Update app.py

app.py

@@ -3,6 +3,7 @@ import requests
 import numpy as np
 from pydub import AudioSegment
 import io
+from IPython.display import Audio
 
 # Define the Hugging Face Inference API URLs and headers
 ASR_API_URL = "https://api-inference.huggingface.co/models/Baghdad99/saad-speech-recognition-hausa-audio-to-text"
@@ -35,15 +36,8 @@ def translate_speech(audio_file):
     response = requests.post(TTS_API_URL, headers=headers, json={"inputs": translated_text})
     audio_bytes = response.content
 
-    # Convert the audio bytes to an audio segment
-    audio_segment = AudioSegment.from_mp3(io.BytesIO(audio_bytes))  # Change this line
-
-    # Convert the audio segment to a numpy array
-    audio_data = np.array(audio_segment.get_array_of_samples())
-    if audio_segment.channels == 2:
-        audio_data = audio_data.reshape((-1, 2))
-
-    return audio_data
+    # Display the audio output
+    return Audio(audio_bytes)
 
 # Define the Gradio interface
 iface = gr.Interface(