Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM
 from aksharamukha import transliterate
 import torch
+from huggingface_hub import InferenceClient
 
 # Set up device
 device = "cuda" if torch.cuda.is_available() else "cpu"