Update app.py

app.py

@@ -44,7 +44,10 @@ default_value_tr = "How are you?"
 tr_input = st.text_area(label = "Input in English", value = default_value_tr, height = 5)
 tr = query(tr_input, model_id, api_token)
 st.write("Translated Example:")
-st.write(tr[0]["translation_text"])
+try:
+	st.write(tr[0]["translation_text"])
+except:
+	st.write("Inference API loads model on demand, please wait for 10 secs and try again 🤗 ")
 st.write("You can check out this [link](https://huggingface.co/models?pipeline_tag=translation&sort=downloads&search=helsinki-nlp) for available translation models.")
 
 
@@ -59,7 +62,10 @@ context = st.text_area(label = "Context", value = "🤗 Transformers provides th
 data = {"inputs": {"question": question, "context": context}}
 output_answer = query(payload = data, model_id = model_id_q, api_token = api_token)
 st.write("Answer:")
-st.write(output_answer["answer"])
+try:
+	st.write(output_answer["answer"])
+except:
+	st.write("Inference API loads model on demand, please wait for 10 secs and try again 🤗 ")
 
 st.subheader("Add Characters to Your Conversational Agent 🧙🏻🦹🏻") 
 st.write("When trained, language models like GPT-2 or DialoGPT is capable of talking like any character you want. If you have a friend-like chatbot (instead of a chatbot built for RPA) you can give your users options to talk to their favorite character. There are couple of ways of doing this, you can either fine-tune DialoGPT with sequences of conversation turns, maybe movie dialogues, or infer with a large model like GPT-J. Note that these models might have biases and you will not have any control over output, unless you make an additional effort to filter it.")