diff --git a/VITS_vc_ft.ipynb b/VITS_vc_ft.ipynb
index 713deb2..3417ef0 100644
--- a/VITS_vc_ft.ipynb
+++ b/VITS_vc_ft.ipynb
@@ -3,10 +3,61 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2c6bd36c",
+   "id": "e6058067",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "# download models & files\n",
+    "!mkdir pretrained_models\n",
+    "%cd pretrained_models\n",
+    "# download pretrained discriminator checkpoint\n",
+    "!wget https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer/resolve/main/pretrained_models/D_trilingual.pth\n",
+    "!wget https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer/resolve/main/pretrained_models/G_trilingual.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f7e44cf5",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "%run user_voice_collect.py"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6bb986a6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%run demucs_denoise.py"
+   ]
   }
  ],
  "metadata": {
diff --git a/user_voice_collect.py b/user_voice_collect.py
index 85e021d..399cc72 100644
--- a/user_voice_collect.py
+++ b/user_voice_collect.py
@@ -2,6 +2,7 @@ import numpy as np
 import torch
 import torchaudio
 import gradio as gr
+import os
 
 anno_lines = []
 with open("./user_voice/user_voice.txt", 'r', encoding='utf-8') as f: