File size: 2,163 Bytes
dc6144b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9502bf6
dc6144b
 
 
9502bf6
dc6144b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
66
67
68
69
70
71
72
73
# -*- coding: utf-8 -*-
import numpy as np
import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM


st.set_page_config(
    page_title="๋ฒˆ์—ญ๊ธฐ", layout="wide", initial_sidebar_state="expanded"
)

@st.cache
def load_model(model_name):
    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
    return model

tokenizer = AutoTokenizer.from_pretrained("QuoQA-NLP/KE-T5-Ko2En-Base")
ko2en_model = load_model("QuoQA-NLP/KE-T5-Ko2En-Base")
en2ko_model = load_model("QuoQA-NLP/KE-T5-En2Ko-Base")


st.title("๐Ÿค– ๋ฒˆ์—ญ๊ธฐ")
st.write("์ขŒ์ธก์— ๋ฒˆ์—ญ ๋ชจ๋“œ๋ฅผ ์„ ํƒํ•˜๊ณ , CTRL+Enter(CMD+Enter)๋ฅผ ๋ˆ„๋ฅด์„ธ์š” ๐Ÿค—")
st.write("Select Translation Mode at the left and press CTRL+Enter(CMD+Enter)๐Ÿค—")

translation_list = ["ํ•œ๊ตญ์–ด์—์„œ ์˜์–ด | Korean to English", "์˜์–ด์—์„œ ํ•œ๊ตญ์–ด | English to Korean"]
translation_mode = st.sidebar.radio("๋ฒˆ์—ญ ๋ชจ๋“œ๋ฅผ ์„ ํƒ(Translation Mode):", translation_list)


default_value = '์‹ ํ•œ์นด๋“œ ๊ด€๊ณ„์ž๋Š” "๊ณผ๊ฑฐ ๋‚ด๋†“์€ ์ƒํ’ˆ์˜ ๊ฒฝ์šฐ ์ถœ์‹œ 2๊ฐœ์›” ๋งŒ์— ์ ๊ธˆ ๊ฐ€์ž…์ด 4๋งŒ์—ฌ ์ขŒ์— ๋‹ฌํ•  ์ •๋„๋กœ ์ธ๊ธฐ๋ฅผ ๋Œ์—ˆ๋‹ค"๋ฉด์„œ "๊ธˆ๋ฆฌ ์ธ์ƒ์— ๋”ฐ๋ผ ์ ๊ธˆ ๊ธˆ๋ฆฌ๋ฅผ ๋” ์˜ฌ๋ ค ๋งŽ์€ ๊ณ ๊ฐ์ด ๋ชฐ๋ฆด ๊ฒƒ์œผ๋กœ ์˜ˆ์ƒํ•˜๊ณ  ์žˆ๋‹ค"๊ณ  ๋งํ–ˆ๋‹ค.'
src_text = st.text_area(
    "๋ฒˆ์—ญํ•˜๊ณ  ์‹ถ์€ ๋ฌธ์žฅ์„ ์ž…๋ ฅํ•˜์„ธ์š”:",
    default_value,
    height=300,
    max_chars=200,
)
print(src_text)



if src_text == "":
    st.warning("Please **enter text** for translation")

# translate into english sentence
if translation_mode == translation_list[0]:
    model = ko2en_model
else: 
    model = en2ko_model

translation_result = model.generate(
    **tokenizer(
        src_text,
        return_tensors="pt",
        padding="max_length",
        truncation=True,
        max_length=64,
    ),
    max_length=64,
    num_beams=5,
    repetition_penalty=1.3,
    no_repeat_ngram_size=3,
    num_return_sequences=1,
)
translation_result = tokenizer.decode(
    translation_result[0],
    clean_up_tokenization_spaces=True,
    skip_special_tokens=True,
)

print(f"{src_text} -> {translation_result}")

st.write(translation_result)
print(translation_result)