Hugging Face's logo

Spaces:
zanesmit29
/
pdf_scientific_article_to_speech
Runtime error

App Files Community
pdf_scientific_article_to_speech / README.md
zanesmit29
Initial commit of PDF summarization to speech app
3010d8f
preview code
|
raw
history blame contribute delete
1.32 kB

A newer version of the Gradio SDK is available: 6.13.0

Upgrade
metadata 
title: Pdf Scientific Article To Speech
emoji: 💻
colorFrom: blue
colorTo: yellow
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
short_description: Article abstract to summary to speech

PDF Scientific Article to Speech

This application converts scientific article abstracts into audio summaries using AI-powered text processing and speech synthesis.

Features

  • PDF Upload: Upload scientific articles in PDF format
  • Abstract Extraction: Automatically extracts the abstract from uploaded PDFs
  • AI Summarization: Generates concise summaries of article abstracts
  • Text-to-Speech: Converts summaries into natural-sounding audio
  • User-friendly Interface: Built with Gradio for easy interaction

Usage

  1. Upload a PDF file containing a scientific article
  2. The app extracts and displays the abstract
  3. An AI-generated summary is created
  4. Listen to the audio version of the summary

Technical Stack

  • Framework: Gradio 5.49.1
  • Python: Core processing logic
  • NLP: For text extraction and summarization
  • TTS: Text-to-speech synthesis

Installation 

pip install -r requirements.txt

Running Locally 

python app.py

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference