Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from transformers import pipeline
+import numpy as np
 
 # Load the pipeline for speech recognition and translation
 pipe = pipeline(
@@ -12,11 +13,8 @@ tts = pipeline("text-to-speech", model="Baghdad99/english_voice_tts")
 
 # Define the function to translate speech
 def translate_speech(audio):
-    # Extract the audio data from the tuple
-    audio_data = audio[0]
-
     # Use the speech recognition pipeline to transcribe the audio
-    transcription = pipe(audio_data)["transcription"]
+    transcription = pipe(audio)["transcription"]
 
     # Use the translation pipeline to translate the transcription
     translated_text = translator(transcription, return_tensors="pt", padding=True)
@@ -40,5 +38,4 @@ iface = gr.Interface(
     description="Realtime demo for Hausa to English translation using speech recognition and text-to-speech synthesis."
 )
 
-
 iface.launch()