Spaces:
Runtime error
Runtime error
| #**************** IMPORT PACKAGES ******************** | |
| import gradio as gr | |
| import numpy as np | |
| import pytesseract as pt | |
| import pdf2image | |
| import os | |
| import tempfile | |
| from fpdf import FPDF | |
| import re | |
| import nltk | |
| from nltk.tokenize import sent_tokenize | |
| from nltk.tokenize import word_tokenize | |
| import pdfkit | |
| import yake | |
| from zipfile import ZipFile | |
| from gtts import gTTS | |
| from transformers import AutoTokenizer, AutoModelForPreTraining, AutoModel, AutoConfig | |
| from summarizer import Summarizer,TransformerSummarizer | |
| from transformers import pipelines | |
| from pdfminer.high_level import extract_text | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM | |
| nltk.download('punkt') | |
| model_name = 'nlpaueb/legal-bert-base-uncased' | |
| tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn") | |
| model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn") | |
| def pdf_to_text(text, PDF): | |
| Min = int(20) | |
| if text == "": | |
| # The setup of huggingface.co | |
| file_obj = PDF | |
| #n = int(Percent.replace('%', '')) | |
| text = extract_text(file_obj.name) | |
| inputs = tokenizer([text], max_length=1024, return_tensors="pt") | |
| Min = int(Min) | |
| # Generate Summary | |
| summary_ids = model.generate(inputs["input_ids"], num_beams=2,min_length=Min, max_length=Min+1000) | |
| output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] | |
| else: | |
| inputs = tokenizer([text], max_length=1024, return_tensors="pt") | |
| # Generate Summary | |
| summary_ids = model.generate(inputs["input_ids"], num_beams=2,min_length=Min, max_length=Min+1000) | |
| output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] | |
| #output_text= bert_legal_model(text, min_length = 8, ratio = 0.05) | |
| pdf = FPDF() | |
| pdf.add_page() | |
| pdf.set_font("Times", size = 12) | |
| # open the text file in read mode | |
| f = output_text | |
| # insert the texts in pdf | |
| pdf.multi_cell(190, 10, txt = f, align = 'C') | |
| # save the pdf with name .pdf | |
| pdf.output("legal.pdf") | |
| myobj = gTTS(text=output_text, lang='en', slow=False) | |
| myobj.save("legal.wav") | |
| return "legal.wav", output_text, "legal.pdf" | |
| # return path | |
| #pageObject.extractText() | |
| iface = gr.Interface(fn = pdf_to_text, | |
| inputs =["text", "file"], outputs=["audio","text", "file"] ) | |
| if __name__ == "__main__": | |
| iface.launch(share=True) |