app.py

import gradio as gr
import pyttsx3  # Text-to-speech
import speech_recognition as sr  # Speech-to-text
from llama_cpp import Llama

model = "bartowski/Llama-3.2-1B-Instruct-GGUF"
llm = Llama.from_pretrained(
    repo_id=model,
    filename="Llama-3.2-1B-Instruct-Q8_0.gguf",
    verbose=True,
    use_mmap=True,
    use_mlock=True,
    n_threads=4,
    n_threads_batch=4,
    n_ctx=2000,
)

# Initialize TTS engine
tts_engine = pyttsx3.init()

# Speech-to-text function
def speech_to_text():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        print("Listening...")
        audio = recognizer.listen(source)
    try:
        text = recognizer.recognize_google(audio)
        print(f"You said: {text}")
        return text
    except sr.UnknownValueError:
        return "Sorry, I did not understand that."
    except sr.RequestError as e:
        return f"Could not request results; {e}"

# Text-to-speech function
def text_to_speech(response_text):
    tts_engine.say(response_text)
    tts_engine.runAndWait()

# Main AI response function
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""
    completion = llm.create_chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p
    )

    for message in completion:
        delta = message['choices'][0]['delta']
        if 'content' in delta:
            response += delta['content']
            yield response

    # Speak the AI response
    text_to_speech(response)

# Gradio UI with added microphone component
demo = gr.Interface(
    fn=respond,
    inputs=[
        gr.Microphone(streaming=True, label="Speak your question"),
        gr.Textbox(
            value="You are a helpful assistant.",
            label="System message",
        ),
        gr.Slider(minimum=1, maximum=8192, value=2048, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
    outputs=gr.Textbox(label="Response"),
    live=True,
    description=model,
)

if __name__ == "__main__":
    demo.launch()