Update app.py

app.py

@@ -80,8 +80,6 @@ def speech_to_speech_translation(audio):
 title = "Cascaded STST"
 description = """
 Demo for cascaded speech-to-speech translation (STST), mapping from source speech in any language to target speech in Spanish.
-
-![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
 """
 
 demo = gr.Blocks()
@@ -103,7 +101,21 @@ file_translate = gr.Interface(
     description=description,
 )
 
+
+# Definir la estructura dentro de gr.Blocks()
 with demo:
+    # Mostrar el título y la descripción
+    gr.Markdown(f"# {title}")
+    gr.Markdown(description)
+    
+    # Incluir la imagen
+    gr.Image("https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png")
+    
+    # Tabbed Interface para las dos modalidades
     gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
 
+
+# with demo:
+#     gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+
 demo.launch()