| import gradio as gr | |
| import torch | |
| import PyPDF2 | |
| from transformers import pipeline | |
| import numpy | |
| import scipy | |
| from gtts import gTTS | |
| from io import BytesIO | |
| from transformers import BartTokenizer | |
| def extract_text(pdf_file): | |
| pdfReader = PyPDF2.PdfReader(pdf_file) | |
| pageObj = pdfReader.pages[0] | |
| return pageObj.extract_text() | |
| def summarize_text(text): | |
| sentences = text.split(". ") | |
| for i, sentence in enumerate(sentences): | |
| if "Abstract" in sentence: | |
| start = i + 1 | |
| end = start + 3 | |
| break | |
| abstract = ". ".join(sentences[start:end+1]) | |
| tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn") | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn", tokenizer=tokenizer) | |
| summary = summarizer(abstract, max_length=40, min_length=40, | |
| do_sample=False) | |
| return summary[0]['summary_text'] | |
| def text_to_audio(text): | |
| tts = gTTS(text, lang='en') | |
| buffer = BytesIO() | |
| tts.write_to_fp(buffer) | |
| buffer.seek(0) | |
| return buffer.read() | |
| def audio_pdf(pdf_file): | |
| text = extract_text(pdf_file) | |
| summary = summarize_text(text) | |
| audio = text_to_audio(summary) | |
| return summary, audio | |
| inputs = gr.File() | |
| summary_text = gr.Text() | |
| audio_summary = gr.Audio() | |
| iface = gr.Interface( | |
| fn=audio_pdf, | |
| inputs=inputs, | |
| outputs=[summary_text,audio_summary], | |
| title="PDF Audio Summarizer 📻", | |
| description="App that converts an abstract into audio", | |
| examples=["Attention_is_all_you_need.pdf", | |
| "ImageNet_Classification.pdf" | |
| ] | |
| ) | |
| iface.launch() |