Spaces:
Sleeping
Sleeping
| title: Interactive Text Summarizer | |
| emoji: 📝 | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| python_version: "3.10" | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # Interactive Text Summarizer | |
| This is a premium, lightweight, interactive Text Summarization tool designed specifically for computational social science and humanities courses. | |
| ## Features | |
| - **Flexible Data Input**: Paste raw text directly or upload datasets (`.csv`, `.xlsx`, or `.txt`). | |
| - **Flexible Summarization Modes**: | |
| - **Local Extractive (CPU & Fast)**: Runs a custom rule-based TF-IDF sentence extraction algorithm locally on CPU. | |
| - **Transformers (API Mode)**: Leverages state-of-the-art abstractive summarization models (like `facebook/bart-large-cnn`) via Hugging Face's Serverless API with your personal access token. | |
| - **Adjustable Compression**: Choose from Short (15%), Medium (35%), or Detailed (55%) summary target ratios. | |
| - **Statistics Report**: Automatically displays original vs. summary word counts and compression rates. | |
| - **Data Export**: Easily download generated summaries as `.txt` files. | |