app.py

import time
import random
import gradio as gr
# from transformers import pipeline

# p = pipeline("automatic-speech-recognition")

def user(user_message, history):
    return "", history + [[user_message, None]]

# def transcribe(audio, state=""):
#     text = p(audio)["text"]
#     state += text + " "
#     return state, state

def bot(history):
    bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
    history[-1][1] = ""
    for character in bot_message:
        history[-1][1] += character
        time.sleep(0.05)
        yield history

with gr.Blocks() as demo:
    # chatbot = gr.Chatbot()
    # msg = gr.Textbox()
    chatbot = gr.Chatbot([], show_label=False, elem_id="chatbot").style(height=500)

    with gr.Row():
        with gr.Column(scale=0.85):
            txt = gr.Textbox(
                show_label=False,
                placeholder="Type your response and press enter, or record your response",
            ).style(container=False)
        with gr.Column(scale=0.15, min_width=0):
            submit = gr.Button("Submit")
    # gr.Interface(
    #     fn=transcribe, 
    #     inputs=[
    #         gr.Audio(source="microphone", type="filepath", streaming=True), 
    #         "state"
    #     ],
    #     outputs=[
    #         msg,
    #         "state"
    #     ],
    #     live=True)

    txt.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    submit.click(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )

demo.queue()
demo.launch()