Spaces:
Sleeping
Sleeping
File size: 1,569 Bytes
a9921cb b87a3d3 c87d667 b87a3d3 c87d667 b87a3d3 c87d667 b87a3d3 c87d667 | 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 | import streamlit as st
from PIL import Image
import os
from ocr_tamil.ocr import OCR
from deep_translator import GoogleTranslator
# Load OCR models
ocr_detect = OCR(detect=True, enable_cuda=False)
ocr_recognize = OCR(detect=False, enable_cuda=False)
# Language code mapping
lang_codes = {
'English': 'en',
'Kannada': 'kn',
'Tamil': 'ta',
'Telugu': 'te',
'Hindi': 'hi',
'Malayalam': 'ml',
'Marathi': 'mr',
'Bengali': 'bn',
'Gujarati': 'gu',
'Urdu': 'ur',
}
# Prediction function
def predict(image_path, target_language):
try:
texts = ocr_detect.predict(image_path)
texts = [" ".join(texts[0])]
detected_text = texts[0]
translated_text = GoogleTranslator(source='auto', target=target_language).translate(detected_text)
return detected_text, translated_text
except Exception as e:
return f"Error: {str(e)}", ""
# Streamlit UI
st.title("Tamil OCR + Translation")
uploaded_file = st.file_uploader("Upload a Tamil handwritten image", type=["jpg", "jpeg", "png"])
target_lang_name = st.selectbox("Target Language", list(lang_codes.keys()))
if uploaded_file:
image = Image.open(uploaded_file)
st.image(image, caption="Uploaded Image", use_column_width=True)
image_path = "uploaded_image.jpg"
image.save(image_path)
if st.button("Submit"):
detected, translated = predict(image_path, lang_codes[target_lang_name])
st.success("Detected Text:")
st.write(detected)
st.success("Translated Text:")
st.write(translated)
|