucs.separate -n htdemucs_6s -d {device} {audio_path} -o out"
# process = subprocess.run(command, shell=True, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
# print("Demucs script output:", process.stdout.decode())
# except subprocess.CalledProcessError as e:
# print("Error in Demucs script:", e.stderr.decode())
# return None
# try:
# # Separating the stems using your custom separator
# separator = Separator("./out/htdemucs_6s/test/vocals.wav", model_name='UVR_MDXNET_KARA_2', use_cuda=use_cuda, output_format='mp3')
# primary_stem_path, secondary_stem_path = separator.separate()
# except Exception as e:
# print("Error in custom separation:", str(e))
# return None
# # Collecting all file paths
# files = [f"./out/htdemucs_6s/test/{stem}.wav" for stem in ["vocals", "bass", "drums", "other", "piano", "guitar"]]
# files.extend([secondary_stem_path,primary_stem_path ])
# # Check if files exist
# existing_files = [file for file in files if os.path.isfile(file)]
# if not existing_files:
# print("No files were created.")
# return None
# return existing_files
# # Gradio Interface
# title = "Source Separation Demo"
# description = "Music Source Separation in the Waveform Domain. To use it, simply upload your audio."
# gr.Interface(
# inference,
# gr.components.Audio(type="numpy", label="Input"),
# [gr.components.Audio(type="filepath", label=stem) for stem in ["Full Vocals","Bass", "Drums", "Other", "Piano", "Guitar", "Lead Vocals", "Backing Vocals" ]],
# title=title,
# description=description,
# ).launch()
# import os
# import gradio as gr
# from scipy.io.wavfile import write
# import subprocess
# import torch
# # Assuming audio_separator is available in your environment
# from audio_separator import Separator
# def inference(audio, vocals, bass, drums, other, piano, guitar, lead_vocals, backing_vocals):
# os.makedirs("out", exist_ok=True)
# audio_path = 'test.wav'
# write(audio_path, audio[0], audio[1])
# device = 'cuda' if torch.cuda.is_available() else 'cpu'
# print(f"Using device: {device}")
# if device=='cuda':
# use_cuda=True
# print(f"Using device: {device}")
# else:
# use_cuda=False
# print(f"Using device: {device}")
# try:
# command = f"python3 -m demucs.separate -n htdemucs_6s -d {device} {audio_path} -o out"
# process = subprocess.run(command, shell=True, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
# print("Demucs script output:", process.stdout.decode())
# except subprocess.CalledProcessError as e:
# print("Error in Demucs script:", e.stderr.decode())
# return [gr.Audio(visible=False)] * 8
# try:
# separator = Separator("./out/htdemucs_6s/test/vocals.wav", model_name='UVR_MDXNET_KARA_2', use_cuda=device==use_cuda, output_format='wav')
# primary_stem_path, secondary_stem_path = separator.separate()
# except Exception as e:
# print("Error in custom separation:", str(e))
# return [gr.Audio(visible=False)] * 8
# stem_paths = {
# "vocals": "./out/htdemucs_6s/test/vocals.wav" if vocals else None,
# "bass": "./out/htdemucs_6s/test/bass.wav" if bass else None,
# "drums": "./out/htdemucs_6s/test/drums.wav" if drums else None,
# "other": "./out/htdemucs_6s/test/other.wav" if other else None,
# "piano": "./out/htdemucs_6s/test/piano.wav" if piano else None,
# "guitar": "./out/htdemucs_6s/test/guitar.wav" if guitar else None,
# "lead_vocals": primary_stem_path if lead_vocals else None,
# "backing_vocals": secondary_stem_path if backing_vocals else None
# }
# return [gr.Audio(stem_paths[stem], visible=bool(stem_paths[stem])) for stem in stem_paths]
# # Define checkboxes for each stem
# checkbox_labels = ["Full Vocals", "Bass", "Drums", "Other", "Piano", "Guitar", "Lead Vocals", "Backing Vocals"]
# checkboxes = [gr.components.Checkbox(label=label) for label in checkbox_labels]
# # Gradio Interface
# title = "Source Separation Demo"
# description = "Music Source Separation in the Waveform Domain. Upload your audio to begin."
# iface = gr.Interface(
# inference,
# [gr.components.Audio(type="numpy", label="Input")] + checkboxes,
# [gr.Audio(label=label, visible=False) for label in checkbox_labels],
# title=title,
# description=description,
# )
# iface.launch()
import os
import gradio as gr
from scipy.io.wavfile import write
import subprocess
import torch
# Assuming audio_separator is available in your environment
from audio_separator import Separator
def inference(audio, vocals, bass, drums, other, piano, guitar, lead_vocals, backing_vocals):
# Initially, show the loading GIF
loading_gif_path = "7RwF.gif"
transparent_img_path = "images.png"
os.makedirs("out", exist_ok=True)
audio_path = 'test.wav'
write(audio_path, audio[0], audio[1])
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Using device: {device}")
try:
command = f"python3 -m demucs.separate -n htdemucs_6s -d {device} {audio_path} -o out"
process = subprocess.run(command, shell=True, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
print("Demucs script output:", process.stdout.decode())
except subprocess.CalledProcessError as e:
print("Error in Demucs script:", e.stderr.decode())
return [gr.Audio(visible=False)] * 8 + [loading_gif_path]
try:
separator = Separator("./out/htdemucs_6s/test/vocals.wav", model_name='UVR_MDXNET_KARA_2', use_cuda=device=='cuda', output_format='wav')
primary_stem_path, secondary_stem_path = separator.separate()
except Exception as e:
print("Error in custom separation:", str(e))
return [gr.Audio(visible=False)] * 8 + [loading_gif_path]
stem_paths = {
"vocals": "./out/htdemucs_6s/test/vocals.wav" if vocals else None,
"bass": "./out/htdemucs_6s/test/bass.wav" if bass else None,
"drums": "./out/htdemucs_6s/test/drums.wav" if drums else None,
"other": "./out/htdemucs_6s/test/other.wav" if other else None,
"piano": "./out/htdemucs_6s/test/piano.wav" if piano else None,
"guitar": "./out/htdemucs_6s/test/guitar.wav" if guitar else None,
"lead_vocals": primary_stem_path if lead_vocals else None,
"backing_vocals": secondary_stem_path if backing_vocals else None
}
# Once processing is done, hide the GIF by returning a transparent image
return [gr.Audio(stem_paths[stem], visible=bool(stem_paths[stem])) for stem in stem_paths] + [transparent_img_path]
# Define checkboxes for each stem
checkbox_labels = ["Full Vocals", "Bass", "Drums", "Other", "Piano", "Guitar", "Lead Vocals", "Backing Vocals"]
checkboxes = [gr.components.Checkbox(label=label) for label in checkbox_labels]
# Gradio Interface
title = "Source Separation Demo"
description = "Music Source Separation in the Waveform Domain. Upload your audio to begin."
iface = gr.Interface(
inference,
[gr.components.Audio(type="numpy", label="Input")] + checkboxes,
[gr.Audio(label=label, visible=False) for label in checkbox_labels] + [gr.Image()],
title=title,
description=description,
)
iface.launch()
|