Update app.py

app.py

@@ -51,26 +51,35 @@ Demo for cascaded speech-to-speech translation (STST), mapping from source speec
 ![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()
-
-mic_translate = gr.Interface(
-    fn=speech_to_speech_translation,
-    inputs=gr.Audio(source="microphone", type="filepath"),
-    outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    title=title,
-    description=description,
-)
-
-file_translate = gr.Interface(
-    fn=speech_to_speech_translation,
-    inputs=gr.Audio(source="upload", type="filepath"),
-    outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    examples=[["./example.wav"]],
-    title=title,
-    description=description,
-)
-
-with demo:
-    gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+# mic_translate = gr.Interface(
+#     fn=speech_to_speech_translation,
+#     inputs=gr.Audio(source="microphone", type="filepath"),
+#     outputs=gr.Audio(label="Generated Speech", type="numpy"),
+#     title=title,
+#     description=description,
+# )
+
+# file_translate = gr.Interface(
+#     fn=speech_to_speech_translation,
+#     inputs=gr.Audio(source="upload", type="filepath"),
+#     outputs=gr.Audio(label="Generated Speech", type="numpy"),
+#     examples=[["./example.wav"]],
+#     title=title,
+#     description=description,
+# )
+
+with gr.Blocks() as demo:
+
+     with gr.Row():
+            audio_in = gr.Microphone(label="Input audio", type="filepath")
+            audio_out = gr.Audio(label="Output audio", type="numpy", autoplay=True)
+
+    audio_in.stop_recording(
+        speech_to_speech_translation,
+        inputs=[audio_in],
+        outputs=[audio_out],
+    )
+         
+    # gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
 
 demo.launch()