Spaces:
Running
A newer version of the Gradio SDK is available:
5.19.0
title: Story Generation
emoji: π
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 5.18.0
app_file: app.py
pinned: false
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
AI Kids' Story Generator β English & Arabic
Project Objectives
The AI Kids' Story Generator is designed to create fun and imaginative short stories for children. By inputting a character name and a setting, users can generate engaging stories in either English or Arabic. This project leverages advanced natural language processing techniques to provide a creative and interactive storytelling experience.
Implemented Pipelines
The project utilizes text generation pipelines from the Transformers library:
- Model Selection:
- English: Utilizes the microsoft/Phi-3-mini-4k-instruct model for generating fluent and engaging English stories.
- Arabic: Employs the ALLaM-AI/ALLaM-7B-Instruct-preview model, optimized for Arabic language generation.
How to Use the Interface
- Enter a Character Name: Input the name of the main character.
- Specify the Setting: Choose a setting for the story (e.g., a magical forest).
- Select Language: Choose whether the story should be in English or Arabic.
- Generate Story: Click the "Submit" button to create a unique children's story. The generated story will be displayed in the "Kids' Story" textbox.
- Use Examples: Predefined examples are available to help users see how the generator works. Simply click on an example to populate the fields automatically.
Justification for Model and Pipeline Choices
- Model Suitability: The selected models are optimized for instruction-following tasks, making them ideal for generating structured and engaging narratives.
- Pipeline Configuration: Parameters are fine-tuned to encourage creativity and engagement, essential for crafting captivating children's stories.
Bilingual Support
The application supports both English and Arabic, enabling users to generate stories in their preferred language, making storytelling accessible to a wider audience.