feat: add vscode debugger

Reviewed-on: terminator/ai-voice-cloning-terminator#1

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Debug Main.py",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/src/main.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}"
+            },
+            "preLaunchTask": "Setup Environment",
+        }
+    ]
+}

.vscode/tasks.json

@@ -0,0 +1,12 @@
+{
+  "version": "2.0.0",
+  "tasks": [
+      {
+          "label": "Setup Environment",
+          "type": "shell",
+          "command": "python",
+          "args": ["activate_env.py"],
+          "problemMatcher": []
+      }
+  ]
+}

activate_env.py

@@ -0,0 +1,9 @@
+import subprocess
+import os
+
+# Ativa o ambiente virtual
+subprocess.run([r'.\venv\Scripts\activate.bat'], shell=True)
+
+# Configura as variáveis de ambiente
+os.environ['PATH'] = r'.\bin;' + os.environ['PATH']
+os.environ['PYTHONUTF8'] = '1'

notebook_colab.ipynb

@@ -38,10 +38,24 @@
             
          ],
          "source":[
-            "!apt install python3.8-venv\n",
+            "!apt install python3.10-venv\n",
             "!git clone https://git.ecker.tech/mrq/ai-voice-cloning/\n",
             "%cd /content/ai-voice-cloning\n",
-            "!./setup-cuda.sh"
+            "# get local dependencies\n",
+            "!git submodule init\n",
+            "!git submodule update --remote\n",
+            "# setup venv\n",
+            "!python3 -m venv venv\n",
+            "!source ./venv/bin/activate\n",
+            "!python3 -m pip install --upgrade pip # just to be safe\n",
+            "# CUDA\n",
+            "!pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n",
+            "# install requirements\n",
+            "!python3 -m pip install -r ./modules/tortoise-tts/requirements.txt # install TorToiSe requirements\n",
+            "!python3 -m pip install -e ./modules/tortoise-tts/ # install TorToiSe\n",
+            "!python3 -m pip install -r ./modules/dlas/requirements.txt # instal DLAS requirements, last, because whisperx will break a dependency here\n",
+            "!python3 -m pip install -e ./modules/dlas/ # install DLAS\n",
+            "!python3 -m pip install -r ./requirements.txt # install local requirements"
          ]
       },
       {
@@ -115,7 +129,8 @@
          "cell_type":"code",
          "source":[
             "%cd /content/ai-voice-cloning/\n",
-            "!./start.sh --share"
+            "!source ./venv/bin/activate\n",
+            "!python3 ./src/main.py --share"
          ],
          "metadata":{
             "id":"QRA8jF3cF-YJ"

requirements.txt

@@ -1,5 +1,9 @@
-git+https://github.com/openai/whisper.git
+--extra-index-url https://download.pytorch.org/whl/cu118
+torch>=2.1.0
+torchvision
+torchaudio
 
+openai-whisper
 more-itertools
 ffmpeg-python
 gradio<=3.23.0

src/webui.py

@@ -371,7 +371,9 @@ def setup_gradio():
 		arg = GENERATE_SETTINGS_ARGS[i]
 		GENERATE_SETTINGS[arg] = None
 
-	with gr.Blocks() as ui:
+	with gr.Blocks(theme="freddyaboulton/dracula_revamped", css="footer { display: none!important}", title="Voice Clonning WebUI") as ui:
+		gr.Markdown("## 🤗🎙️ Voice clonning ")
+		gr.Markdown("Ai Voice clonning <a href='https://git.ecker.tech/terminator/ai-voice-cloning-terminator'>based on Tortoise</a>")
 		with gr.Tab("Generate"):
 			with gr.Row():
 				with gr.Column():