File size: 1,473 Bytes
c29d314 1073c6d c29d314 15e4b11 c29d314 |
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 |
#importing the necessary libraries
import gradio as gr
import numpy as np
import pandas as pd
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
#Defining the labels of the models
labels = ['Politics', 'Tech', 'Entertainment', 'Business', 'World', 'Sport']
#Defining the models and tokenuzer
model_name = 'valurank/finetuned-distilbert-news-article-categorization'
model = AutoModelForSequenceClassification.from_pretrained(model_name, use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
#Reading in the text file
def read_in_text(url):
with open(url, 'r') as file:
article = file.read()
return article
#Defining a function to get the category of the news article
def get_category(file):
text = read_in_text(file.name)
input_tensor = tokenizer.encode(text, return_tensors='pt', truncation=True)
logits = model(input_tensor).logits
softmax = torch.nn.Softmax(dim=1)
probs = softmax(logits)[0]
probs = probs.cpu().detach().numpy()
max_index = np.argmax(probs)
emotion = labels[max_index]
return emotion
#Creating the interface for the radio app
demo = gr.Interface(get_category, inputs=gr.inputs.File(label='Upload your .txt file here'),
outputs = 'text',
title='News Article Categorization')
#Launching the radio app
if __name__ == '__main__':
demo.launch(debug=True) |