Update app.py

app.py

@@ -22,12 +22,11 @@ def s2t(audio, model_name):
     yield text
 
 with gr.Blocks() as demo:
-    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=[
+    with gr.Row():
+        with gr.Column():
+            model_name = gr.Dropdown(
+                label="Models:",
+                choices=[
                     "openai/whisper-large-v3",
                     "openai/whisper-large-v2",
                     "openai/whisper-large",
@@ -35,13 +34,14 @@ with gr.Blocks() as demo:
                     "openai/whisper-small",
                     "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",
+            )
+            audio = gr.Audio(sources=["microphone","upload"], type="filepath", label="Audio")
+
+        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)
+        audio.change(s2t, inputs=[audio, model_name], outputs=output)
     
 demo.queue().launch(max_threads=4)