Building a Voice to Text App USING AI! [OpenAI Whisper]

да это был Русский язык там в программе)

Is there a way to record screen audio only?

Hi I am trying to run this program but I am getting this error: """TypeError: CTkLabel.__init__() missing 1 required positional argument: 'master'
Any help how to solve will be appreciated.

Hello Boris while compile your code i get these error " ModuleNotFoundError: No module named 'customtkinter' " may i know how to install these customtkinter thanks in advance

Thanks for sharing your insights! Can this setup be modified to transcribe speech live, in realtime, with no delay? ( < 200 miliseconds)

And can it transcribe consistently for 1+ hours?

what's the background music? pls

Hi Boris,

I have used your code but getting the following message. Could you help me?

File "c:\Users\Max\.venv2\whispertest (dot) py", line 18, in <module>
main_label = ctk.CTkLabel(
TypeError: __init__() missing 1 required positional argument: 'master'

hey i have installed all the packages that u have mentioned like customtkinter, soundfile and sounddevice
after installing also still its showing like there is no moduled called !!??
how can i solve that ?

great video man

You are studying in which university?

you're my hero

By the way bro I've have a another question in my mind 😅 Can you briefly explain me that how much GPA will be needed to get into TU Berlin Computer Science in Bachelors by the way I'm going to enroll in Studienkolleg right now So how much GPA should I be target in FSP to get into TU Berlin and also in TU München and RWTH might be

Are you originally from Germany?

Your videos are quite interesting please do make a video about all the branches of Computer Science AI & ML vs Data Science vs Information Technology vs Blockchain vs Robotics

nice bruder love from india

Look who is back! Feeling enthusiastic as always, MLbruh! This is cool.

The worst part of this video is it ends so soon ... Keep it up with the amazing content 👍🏻