Update app.py

app.py

@@ -16,10 +16,10 @@ from transformers import pipeline
 
 device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
 
-narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
+narrator = pipeline("text-to-speech", model="facebook/mms-tts-en")
 
 # Load the pretrained weights
-caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large", device=device)
+caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
 
 # Define the function to generate audio from text