import gradio as gr
import numpy as np
import pytesseract as pt
import pdf2image
from fpdf import FPDF
import re
import nltk
from nltk.tokenize import sent_tokenize
from nltk.tokenize import word_tokenize
import os
import pdfkit
import yake
from summarizer import Summarizer,TransformerSummarizer
from transformers import pipelines
nltk.download('punkt')
from transformers import AutoTokenizer, AutoModelForPreTraining, AutoConfig, AutoModel
# model_name = 'distilbert-base-uncased'
model_name = 'nlpaueb/legal-bert-base-uncased'
#model_name = 'laxya007/gpt2_legal'
# model_name = 'facebook/bart-large-cnn'


from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laxya007/gpt2_BSA_Legal_Initiproject_OE_OS_BRM")

model = AutoModelForCausalLM.from_pretrained("laxya007/gpt2_BSA_Legal_Initiproject_OE_OS_BRM")
bert_legal_model = Summarizer(custom_model= model, custom_tokenizer= tokenizer)
print('Using model {}\n'.format(model_name))


def lincoln(input_text):
  output_text= bert_legal_model(input_text,  min_length = 8, ratio = 0.05)
  
iface = gr.Interface(
    lincoln, 
    "text", 
    "text"
   )

if __name__ == "__main__":
    iface.launch(share=False)