Upload streamlit_app.py

src/streamlit_app.py

@@ -37,16 +37,29 @@ h1 a, h2 a, h3 a, h4 a, h5 a, h6 a { display: none !important; pointer-events: n
 .stMarkdown a { text-decoration: none !important; pointer-events: none !important; }
 
 /* ═══════════════════════════════════════════════════════════════
-   STATUS, SPINNERS & TOASTS
+   STATUS, SPINNERS, TOASTS & PROGRESS BARS (100% DARK MODE FIX)
    ═══════════════════════════════════════════════════════════════ */
-[data-testid="stStatusWidget"], [data-testid="stToast"], div[role="status"], div[data-baseweb="toast"] { 
-    background-color: #171a1f !important; border: 1px solid #8ff5ff !important; border-radius: 4px !important;
+/* Target absolutely every single popup, toast, and cache notification container */
+[data-testid="stStatusWidget"], [data-testid="stToast"], [data-testid="stToastContainer"], 
+[data-testid="stNotification"], [data-testid="stNotificationContainer"], 
+div[role="status"], div[role="alert"], div[role="dialog"], 
+div[data-baseweb="toast"], div[data-baseweb="snackbar"], div[data-baseweb="notification"] { 
+    background-color: #171a1f !important; border: 1px solid #8ff5ff !important; border-radius: 4px !important; box-shadow: 0 0 15px rgba(143, 245, 255, 0.05) !important;
 }
-[data-testid="stStatusWidget"] *, [data-testid="stToast"] *, div[role="status"] * { 
-    color: #8ff5ff !important; font-family: 'Space Grotesk', sans-serif !important;
+
+/* Force nested white boxes to turn transparent so the dark background shows */
+[data-testid="stStatusWidget"] *, [data-testid="stToast"] *, [data-testid="stNotification"] *, 
+div[role="status"] *, div[role="alert"] *, div[role="dialog"] *, 
+div[data-baseweb="toast"] *, div[data-baseweb="snackbar"] *, div[data-baseweb="notification"] * { 
+    background-color: transparent !important; color: #8ff5ff !important; font-family: 'Space Grotesk', sans-serif !important;
 }
+
 [data-testid="stStatusWidget"] label { color: #f6f6fc !important; }
 
+/* Dynamic Progress Bar Override */
+[data-testid="stProgress"] > div > div > div > div { background-color: #8ff5ff !important; }
+[data-testid="stProgress"] p { color: #8ff5ff !important; font-family: 'Space Grotesk' !important; font-size: 14px !important; font-weight: 500 !important; letter-spacing: 1px; text-transform: uppercase;}
+
 /* ═══════════════════════════════════════════════════════════════
    SELECT MODEL BOX
    ═══════════════════════════════════════════════════════════════ */
@@ -140,13 +153,13 @@ div[data-testid="stFileUploader"] * {
 # ═══════════════════════════════════════════════════════════════
 # MODELS & OCR LOGIC
 # ═══════════════════════════════════════════════════════════════
-@st.cache_resource(show_spinner=False)
+@st.cache_resource(show_spinner="Waking up Neural Architecture...")
 def load_vision_engine():
     import logging
     logging.getLogger("easyocr").setLevel(logging.ERROR)
     return easyocr.Reader(['en'], gpu=torch.cuda.is_available())
 
-@st.cache_resource(show_spinner=False)
+@st.cache_resource(show_spinner="Loading TrOCR Weights into VRAM...")
 def load_trocr_model(model_path):
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     
@@ -158,21 +171,14 @@ def load_trocr_model(model_path):
         model = model.half()
     
     # ─── THE ACTUAL ROOT-CAUSE FIX ───
-    # Find the broken Hugging Face class, destroy its empty meta tensor, 
-    # and mathematically rebuild a brand new tensor natively on the GPU.
     for module in model.modules():
         if "TrOCRSinusoidalPositionalEmbedding" in module.__class__.__name__:
-            # Extract dimensions from the broken tensor
             num_positions, embedding_dim = module.weights.shape
-            
-            # Use the class's own method to generate a brand new, physical tensor
             new_weights = module.__class__.get_embedding(
                 num_positions, 
                 embedding_dim, 
                 padding_idx=getattr(module, "padding_idx", None)
             )
-            
-            # Assign the real tensor directly to the GPU matching the model's datatype
             module.weights = new_weights.to(device=device, dtype=model.dtype)
                     
     model.eval()
@@ -209,7 +215,7 @@ def main():
     with col_t3:
         with st.popover("INFO"):
             st.markdown("### 🧠 Forensic Neural Architecture")
-            st.write("This engine operates in a two-stage forensic sequence designed to maximize character fidelity. First, **EasyOCR** maps the image using mathematical line fusion, isolating text rows. Second, a **TrOCR Transformer** synthesizes the features into text.")
+            st.write("This engine operates in a two-stage forensic sequence designed to maximize character fidelity. First, **EasyOCR** maps the image using mathematical line fusion, isolating text rows. Second, a **TrOCR Transformer** synthesizes the features into text. It may take a long time if ran online.")
             st.markdown("---")
             st.markdown("### ⚙️ The Neural Engines")
             st.write("**Model V13 (Specialist):** I trained this specific model myself using the **IAM Handwriting Database** (over 65,000 instances). It is highly optimized for cursive loops and manual pen-strokes. It is excellent for handwritten manuscripts but might struggle with standard modern print.")
@@ -254,12 +260,24 @@ def main():
 
     with c_right:
         if run_scan_trigger:
-            with st.spinner("Extracting parameters and running neural synthesis..."):
-                start = time.time()
-                crops = extract_lines(st.session_state.image_data, reader)
-                proc, model, device = load_trocr_model(m_map[model_choice])
-                decoded, scores = [], []
-                for crop in crops:
+            start = time.time()
+            
+            # This triggers the @st.cache_resource loaders
+            proc, model, device = load_trocr_model(m_map[model_choice])
+            crops = extract_lines(st.session_state.image_data, reader)
+            
+            decoded, scores = [], []
+            total_crops = len(crops)
+            
+            if total_crops > 0:
+                # ─── DYNAMIC PROGRESS BAR INJECTION ───
+                progress_bar = st.progress(0, text="Initializing Neural Matrix...")
+                
+                for idx, crop in enumerate(crops):
+                    # Update Progress Text & Percentage
+                    pct = int((idx / total_crops) * 100)
+                    progress_bar.progress(pct, text=f"Synthesizing segment {idx + 1} out of {total_crops} | {pct}% Complete...")
+                    
                     pixel_values = proc(crop, return_tensors="pt").pixel_values.to(device)
                     if device.type == "cuda": pixel_values = pixel_values.half()
                     with torch.no_grad():
@@ -267,7 +285,12 @@ def main():
                     decoded.append(proc.batch_decode(out.sequences, skip_special_tokens=True)[0].strip())
                     try: scores.extend(np.exp(model.compute_transition_scores(out.sequences, out.scores, normalize_logits=True)[0].cpu().numpy()))
                     except: pass
-                st.session_state.ocr_results = {"text": "\n".join(decoded), "time": time.time() - start, "words": len("\n".join(decoded).split()), "conf": np.mean(scores)*100 if scores else 0}
+                
+                # Snap to 100% just before closing out
+                progress_bar.progress(100, text="Sequence Complete. Compiling output...")
+                time.sleep(0.3) 
+                
+            st.session_state.ocr_results = {"text": "\n".join(decoded), "time": time.time() - start, "words": len("\n".join(decoded).split()), "conf": np.mean(scores)*100 if scores else 0}
             st.rerun()
             
         elif st.session_state.ocr_results: