Update app.py

app.py

@@ -49,7 +49,7 @@ MAX_IMAGE_SIZE = 1024
 # Speech GenAI
 # Function for translating different language using pretrained models
 def translate(audio):
-    outputs = asr_pipe(audio, max_new_tokens=256, generate_kwargs={"task": "translate"})
+    outputs = asr_pipe(input_features=audio, max_new_tokens=256, generate_kwargs={"task": "translate"})
     return outputs["text"]
 
 # Function to synthesise the text using the processor above
@@ -62,13 +62,13 @@ def synthesise(text):
 def speech_to_speech_translation(audio):
     translated_text = translate(audio)
     synthesised_speech = synthesise(translated_text)
-    synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
+    synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)  # Ensure int16 format
     return 16000, synthesised_speech
 
 # Function for text to speech
 def text_to_speech(text):
     synthesised_speech = synthesise(text)
-    synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)
+    synthesised_speech = (synthesised_speech.numpy() * 32767).astype(np.int16)  # Ensure int16 format
     return 16000, synthesised_speech
 
 # Image GenAI