Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,10 +1,7 @@
 import streamlit as st
 from PIL import Image
 import requests
-from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from io import BytesIO
-import torch
-import torchvision.transforms as T
 
 st.set_page_config(page_title="WikiExplorer AR", layout="centered")
 st.title("📷 WikiExplorer AR (Streamlit Edition)")
@@ -23,47 +20,16 @@ lang = st.selectbox(
 
 lang_code = lang[1]
 
-# --- Load Hugging Face OCR model ---
-@st.cache_resource
-def load_trocr():
-    processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
-    model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
-    return processor, model
-
-processor, model = load_trocr()
-
-# --- Camera input (main source of place name) ---
-st.markdown("**📸 Capture a place name from signage, poster, or board:**")
-img_file_buffer = st.camera_input("Take a picture")
-
-# --- Optional text input if OCR fails ---
-place_name = st.text_input("📝 Or manually enter the place name (optional)")
-
-# --- OCR from captured image ---
-def run_trocr_ocr(image_data):
-    image = Image.open(image_data).convert("RGB")
-    transform = T.Compose([
-        T.Resize((384, 384)),
-        T.ToTensor()
-    ])
-    pixel_values = transform(image).unsqueeze(0)
-    generated_ids = model.generate(pixel_values)
-    text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return text.strip()
+# --- Place name input ---
+st.markdown("**📝 Enter a place or person name to learn more:**")
+place_name = st.text_input("🏛️ For example: Charminar, Taj Mahal, Shah Jahan")
+
+# --- Camera input (optional) ---
+img_file_buffer = st.camera_input("📸 Take a picture (optional)")
 
 if img_file_buffer is not None:
     st.markdown("### 📷 Captured Image")
     st.image(img_file_buffer, caption="Uploaded via camera", use_column_width=True)
-    try:
-        with st.spinner("🧠 Running OCR..."):
-            ocr_text = run_trocr_ocr(BytesIO(img_file_buffer.getvalue()))
-            if ocr_text:
-                place_name = ocr_text
-                st.success(f"🧠 OCR detected: **{place_name}**")
-            else:
-                st.warning("OCR ran but could not extract any meaningful text.")
-    except Exception as e:
-        st.error(f"OCR failed: {e}")
 
 # --- Translation helpers ---
 def translate_text(text, target_lang):
@@ -159,9 +125,8 @@ if place_name.strip():
 # --- Footer ---
 st.markdown("""
 ---
-- 📸 Take a picture to auto-detect monument/place using Hugging Face OCR.
-- ✍️ Optional manual input if OCR fails.
+- 📸 Capture photo optionally — main input is typed place name.
 - 🌐 Wikipedia multilingual summary with fallback + sentence-level translation.
 - 🖼️ Commons image gallery integration.
-- ✅ Works in Hugging Face Spaces with Streamlit + Transformers.
-""")
+- ✅ Works in Hugging Face Spaces with Streamlit.
+""")