Guide to Using Whisper AI with Pinocchio on Windows
Learn to install and use Whisper AI for speech-to-text via Pinocchio on Windows. Troubleshoot issues like OpenMP runtime errors for seamless operation.
File
How to Use Whisper AI to Transcribe Audio with Pinokio and Whisper-WebUI
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: Hey guys, I'm going to show you how to use Whisper AI to transcribe audio. Whisper is a general-purpose model for converting speech to text. This is a model by OpenAI which has been open sourced. You can find in the OpenAI's GitHub page Whisper. This is under an MIT license and they sure have installation instructions here as well. But this is not the easiest way to use it. You can instead use Pinocchio. So Pinocchio is something you can easily download the installer for and install on your Windows PC. Check the link down below in the description where I install Pinocchio. And here in Pinocchio you can go to Discover and you have all of these AI tools which you can use and kind of just single click and install. And you can also find a Whisper in here. So if you just type in Whisper we can find Whisper web UI. And here we have a

Speaker 2: download button and we can say download and it will start the download process. Okay we need to press install still.

Speaker 1: So this will get all the dependencies and stuff which need to be downloaded to run Whisper. This might take a while but after that it will be very easy to try this out and use it. Okay that didn't take too long and it

Speaker 2: now says install success and we can press done. Now it's starting up the web UI. Okay now with the web UI ready we can use a YouTube link or we could record something from the microphone or we could give it a file. Now we can also choose which model we want to use.

Speaker 1: Large version 2, version 3, medium, small. So of course the larger model will take a bit longer. Okay I'm testing out the YouTube option and giving it a link to one of my videos here. I'm choosing the medium model so that it wouldn't take that long using language automatic detection. And we can see that there's a counter calculating the time here but it's saying still initializing model and 0% done. So if you want to track the progress we can go to the terminal and we can actually see that for this first run it's downloading the model. So that will take a while but on the next try it will be faster. Okay it seems I ran into an error in the command line. I can see an error about libcomp5md dll and it says hint this means that the multiple copies of the OpenMP runtime have been linked into the program that is dangerous and blah blah blah and so on. And then it says there's a workaround to add an environment variable so that might help. But I'll leave the video at this and try to figure out the error and leave the solution in the description if I find one. Thanks for watching.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript