Create app.py

app.py

@@ -0,0 +1,30 @@
+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', 'jpg']) 
+
+if uploaded_file is not None:
+    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))