Update app.py

app.py

@@ -22,15 +22,12 @@ def s2t(audio, model_name):
     yield text
 
 with gr.Blocks() as demo:
-    with gr.Row():
-        with gr.Column():
-            voice = gr.Audio(sources=["microphone"], type="filepath", label="Voice")
-            voice.stop_recording(s2t, inputs=[voice, model_name], outputs=output)
-            audio = gr.Audio(sources=["upload"], type="filepath", label="Audio file")
-            audio.upload(s2t, inputs=[audio, model_name], outputs=output)
-            model_name = gr.Dropdown(
-                label="Models:",
-                choices=[
+    with gr.Column():
+        voice = gr.Audio(sources=["microphone"], type="filepath", label="Voice")
+        audio = gr.Audio(sources=["upload"], type="filepath", label="Audio file")
+        model_name = gr.Dropdown(
+            label="Models:",
+            choices=[
                     "openai/whisper-large-v3",
                     "openai/whisper-large-v2",
                     "openai/whisper-large",
@@ -39,9 +36,12 @@ with gr.Blocks() as demo:
                     "openai/whisper-base",
                     "openai/whisper-tiny",
                 ],
-                value="openai/whisper-large-v3",
-            )
-        with gr.Column():
-            output = gr.Textbox(label="Transcription results")
+            value="openai/whisper-large-v3",
+        )
+    with gr.Column():
+        output = gr.Textbox(label="Transcription results")
+            
+    voice.stop_recording(s2t, inputs=[voice, model_name], outputs=output)
+    audio.upload(s2t, inputs=[audio, model_name], outputs=output)
     
 demo.queue().launch(max_threads=4)