modify app

app.py

@@ -156,23 +156,23 @@ def update_ito_output(all_results, selected_step):
 with gr.Blocks() as demo:
     gr.Markdown("# ITO-Master: Inference Time Optimization for Mastering Style Transfer")
     with gr.Row():
-        gr.Markdown("Demo of Inference Time Optimization (ITO) for Music Mastering Style Transfer. \
+        gr.Markdown("Interactive demo of Inference Time Optimization (ITO) for Music Mastering Style Transfer. \
                     The mastering style transfer is performed by a differentiable audio processing model, and the predicted parameters are shown as the output. \
-                    Perform mastering style transfer with an input source audio and a reference mastering style audio. On top of this result, you can perform ITO to optimize the reference embedding \(z_\text{ref}\) to further gain control over the output mastering style.")
-        gr.Image("ito_snow.png", width=350)
+                    Perform mastering style transfer with an input source audio and a reference mastering style audio. On top of this result, you can perform ITO to optimize the reference embedding z~ref~ $z_{ref}$ to further gain control over the output mastering style.")
+        gr.Image("ito_snow.png", width=300)
 
-    gr.Markdown("# Step 1: Mastering Style Transfer")
+    gr.Markdown("## Step 1: Mastering Style Transfer")
 
     with gr.Tab("Upload Audio"):
         with gr.Row():
-            input_audio = gr.Audio(label=r"Source Audio (\(x_\text{in}\))")
-            reference_audio = gr.Audio(label="Reference Style Audio (\(x_\text{ref}\))")
+            input_audio = gr.Audio(label="Source Audio (x~in~ $x_{in}$)")
+            reference_audio = gr.Audio(label="Reference Style Audio (x~ref~ $x_{ref}$)")
         
         process_button = gr.Button("Process Mastering Style Transfer")
         
         with gr.Row():
             with gr.Column():
-                output_audio = gr.Audio(label="Output Audio ($y'$)", type='numpy')
+                output_audio = gr.Audio(label="Output Audio (y')", type='numpy')
                 normalized_input = gr.Audio(label="Normalized Source Audio", type='numpy')
             param_output = gr.Textbox(label="Predicted Parameters", lines=5)