File size: 1,026 Bytes
b8b90b4 7df6ad9 b8b90b4 7df6ad9 b8b90b4 |
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 |
import streamlit as st
import pytesseract
import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("usvsnsp/code-vs-nl")
model = AutoModelForSequenceClassification.from_pretrained("usvsnsp/code-vs-nl")
def classify_text(text):
input_ids = tokenizer(text, return_tensors="pt")
with torch.no_grad():
logits = model(**input_ids).logits
predicted_class_id = logits.argmax().item()
return model.config.id2label[predicted_class_id]
uploaded_file = st.file_uploader("Upload Image", type= ['png', 'jpeg', 'jpg'])
if uploaded_file is not None:
st.image(uploaded_file)
print(type(uploaded_file))
ocr_list = [x for x in pytesseract.image_to_string(uploaded_file).split("\n") if x != '']
ocr_class = [classify_text(x) for x in ocr_list]
idx = []
for i in range(len(ocr_class)):
if ocr_class[i] == 'Code':
idx.append(ocr_list[i])
st.text(("\n").join(idx)) |