app.py

import openai
import gradio as gr
import os
openai.api_key = os.getenv("OPENAI_API_KEY")

from transformers import pipeline
p = pipeline("automatic-speech-recognition",model="openai/whisper-tiny")

def transcribe(audio):
    text = p(audio)["text"]
    return text
    
# gr.Interface(
#     fn=transcribe, 
#     inputs=gr.Audio(source="microphone", type="filepath"), 
#     outputs="text").launch()



 
messages = [
    {"role": "system", 
     "content": "you name is Rebecca and you are a Pepsico call center assistant and your job is to take the order from the customer"}
]

def chatbot(input):
    if input:
        input = transcribe(input)
        messages.append({"role": "user", "content": input})
        chat = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            temperature=0.2,
            max_tokens=320,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0
        )
        reply = chat.choices[0].message.content
        messages.append({"role": "assistant", "content": reply})
        return reply

##inputs = gr.inputs.Textbox(lines=7, label="Chat with PepsiCo AI assitant")

inputs= gr.Audio(source="microphone", type="filepath")


outputs = gr.outputs.Textbox(label="Reply")

gr.Interface(fn= chatbot, 
             inputs=inputs, 
             outputs=outputs, 
             title="chatbot",
             description="Ask anything you want",
             theme="compact").launch()


# gr.Interface(
#     fn=transcribe, 
#     inputs= inputs, 
#     outputs="text"

# ).launch()