How to use Retrieval-based-Voice-Conversion-WebUI with google colab debug way

gistfile1.txt

1. Open https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/tree/main

2. Open google colab for 
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb

3. Change pip version to 22.2

4. python -m pip install pip==22.2

5. git clone https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
5.1 python -m venv venv
5.2 source ./venv/bin/activate

6. pip install -r requirements.txt

7. pip install torch torchvision torchaudio tensorrt

8. In google colab

	8.1 Install aria2
	
	8.2 Download base template

	8.3 Download the Vocal Separation Model

	8.4 Download hubert_base

	8.5 Download rmvpe model

9. Cd into tools and run python download_models.py 

10. In google colab Load the packaged dataset from Google Drive to /content/dataset

Fix error and paste: 

/content/drive/MyDrive/dataset/tyler-denoise.zip

10.1 Rename duplicate files in the dataset

11. Run the app

python infer-web.py --colab --pycmd python

You should get the following output in the logs

Running on local URL:  http://127.0.0.1:7860
Running on public URL: https://dcb9a19b14da82c2de.gradio.live