Update app.py

<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6743bed2f6b05a786ed5004b/DTHRwHIQTq6XuK8COxuWE.mpga"></audio>

app.py

@@ -2,8 +2,10 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import os
 
-HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")  # Will pull from env variable (recommended)
+# The token is securely pulled from the Hugging Face Space Secret named HUGGINGFACEHUB_API_TOKEN
+HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 
+# Setup the inference client with your model and token
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
 
 def respond(
@@ -34,7 +36,6 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response