Spaces:
Sleeping
Sleeping
File size: 2,284 Bytes
b69d9b2 c9a2e1a b69d9b2 c9a2e1a b69d9b2 c9a2e1a b69d9b2 c9a2e1a b69d9b2 e96727a b69d9b2 471b76d b69d9b2 c9a2e1a b69d9b2 471b76d e79d3d5 471b76d e79d3d5 b69d9b2 e96727a b69d9b2 489b827 b69d9b2 e96727a fe4994f b69d9b2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
#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) |