up

app.py

@@ -68,21 +68,22 @@ with gr.Blocks() as demo_blocks:
     gr.Markdown("""<h1 align="center">🐶 Bark with Vocos</h1>""")
     gr.HTML("""<h3 style="text-align:center;">📢 Vocos-enhanced TTS 🦾! </h3>""")
     with gr.Group():
-      with gr.Row():
-        inp_text = gr.Textbox(label="What should Bark say?", info="Enter text here")
-        dd = gr.Dropdown(
+        with gr.Row():
+            inp_text = gr.Textbox(label="What should Bark say?", info="Enter text here")
+        with gr.Row():
+            spk = gr.Dropdown(
                 speaker_embeddings,
                 value=None, 
                 label="Available voice presets", 
-                info="Defaults to no speaker embeddings!"
+                info="Default: No speaker embeddings"
                 )
     
     with gr.Row():
         btn = gr.Button("Synthesise speech!")
     
     with gr.Row():
-        out_audio_vocos = gr.Audio(type="numpy", autoplay=False, label="Vocos enhanced output", show_label=True)
+        out_audio_vocos = gr.Audio(type="numpy", autoplay=False, label="Vocos enhanced speech", show_label=True)
         
-        btn.click(generate_audio, [inp_text, dd], [out_audio_vocos])
+        btn.click(generate_audio, [inp_text, spk], [out_audio_vocos])
 
 demo_blocks.queue().launch(debug=True)