Update app.py

app.py

@@ -36,7 +36,7 @@ def get_model(model_name):
 @spaces.GPU(duration=120)
 def transcribe_and_score(audio):
     if audio is None:
-        return "", None
+        return ""
     model = get_model(MODEL_NAMES[0])
     predictions = model.transcribe([audio])
     item = predictions[0] if isinstance(predictions, list) else predictions
@@ -51,7 +51,7 @@ def transcribe_and_score(audio):
     else:
         text = str(item)
 
-    return text.strip(), audio
+    return text.strip()
 
 @spaces.GPU(duration=120)
 def batch_transcribe(audio_files):
@@ -86,10 +86,8 @@ with gr.Blocks(title="EgypTalk-ASR-v2") as demo:
         with gr.Row():
             audio_input = gr.Audio(sources=["microphone", "upload"], type="filepath", label="Audio")
         transcribe_btn = gr.Button("Transcribe")
-        with gr.Row():
-            pred_output = gr.Textbox(label="Transcription")
-            audio_playback = gr.Audio(type="filepath", label="Playback")
-        transcribe_btn.click(transcribe_and_score, inputs=[audio_input], outputs=[pred_output, audio_playback])
+        pred_output = gr.Textbox(label="Transcription")
+        transcribe_btn.click(transcribe_and_score, inputs=[audio_input], outputs=[pred_output])
 
     with gr.Tab("Batch Test"):
         gr.Markdown("Upload multiple audio files. Batch size is limited by GPU/CPU memory.")