Update app.py

app.py

@@ -10,6 +10,8 @@ client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 # Initialize the ASR pipeline
 asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
 
+INITIAL_MESSAGE = "Hi! I'm your music buddy—tell me about your mood and the type of tunes you're in the mood for today!"
+
 def speech_to_text(speech):
     """Converts speech to text using the ASR pipeline."""
     return asr(speech)["text"]
@@ -23,7 +25,6 @@ def classify_mood(input_string):
             return word, True
     return None, False
 
-
 def generate(prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -51,6 +52,7 @@ def generate(prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, r
             playlist_message = f"Playing {mood.capitalize()} playlist for you!"
             return playlist_message
     return output
+
 def format_prompt(message, history):
     """Formats the prompt including fixed instructions and conversation history."""
     fixed_prompt = """
@@ -63,8 +65,6 @@ def format_prompt(message, history):
     Note: Mood should be classified only from any of these 4 classes {Happy, Sad, Instrumental, Party}, if not any of these 4 then continue with a follow-up question until you classify the mood.
 
     Note: if user asks something like i need a coffee then do not classify the mood directly and ask more follow-up questions as asked in examples.
-
-    [Examples omitted for brevity]
     """
     prompt = f"{fixed_prompt}\n"
     for user_prompt, bot_response in history:
@@ -84,7 +84,7 @@ def process_input(input_text, history):
         return history, history, "", None
     response = generate(input_text, history)
     history.append((input_text, response))
-    return history, history, "", None  # Return history twice: once for state, once for chatbot, and reset voice input
+    return history, history, "", None
 
 async def generate_audio(history):
     if history and len(history) > 0:
@@ -93,6 +93,11 @@ async def generate_audio(history):
         return audio_path
     return None
 
+async def init_chat():
+    history = [("", INITIAL_MESSAGE)]
+    audio_path = await text_to_speech(INITIAL_MESSAGE)
+    return history, history, audio_path
+
 # Gradio interface setup
 with gr.Blocks() as demo:
     gr.Markdown("# Mood-Based Music Recommender with Continuous Voice Chat")
@@ -107,6 +112,9 @@ with gr.Blocks() as demo:
         submit = gr.Button("Send")
         voice_input = gr.Audio(sources="microphone", type="filepath", label="Voice Input")
 
+    # Initialize chat with greeting
+    demo.load(init_chat, outputs=[state, chatbot, audio_output])
+
     # Handle text input
     msg.submit(process_input, inputs=[msg, state], outputs=[state, chatbot, msg, voice_input]).then(
         generate_audio, inputs=[state], outputs=[audio_output]