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.
Installation
pip install shirley
Or, copy shirley
directory to your working directory.
[Chat] Setup Qwen-VL-Chat model (local)
Add Qwen/Qwen-VL-Chat as a git submodule:
git submodule add https://huggingface.co/Qwen/Qwen-VL-Chat.git models/qwen_vl_chat
git submodule update --init --recursive models/qwen_vl_chat
git submodule update --remote --merge models/qwen_vl_chat
This downloads the model repository from Hugging Face and saves it in models/qwen_vl_chat
.
Note: You can skip this if you want to use remote model.
[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
Set environment variables on Windows:
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
Quicktour
# webui.py
import gradio as gr
import shirley as sh
with gr.Blocks() as blocks:
sh.interfaces.Header()
with gr.Tab('Chat'):
sh.interfaces.Chat()
with gr.Tab('Text-To-Speech'):
sh.interfaces.TextToSpeech()
sh.interfaces.Footer()
blocks.queue().launch()
Chat interface uses local model by default. If you want to use remote one, add options:
...
sh.interfaces.Chat(
options=ChatInterfaceOptions(
client=ChatClientOptions(local=False),
),
)
...
Note: I made an example webui.py. You can use that to start with.
Running
pip install -r requirements.txt
python webui.py
Note: I recommend using poetry
to manage dependencies and run Python. See DEVELOPMENT.md for more details.
Development
See DEVELOPMENT.md.
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.