Speaker 1: Hey everyone. Last week I shared my prototype of real-time translation and subtitles on Twitter and it had pretty good reception, so I decided to kind of make it into an easy-to-use program and share it with you. In this video I will show you how to get it, how to install it, and how to set up a dual PC setup if you would prefer running it on a dual PC setup. Also, the whole time I will be using the real-time subtitles. So yeah, let's get started. You are going to be able to find more information about my program on my website which is going to be in the description or right here on the video. It is accessible to my tier 2 supporters on Ko-Fi, so if you subscribe on the tier 2 there, you're going to be able to get a role on Discord which will give you permissions for the program forum where you will be able to get all the relevant links. After you've downloaded them, open them up, install the CUDA driver which is essential for you to run the inference, and open the folder. Of course, after you've unzipped it of the program, find settings.exe. There you will be able to set up some important settings. You are able to choose the model. You can go from fastest to slowest. Of course, the slowest one is going to be the best, but it's going to be pretty slow and you're going to need a pretty good GPU, ideally using it on a dual PC setup. You can also choose the models according to some resources I've put on my website. You can click on the benchmarks and it's going to show you some benchmarks of some of the supported languages. You could also go to OpenAI's resources and find some benchmarks for all the languages as well. I speak Slovak which is somewhere in the middle and I found the larger model works the best, so at the moment when I'm streaming in my native language, I'm using it on a dual PC setup. If you would only be speaking and transcribing English, you could probably go with the tiny or base model and that might even work on your CPU. You can also here choose if you want to use an English-only model which are smaller to download, then you can choose if you want to translate or just transcribe which would mean if I would speak Slovak, I could get Slovak subtitles if I would only choose to transcribe, but if I turn on translate, it will translate my Slovak speech to English. Then you are able to turn on context which is a simple algorithm I've written for the ability to give the AI previous context from sentences you've said before within the context time. You can also choose if you want to use a GPU or CPU, float16 or int8 are GPU and CPU is CPU. If you'd like to speed up the computation, you could use int8 but you might lose some precision. Choose the language you're using, for example, I would speak Slovak, so I would choose Slovak, but right now I'm gonna speak English, so I'm gonna go for English. You are also able to send the closed captions to Twitch which gives your viewers the ability to turn on or off the captions in the Twitch player which is a nice feature to have. You can enable it here, but you also have to go to tools in OBS, click WebSocket, enable WebSocket server, you can turn off authentication, then you don't need to worry about the password. Only do that on your home network though, then everything should work. You can also delay the Twitch subtitles by a number of seconds to better match your lips as you're speaking, for example. You can also choose to censor the subtitles if that's something you need. I will save the settings and then I can turn on the program. When you first turn on the program, it will download the model and then it's going to tell you it's ready to go. An important thing here is that on some instances of Windows, you need to change one setting in the command prompt by right-clicking on the top left corner, going to properties and turn off quick edit mode, this. Make sure it's turned off. If you wouldn't do that, it could sometimes pause the translation. That's just a quirk of Windows, sadly. As you see, the transcription has already started and at the top we can see some IPs that are relevant for our use. Remember the first one and open your OBS and create a new browser source. Write the IP in the URL, including the port. Put the size the same as you have your OBS canvas and click OK. There you will be able to see the settings and as you can see, the subtitles have already synced. You can right-click and click interact to be able to set all relevant visual settings that you would like to change. You can choose a font from Google fonts, you can change the size and change max words that are shown and do all kinds of stuff and change the background etc. After you're done, you can close this. OBS is going to remember the settings which is nice and then you can hold alt and just hide the settings and only the subtitles are going to be visible. You might also want to turn on a delay if that's something you feel like is needed. To do that for audio you can click on this and go advanced audio properties and for example I'm using two seconds for delay on audio and to do the same for video you can right-click your source, go filters and add render delay. The max delay for one instance is 500 milliseconds so you can just duplicate and add as many as you need. For me, when I'm using the large model on a dual pc setup, two seconds is perfect. To run the subtitles on a dual pc setup you can also download the dual pc file from my discord. It's going to have two folders, one for your gaming pc that you will use for gaming and one for the pc that's doing the inference. So first, install the OBS plugin and the runtime for NDI on your pc that you are using the microphone on and install NDI tools on the pc that's running the inference. After that, on your gaming pc, go to your OBS, click on filters but make sure you click on it on your microphone, add a filter that's called dedicated NDI output, give it a name and click on apply changes. Now on your pc that's going to do the inference, open NDI tools, click on webcam, find it in the toolbar, find it in the toolbar, click on it, click on the cog and find your pc and click on the name you've set previously. After you've done that, find your audio settings and set the webcam as your default device. That should allow you to real-time stream audio from your gaming pc to your inference pc. That's it. Hopefully that was comprehensive enough.