Update app.py

app.py

@@ -1,11 +1,116 @@
 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 = """
 """
 
@@ -22,6 +127,41 @@ with gr.Blocks(theme="Hev832/Applio", fill_width=True, css=CSS) as demo:
             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(
                 """
@@ -37,4 +177,5 @@ with gr.Blocks(theme="Hev832/Applio", fill_width=True, css=CSS) as demo:
 
 
 
+
 demo.launch(debug=True,show_api=False)