File size: 1,769 Bytes
4433b13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import streamlit as st

from transformers import BertTokenizer, EncoderDecoderModel, EncoderDecoderConfig
model_ckpt = 'ardavey/bert2gpt-indosum'
tokenizer = BertTokenizer.from_pretrained(model_ckpt)
tokenizer.bos_token = tokenizer.cls_token
tokenizer.eos_token = tokenizer.sep_token

config = EncoderDecoderConfig.from_pretrained(model_ckpt)
config.early_stopping = True

model = EncoderDecoderModel.from_pretrained(model_ckpt, config=config)

text = st.text('Enter an article to summarize:')

if text:
    input_ids = tokenizer.encode(custom_text, return_tensors='pt', padding=True, truncation=True, max_length=512)
    summary_ids = model.generate(input_ids,
            min_length=40,
            max_length=200,
            num_beams=10,
            repetition_penalty=2.0,
            length_penalty=1.0,
            no_repeat_ngram_size=3,
            use_cache=True,
            do_sample = False,
            top_k = 50,
            )

    summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    # capitalize the first letter of the summary and after each period
    def capitalize_sentences(text):
        sentences = text.split('. ')
        capitalized_sentences = [sentence[0].upper() + sentence[1:] if sentence else sentence for sentence in sentences]
        return '. '.join(capitalized_sentences)
    
    # correct any wrong terms using the replacement_dict
    replacement_dict = {
        "optiglain": "OptiGuard",
        "telkom university": "Telkom University",
        "menyerbut": "menyebut"
    }
    
    for wrong_term, correct_term in replacement_dict.items():
        summary_text = summary_text.replace(wrong_term, correct_term)
    
    summary_text = capitalize_sentences(summary_text)
    st.info(summary_text)