GUI/real-time.py

import whisper
import pyaudio
import tkinter as tk

# PyAudio config 
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100

# Create GUI
root = tk.Tk()
text_box = tk.Text(root)
text_box.pack()

# Load Whisper 
model = whisper.load_model("base")

# Start audio stream
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, 
                channels=CHANNELS, 
                rate=RATE, 
                input=True,
                frames_per_buffer=CHUNK)

# Listen to mic in a loop
while True:
    data = stream.read(CHUNK)
    text = model.transcribe(data)['text']
    
    # Insert into GUI
    text_box.insert('end', text)
    text_box.see('end')
    
    root.update()

stream.stop_stream()
stream.close()
p.terminate()