/drake-ai

Primary LanguageJupyter Notebook

Drake AI - Voice Cloning

Jupyter Python PyTorch TensorFlow License

This repository contains the code and resources needed to clone Drake's voice using a pre-trained AI model. It is based on the so-vits-svc library and uses the pre-trained model to generate synthesized speech in Drake's voice.

Links:

https://github.com/w-okada/voice-changer https://github.com/voicepaw/so-vits-svc-fork https://www.youtube.com/watch?v=9sN1JYqKv9w https://www.youtube.com/watch?v=2sMpIXQcSCA

Getting Started

Follow these steps to set up the environment and clone Drake's voice:

1. Clone the Repository

Clone this repository to your local machine.

git clone https://github.com/mrBlackHat777/drake-ai.git

2. Download and Extract the Pre-trained Model

Download the pre-trained model from the following link:

https://mega.nz/file/Sm53wAwI#4PmIrSWDrEP1-pnZb5MJpTcfoHy3OBhBOhn2FVxfyb8

Extract the downloaded .zip file and place the contents in the models directory.

3. Install Dependencies

Install the required dependencies by running:

pip install -r requirements.txt

4. Run the Program

Run the program by executing the following command:

cd notebooks
jupyter notebook

Acknowledgments

This project is based on the so-vits-svc library and the pre-trained model was obtained from the Mega.nz link provided in the instructions. Special thanks to the contributors and developers of the original library and the pre-trained models.