I’m making a voice assistant and I want to teach him how to set a timer. I need to somehow implement a function that takes out the right amount of said time. I have an approximate working time of such a function, but it is not working

class TimerVoice():
 
    def parse_command(text):
       
        words = text.split() 
        if len(words) >= 5 and words[0] in ["put it on", "start it up"] and words[1] ==  and words[2] == "on": 
            try:
                minutes = int(words[3])
                word_minutes = words[4]
                if word_minutes in ["minute", "minutes"]:
                    return minutes, word_minutesword_minutes
            except ValueError:
                pass
        return None, None

    def set_timer(minutes, word_minutes):
        
        seconds = minutes * 60
        time.sleep(seconds)
        speaker(f"Time's up! Passed {minutes} {word_minutes}.")время

how do I take the number of minutes out of the said phrase and implement the timer function?

I expect that my assistant will be able to set the timer for the time specified to him