Speaker Recognition

demonstration of speaker recognition using embeddings.

🛠️ Prerequisites

• Python 3.x (tested with Python 3.11 via pyenv)
• Access to Pyannote/embeddings embeddings

Environment Variables

Create a .env file in the project root with the following keys:

GEMINI_API_KEY=<your_gemini_api_key>
HF_API_KEY=<your_huggingface_api_key>

Voice Samples

• Your voice sample should be stored as .speakers/<your_name>.wav
• Assistant voice sample should be stored as .voices/<language_code>.wav

📦 Installation

1. Clone the repository

git clone https://github.com/ecnivs/speaker_rec_demo.git
cd speaker_rec_demo

1. Install dependencies

pip install -r requirements.txt

🚀 Running

python main.py

Thank you for checking out this project!