Learn to Use OpenAI Whisper Without Coding (Full Transcript)

Speaker 1: Hello, everyone. Welcome to another tutorial video. Today, I will show you how to use OpenAI Whisper without actually coding and using Python for it. Now, as you can see, AI Whisper or Whisper AI is basically a speech-to-text OpenAI tool that allows you to record a video or record an audio, sorry, and then you can basically reveal a script, right? That audio will be turned into a text-based script, right? As you can see, this is basically how it works, but the best way to do this without actually going to encode it is to go and type in Whisper AI online. Once you type that in, you will be brought to a bunch of pages like this and you will need to find this one, Hugging Face, click on that, and you will be brought to this page right here. Here, you can go and record a video, click record a video or record an audio, sorry, not video, and then you will be brought to this right here and you will be able to click transcribe. Now, as you can see, I already transcribed one part of my audio. As you can see, this was the audio. Welcome to another video. In this video, I will show you how you can go and use Whisper AI. As you can see, this is what I said, right? And this is basically the text, right? So if I go here, I can also edit it, right? I can cut it, right? If I want, I can delete it and I can record again from my microphone as well. Then once I record from my microphone, I can hit this transcribe and this will be transcribed and then I can copy this, right? Into a Google Docs, right? Or I can share this to community, right? Now, this is basically a OpenAI Whisper, Whisper AI based on a web, right? So you can actually go and you don't have to go and just type codes into Python and stuff like that in order to make this work, right? You can just go here and you can basically go and yeah, you can basically use Whisper AI. As you can see, Whisper is a general purpose speech recognition model. It's trained on a large data set of diverse audio and also a multitask model that can perform multilingual speech recognition as well as speech translation and language identification. Now, as you can see, this demo cuts audio after 30 seconds. So keep in mind, this is only for 30 seconds, unfortunately. So hope you find this video useful. It is a little bit different video than what we usually do. If you want more ChatGPT 4 videos, ChatGPT 3 videos, then definitely go and click the subscribe down below and comment down below and we'll see you in the next video. Thank you guys for watching. Transcribed by https://otter.ai