Update app.py

app.py

@@ -1,158 +1,21 @@
-import streamlit as st
+import gradio as gr
 from transformers import pipeline
 import numpy as np
-import threading
-from gradio_client import Client
-from streamlit_audio_recorder import st_audiorec
 
-# Initialize session state for chat history
-if "messages" not in st.session_state:
-    st.session_state["messages"] = []  # Store chat history
-
-# Load the ASR model using the Hugging Face transformers pipeline
 transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
 
-# Function to generate a response using Gradio client
-def generate_response(query):
-    try:
-        client = Client("Gopikanth123/llama2")
-        result = client.predict(query=query, api_name="/predict")
-        return result
-    except Exception as e:
-        return f"Error communicating with the Gradio backend: {e}"
-
-# Function to handle user input and bot response
-def handle_user_input(user_input):
-    if user_input:
-        # Add user message to session state
-        st.session_state["messages"].append({"user": user_input})
-
-        # Generate bot response
-        response = generate_response(user_input)
-        st.session_state["messages"].append({"bot": response})
-
-        # Speak out bot response in a new thread to avoid blocking
-        threading.Thread(target=speak_text, args=(response,), daemon=True).start()
-
-# Function to speak text (Voice Output)
-def speak_text(text):
-    import pyttsx3
-    engine = pyttsx3.init()
-    engine.stop()  # Ensure no previous loop is running
-    engine.say(text)
-    engine.runAndWait()
-
-# Function to update chat history dynamically
-def update_chat_history():
-    chat_history = st.session_state["messages"]
-    for msg in chat_history:
-        if "user" in msg:
-            st.markdown(f"<div class='chat-bubble user-message'><strong>You:</strong> {msg['user']}</div>", unsafe_allow_html=True)
-        if "bot" in msg:
-            st.markdown(f"<div class='chat-bubble bot-message'><strong>Bot:</strong> {msg['bot']}</div>", unsafe_allow_html=True)
-
-# Function to process and transcribe audio
-def transcribe_audio(audio_data, sr):
-    # Normalize audio to float32
-    audio_data = audio_data.astype(np.float32)
-    audio_data /= np.max(np.abs(audio_data))
+def transcribe(audio):
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
 
-    # Use the ASR model to transcribe the audio
-    transcription = transcriber({"sampling_rate": sr, "raw": audio_data})["text"]
-    return transcription
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
 
-# Main Streamlit app
-st.set_page_config(page_title="Llama2 Chatbot", page_icon="🤖", layout="wide")
-st.markdown(
-    """
-    <style>
-    .stButton>button {
-        background-color: #6C63FF;
-        color: white;
-        font-size: 16px;
-        border-radius: 10px;
-        padding: 10px 20px;
-    }
-    .stTextInput>div>input {
-        border: 2px solid #6C63FF;
-        border-radius: 10px;
-        padding: 10px;
-    }
-    .chat-container {
-        background-color: #F7F9FC;
-        padding: 20px;
-        border-radius: 15px;
-        max-height: 400px;
-        overflow-y: auto;
-    }
-    .chat-bubble {
-        padding: 10px 15px;
-        border-radius: 15px;
-        margin: 5px 0;
-        max-width: 80%;
-        display: inline-block;
-    }
-    .user-message {
-        background-color: #D1C4E9;
-        text-align: left;
-        margin-left: auto;
-    }
-    .bot-message {
-        background-color: #BBDEFB;
-        text-align: left;
-        margin-right: auto;
-    }
-    .input-container {
-        display: flex;
-        justify-content: space-between;
-        gap: 10px;
-        padding: 10px 0;
-    }
-    </style>
-    """,
-    unsafe_allow_html=True
-)
 
-st.title("🤖 Chat with Llama2 Bot")
-st.markdown(
-    """
-    Welcome to the *Llama2 Chatbot*!   
-    - *Type* your message below, or   
-    - *Use the microphone* to speak to the bot.   
-    """
+demo = gr.Interface(
+    transcribe,
+    gr.Audio(sources=["microphone"]),
+    "text",
 )
 
-# Display chat history
-chat_history_container = st.container()
-with chat_history_container:
-    # Add input field within a form
-    with st.form(key='input_form', clear_on_submit=True):
-        user_input = st.text_input("Type your message here...", placeholder="Hello, how are you?")
-        submit_button = st.form_submit_button("Send")
-
-        # Handle form submission
-        if submit_button:
-            handle_user_input(user_input)
-
-    # Separate button for speech recognition outside of the form
-    if st.button("Speak"):
-        # Record and process the speech using Streamlit Audio Recorder
-        audio_data, sr = st_audiorec()
-        
-        if audio_data is not None:
-            st.audio(audio_data, format="audio/wav")
-
-            # Convert to numpy array
-            audio_np = np.array(audio_data)
-
-            # Transcribe the audio
-            transcription = transcribe_audio(audio_np, sr)
-
-            # Display the recognized text
-            st.session_state["user_input"] = transcription
-            st.success(f"Recognized Text: {transcription}")
-            handle_user_input(transcription)
-
-    st.markdown("### Chat History")
-    # Update chat history on every interaction
-    update_chat_history()
+demo.launch()