Update app.py

app.py

@@ -10,6 +10,7 @@ import time
 import uuid
 import soundfile as sf
 from model import get_pretrained_model, language_to_models
+# demo for a input given image transform into text interpretation, and those text put a speech text to be played 
 
 #text to speech code from https://huggingface.co/spaces/k2-fsa/text-to-speech/blob/main/app.py
 image_to_text_model = pipeline("image-classification",model="microsoft/beit-base-patch16-224-pt22k-ft22k")