Your own AI Voice Assistant
- Run on CPU only
- Voice chat with Bot
- Voice Q&A with Bot
- Built with LLama, Fast Whisper, Langchain, python-llama-cpp
Strictly follow the below instructions to run the application
- Clone this Repo:
git clone https://github.com/DuongNg2911/WhisBot.git
- Make sure you have installed a version of Python that supports arm64 architecture, otherwise:
wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-MacOSX-arm64.sh
bash Miniforge3-MacOSX-arm64.sh
- Create conda environment for python v3.9:
conda create -n myenv python==3.9
conda activate myenv
- Run
pip install -r requirements.txt
- Install python-llama-cpp:
!CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64" pip install --upgrade --verbose --force-reinstall --no-cache-dir llama-cpp-python==0.2.11
- Download models:
bash scripts/download_models.sh
- To run frontend:
cd frontend
npm start
- To run backend:
cd whisbot
uvicorn router:app --reload