abdulmatinomotoso's picture
Update app.py
471b76d
raw
history blame
2.28 kB
#importing the necessary libraries
import re
import nltk
from nltk.tokenize import sent_tokenize
nltk.download('punkt')
import gradio as gr
from gradio.mix import Parallel
# Defining a function to read in the text file
def read_in_text(url):
with open(url, 'r') as file:
article = file.read()
return article
#Doing some text preprocessing, more will still be needed later
def clean_text(text):
#text = read_in_text(url)
text = text.encode("ascii", errors="ignore").decode(
"ascii"
) # remove non-ascii, Chinese characters
text = re.sub(r"\n", " ", text)
text = re.sub(r"\n\n", " ", text)
text = re.sub(r"\t", " ", text)
text = text.strip(" ")
text = re.sub(
" +", " ", text
).strip() # get rid of multiple spaces and replace with a single
return text
#importing the model and tokenizer for the headline generator
from transformers import (
AutoTokenizer,
AutoModelForSeq2SeqLM,
)
#initializing the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained("valurank/final_headline_generator")
model = AutoModelForSeq2SeqLM.from_pretrained("valurank/final_headline_generator")
#Defining a function to generate the headlines
def headline_generator_2(file):
input_text = file
#input_text = sent_tokenize(input_text)
#text = ''.join(input_text[:6])
inputs = tokenizer(input_text,truncation=True, return_tensors="pt")
summary_ids = model.generate(inputs["input_ids"],min_length=20, max_length=40)
summary = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
return summary
#creating an interface for the headline generator using gradio
demo = gr.Interface(headline_generator_2, inputs=[gr.inputs.Textbox(label="Drop your .txt file here", optional=False)],
title = "HEADLINE GENERATOR",
outputs=[gr.outputs.Textbox(label="Headline")],
theme= "darkhuggingface")
#launching the app
if __name__ == "__main__":
demo.launch(debug=True)