Update app.py

app.py

@@ -94,12 +94,13 @@ def whisper_speech_demo(multilingual_text, speaker_audio):
 
     concatenated_audio = concatenate_audio_segments(audio_segments)
     print("Final concatenated audio shape:", concatenated_audio.shape)  # Debug statement
-
     # Normalize the concatenated audio
     concatenated_audio = concatenated_audio / np.max(np.abs(concatenated_audio))
 
-    # Return the concatenated audio as a NumPy array
-    return concatenated_audio[0]
+    # Write the audio data to a temporary file and return the file path
+    with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp_file:
+        sf.write(tmp_file.name, concatenated_audio.T, 24000, format='WAV', subtype='PCM_16')
+        return tmp_file.name
 
 with gr.Blocks() as demo:
     gr.Markdown(title)