TextDistiller is an advanced, AI-driven tool designed to summarize books chapter by chapter or as a whole, providing concise yet comprehensive overviews. With TextDistiller, you can quickly grasp the core ideas and key takeaways from any book, saving time while maintaining comprehension.

Chapter-wise Summarization: TextDistiller offers detailed summaries for each chapter, allowing you to focus on specific sections of interest.

Entire Book Synopsis: For books without chapter divisions, TextDistiller condenses the entire text into a coherent summary.

Powered by NLP: Utilizing state-of-the-art Natural Language Processing (NLP) techniques, TextDistiller effectively captures and summarizes the most pertinent content.

User-Friendly Interface: TextDistiller features a clean and intuitive interface, making the summarization process accessible and straightforward for all users.

TextDistiller leverages the T5-small pretrained model from HuggingFace Transformers to generate accurate and readable summaries. The process includes:

Chunking: The book is divided into chunks, either by chapter or as a single unit.

Tokenization: These chunks are tokenized using the T5Tokenizer for compatibility with the T5 model.

Summary Generation: The tokenized text is processed by the T5ForConditionalGeneration model to generate summary token IDs.

Decoding: The summary token IDs are decoded into human-readable text using the T5Tokenizer's decode() function.

Clone the repository:

Install the required dependencies:

To run via CLI:

To run on a Flask server with frontend and mail:

We welcome contributions from the community! If you'd like to contribute to TextDistiller, please feel free to submit a pull request or open an issue. Your feedback and support are greatly appreciated!

TextDistiller is distributed under the MIT License.