File size: 1,868 Bytes
8d2760c
 
 
 
 
 
 
cc6486b
 
 
8d2760c
 
 
 
 
 
 
 
6097bd9
 
8d2760c
 
 
 
 
cc6486b
 
8d2760c
 
20f1be3
8d2760c
 
20f1be3
8d2760c
 
 
 
 
 
 
6097bd9
8d2760c
6097bd9
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
import streamlit as st
import numpy as np
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from normalizer import normalize

# Set the page configuration
st.set_page_config(
    page_title="Bengali to English Translator App",
    page_icon=":shield:",
    initial_sidebar_state="auto"
)

# Load custom CSS styling
with open("assets/style.css") as f:
    st.markdown("<style>{}</style>".format(f.read()), unsafe_allow_html=True)

# Function to load the pre-trained model
def get_model():
    tokenizer = AutoTokenizer.from_pretrained("kazalbrur/BanglaEnglishTokenizerBanglaT5", use_fast=True)
    model = AutoModelForSeq2SeqLM.from_pretrained("kazalbrur/BanglaEnglishTranslationBanglaT5")
    return tokenizer, model

# Load the tokenizer and model
tokenizer, model = get_model()

# Add a header to the Streamlit app with custom CSS for black font color
st.markdown("<h1 style='color:black;'>Bengali to English Translator</h1>", unsafe_allow_html=True)

# Add placeholder text with custom CSS styling
st.markdown("<span style='color:black'>Enter your Bengali text here</span>", unsafe_allow_html=True)

# Text area for user input with label and height set to 250
user_input = st.text_area("Enter your Bengali text here", "", height=250, label_visibility="collapsed")

# Button for submitting the input
submit_button = st.button("Translate")

# Perform prediction when user input is provided and the submit button is clicked
if user_input and submit_button:
    input_ids = tokenizer(normalize(user_input), padding=True, truncation=True, max_length=128, return_tensors="pt").input_ids
    generated_tokens = model.generate(input_ids, max_new_tokens=128)
    decoded_tokens = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
    st.write(f"<span style='color:black'>English Translation: {decoded_tokens}</span>", unsafe_allow_html=True)