Refactor UI: separate tables and add Advanced Options accordion

app.py

@@ -151,7 +151,7 @@ def get_mem_usage():
     return process.memory_info().rss / (1024 ** 2)
 
 # === INFERENCE FUNCTION ===
-def predict_language(audio_path, top_k=3, threshold=0.0):
+def predict_language(audio_path, fam_k=1, fam_thresh=0.0, super_k=1, super_thresh=0.0, code_k=3, code_thresh=0.0):
     if not audio_path:
         raise gr.Error("No audio provided! Please upload or record an audio file.")
     
@@ -195,21 +195,14 @@ def predict_language(audio_path, top_k=3, threshold=0.0):
         super_probs = torch.softmax(outputs["super_logits"], dim=-1)
         code_probs = torch.softmax(outputs["code_logits"], dim=-1)
         
-        # Extract top-k indices and probabilities
-        top_k = int(top_k)
-        fam_top = torch.topk(fam_probs[0], min(top_k, fam_probs.shape[-1]))
-        super_top = torch.topk(super_probs[0], min(top_k, super_probs.shape[-1]))
-        code_top = torch.topk(code_probs[0], min(top_k, code_probs.shape[-1]))
-        
-        table_data = []
-
-        # Helper to format and add results to the table
-        def add_to_table(category, top_vals, top_idx, labels_list, apply_mapping=False):
-            # top_vals and top_idx are 1D tensors
-            valid_rank = 1
+        def build_df(probs_tensor, k, thresh, labels_list, apply_mapping=False):
+            k = int(k)
+            top_vals, top_idx = torch.topk(probs_tensor[0], min(k, probs_tensor.shape[-1]))
+            
+            table_data = []
             for i in range(len(top_vals)):
                 score = top_vals[i].item()
-                if score < threshold:
+                if score < thresh:
                     continue
                 
                 idx = top_idx[i].item()
@@ -220,22 +213,20 @@ def predict_language(audio_path, top_k=3, threshold=0.0):
                 else:
                     name = raw_label
                 
-                table_data.append([category, valid_rank, name, f"{score:.2%}"])
-                valid_rank += 1
-
-        add_to_table("🌍 Family", fam_top.values, fam_top.indices, label_extractor.family_labels)
-        add_to_table("🗣️ Superlanguage", super_top.values, super_top.indices, label_extractor.super_labels)
-        add_to_table("🔤 Code", code_top.values, code_top.indices, label_extractor.code_labels, apply_mapping=True)
+                table_data.append([name, f"{score:.2%}"])
+                
+            if not table_data:
+                return pd.DataFrame(columns=["Prediction", "Confidence"])
+            return pd.DataFrame(table_data, columns=["Prediction", "Confidence"])
 
-        if not table_data:
-            df = pd.DataFrame(columns=["Category", "Rank", "Prediction", "Confidence"])
-        else:
-            df = pd.DataFrame(table_data, columns=["Category", "Rank", "Prediction", "Confidence"])
+        df_fam = build_df(fam_probs, fam_k, fam_thresh, label_extractor.family_labels)
+        df_super = build_df(super_probs, super_k, super_thresh, label_extractor.super_labels)
+        df_code = build_df(code_probs, code_k, code_thresh, label_extractor.code_labels, apply_mapping=True)
 
         print(f"[LOG] Final Memory: {get_mem_usage():.2f} MB")
         print(f"--- [LOG] Request Finished ---\n")
         
-        return df
+        return df_fam, df_super, df_code
     except Exception as e:
         print(f"Error during inference: {e}")
         raise gr.Error(f"Processing failed: {str(e)}")
@@ -259,34 +250,43 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="indigo", secondary_hue="blue"))
                 type="filepath", # Changed from numpy to filepath
                 label="Upload or Record"
             )
-            with gr.Row():
-                top_k = gr.Slider(minimum=1, maximum=10, step=1, value=3, label="Top-K Predictions")
-                threshold = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, value=0.0, label="Confidence Threshold")
-                
+            with gr.Accordion("⚙️ Advanced Options", open=False):
+                with gr.Group():
+                    gr.Markdown("#### Language Family")
+                    with gr.Row():
+                        fam_k = gr.Slider(minimum=1, maximum=10, step=1, value=1, label="Top-K")
+                        fam_thresh = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, value=0.0, label="Threshold")
+                with gr.Group():
+                    gr.Markdown("#### Superlanguage")
+                    with gr.Row():
+                        super_k = gr.Slider(minimum=1, maximum=10, step=1, value=1, label="Top-K")
+                        super_thresh = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, value=0.0, label="Threshold")
+                with gr.Group():
+                    gr.Markdown("#### Language Code")
+                    with gr.Row():
+                        code_k = gr.Slider(minimum=1, maximum=10, step=1, value=3, label="Top-K")
+                        code_thresh = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, value=0.0, label="Threshold")
+                        
             with gr.Row():
                 clear_btn = gr.Button("🗑️ Clear", variant="secondary")
                 submit_btn = gr.Button("🚀 Classify", variant="primary")
             
         with gr.Column(scale=1):
             gr.Markdown("### 📊 2. Classification Results")
-            results_table = gr.Dataframe(
-                headers=["Category", "Rank", "Prediction", "Confidence"],
-                datatype=["str", "number", "str", "str"],
-                label="Predictions",
-                interactive=False,
-                wrap=True
-            )
+            fam_table = gr.Dataframe(headers=["Prediction", "Confidence"], datatype=["str", "str"], label="🌍 Language Family", interactive=False, wrap=True)
+            super_table = gr.Dataframe(headers=["Prediction", "Confidence"], datatype=["str", "str"], label="🗣️ Superlanguage", interactive=False, wrap=True)
+            code_table = gr.Dataframe(headers=["Prediction", "Confidence"], datatype=["str", "str"], label="🔤 Language Code", interactive=False, wrap=True)
 
     submit_btn.click(
         fn=predict_language,
-        inputs=[audio_input, top_k, threshold],
-        outputs=[results_table]
+        inputs=[audio_input, fam_k, fam_thresh, super_k, super_thresh, code_k, code_thresh],
+        outputs=[fam_table, super_table, code_table]
     )
     
     clear_btn.click(
-        fn=lambda: (None, None),
+        fn=lambda: (None, None, None, None),
         inputs=None,
-        outputs=[audio_input, results_table]
+        outputs=[audio_input, fam_table, super_table, code_table]
     )
 
     gr.Markdown(