It is just doing some stuff intelligently.
Project description
🦈 Shirley
It is just doing some stuff intelligently. It has the following features:
- Chat, powered by Qwen/Qwen-VL-Chat (通义千问).
- Text-To-Speech, powered by Azure AI Speech.
Requirements
- Git
- CUDA if using NVIDIA graphics cards
- Python 3.10.6
- pip
- poetry
Installation
Setup virtual environment
[Optional] Configure that creating the virtualenv inside the project’s root directory:
poetry config virtualenvs.in-project true
If you are not using Python 3.10.6, you need to install the specific version. Alternatively, use pyenv
to manage
Python versions:
pyenv install 3.10.6
Use Python 3.10.6 for the environment:
poetry env use <PATH>
Create and activate the virtual environment:
poetry shell
Setup dependencies
Install dependencies:
poetry install
Install PyTorch.
[Chat] Setup Qwen model
Install submodule:
git submodule update --init --recursive
Update submodule:
git submodule update --remote --merge
[Text-To-Speech] Setup Azure AI Speech
Create AI Speech service in Azure portal.
Set environment variables:
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
Running
Activate the virtual environment:
poetry shell
Run WebUI:
poetry run webui
Run tests (not available yet):
poetry run pytest
WebUI Usage
TODO
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.