This is amazing and inspiring. I love the ending of the video and can’t wait for Wednesday. As a dyslexic person I think you unlocked a new use case for learning.
Tips: You can transform your device's audio output into a "microphone" on Windows, so you don't need to place your headphones over your microphone. 1. Press Windows key + R -> type "mmsys.cpl" 2. In the Recording tab, enable the Stereo Mix option. Now, "Stereo Mix" is an available microphone option! You can select it as the audio input.
Pulling in people with a flashy thumbnail of a Python code that works and then trying to monetize your code based on a library that is already supposed to be open source is in my opinion bs. it is not fair for beginners that might not know Python or whisper very well. for that I give you a thumbs down!
Ohh man !! this is the exact tutorial i need. great ides and usage of Whisper AI tool. Also planning to combine different AI into an UI interface . So cool !
There is a product for Live video Transcription there. Live text services are expensive and does not work on many current languages.. Set up a server/service that will ingest a RTMP video source, delay the video and overlay text on video in perfect sync. then offer RTMP output with burned in Live text. :) There is need for this service.
Hey man this is really cool! I'd like to know if you: 1) used the whisper v3 model? or the v2? 2) If you have seen the demos from gpt4, they also showed that gpt ASR is better than whisper v3, wonder if it will be open like whisper.
I have tried to get this to run on M1 MacBook. No joy. The CPU maxes out even with the tiny model. But then I tried with the Whisper.cpp implementation which is compiled for apple silicon. I found a whisper-cpp-python wrapper for that library. That actually runs and is far less CPU bound. It has a bit of a stutter, it is not as clean, it misses words between the chunk processing but you can see that with just a little bit more power it could work.
@Kris : I already joined as an Adept member on Jan 18th 2024 and requested access to the Github Repo via email and also via Discord but have not had any response from you yet ?
Thanks for sharing your knowledge/experience. I'm bit perplexed. The description here mentions 45+ prompts in the PDF book, the newsletter website says 40+, and the PDF doc says 35+. Which number is correct?
Interesting stuff on the image creation at the end while talking, not sure if you are taking into consideration puctuation in you sentences? Im pretty sure this would have to do with something cool, maby keeping an overview of all the text that has been moving out of the "buffer" for style ? Looks like something I could have a lot of fun with, do not have the GPU though :/ Colab however.
running fully local is one thing ... doing this via webaudio api towards a backend is a different topic - is there any implementation for that as well foreseen?
Hi Kris! I love what you do, I would like to become a member of your channel, but I can't access the page to subscribe, do you have a direct link? the one in description doesn't work for me.. have a good day!
Hello and great to see this kind of contents. I actually have a question about speech to text in another language and for example Swedish.. and passing it throw llama for correction ,.. maybe for a meeting conference or something like that .. what do you suggest ?
wow !! great video !!! Thank you for being so generous and teaching this to us, this is epic stuff! I can already start see all kinds of use cases, I cant wait to get it running, I'm really looking forward to Wednesday's video . Thanks again from Canada
Microsoft co-pilot in a teams call recording transcription. Cant simply call, needs to he a meeting call... subtle difference. Try 'meet now' in teams calender view, or make calendar event.
Faster whisper and Insanely Fast Whisper don't seem to have AMD gpu support yet. So I had to go with an alternative for the 7900xt. I used wishper.cpp with cuda/HIP + distilled whisper model. Seriously this combination is kinda real-time too, even when using the distil large v2. Though there is a downside to that, the TTS and Whisper on the GPU gobble up like 8GB or vram. This put some limit to the LLM model I can use at same time.
that is awesome. Sooo i am trying to do something like this. My sister is deaf and i want something that can also just label the who is speaking. So for a small group it will say user 1 user 2 user 3. and who ever is speaking it will let person know. Do you think that is possible.. How could i do that. I got everything but that last part.
Hey, it's in your video description, therefore easily fixed: the word is "transcription". Why not avoid the irony of a video that extols modern AI voice to text ... transcription ... in which the AI engine will surely avoid this mistake, and at the speed of light.
@@naczelnyh8rpolskiegoyt167 Yes I did. I went to Sound Recorder and made a test to see what was actually being recorded and playing it back. There was No Sound. Windows wasn't recording anything for some reason. I guess when nothing is recorded, Whisper hallucinates "Thank You" or sometimes just "You." So weird. But anyway, had to find a way to get the mic that this app was working with to record sound. So I would investigate that route, find out if the mic that this app is accessing is actually hearing anything at all.
The sentiment analysis really scares me. I mean, there's absolutely no chance that'll be abused by big tech in terms of political marketing. I mean, like, there's no way in hell right?
Kris, you are a genius. Real-time speech transcription can do a lot of things. The last example is great. I can’t wait to watch the video released on Wednesday. My computer is a Mac M chip computer. I found the code in your github and changed it to run on the CPU. Later, some problems occurred, such as incomplete transcribed content and OSError. Can you release a version suitable for Mac computers? grateful
I might be jaded but... I mean really, how about an AI that calculates the probability of drone attacks or artillery attacks? How about an AI that calculates the probability of soldiers hiding in terrain? I mean, there are already good search algorithms out there, that one may-or-may-not use to carry out artillery strikes. I'm just thinking aloud here. Probably nothing.
Zero latency? I have been check your video timeline. terminal output and audio is not correspond. you must be living a world 1-2 second ahead our timeline. 😅
What a disgusting practice of hiding very basic and poorly written code behind a paywall. No effort, no skill, GPT generated based on million dollar investments shared for free - slamming behind a paywall is as low as you can get as a UA-camr. But you don't care.
Epic! - These videos are some of the best stuff on UA-cam - love the idea with the image generation at the end
This is amazing and inspiring. I love the ending of the video and can’t wait for Wednesday. As a dyslexic person I think you unlocked a new use case for learning.
Tips: You can transform your device's audio output into a "microphone" on Windows, so you don't need to place your headphones over your microphone.
1. Press Windows key + R -> type "mmsys.cpl"
2. In the Recording tab, enable the Stereo Mix option. Now, "Stereo Mix" is an available microphone option! You can select it as the audio input.
this really helped me! Thank you!
this a grewt idea, i was using voice meeter as a virtual audio thingy and its complicated to use
I enabled the microphone but I don't know how to select it in the code. It doesn't hear anything when I start the app.
Pulling in people with a flashy thumbnail of a Python code that works and then trying to monetize your code based on a library that is already supposed to be open source is in my opinion bs. it is not fair for beginners that might not know Python or whisper very well. for that I give you a thumbs down!
Wow, an AI channel scamming people? Who would’ve ever heard of such a thing!
Tired of the fucking grifternet man, how did this happen?
@@majestechtn can you please share the code
@@majestechtn Can you share the code
Ohh man !! this is the exact tutorial i need.
great ides and usage of Whisper AI tool.
Also planning to combine different AI into an UI interface .
So cool !
how to get the code for this?
5:51 Neutral = I'm gonna go troll now. Funny stuff, great video! Thanks
Fantastic !!! A bit fast in explaining and showing, but I can always pause!
Good to see transcription and generate responses as audio in real-time for phone call
Nice video!! thanks for your help in this topics!!
There is a product for Live video Transcription there. Live text services are expensive and does not work on many current languages.. Set up a server/service that will ingest a RTMP video source, delay the video and overlay text on video in perfect sync. then offer RTMP output with burned in Live text. :) There is need for this service.
Excellent! Thank you so much for sharing!
Awesome bro! ❤
can it translate?
Could you modify this program to work with a text to speech program?
Hey man this is really cool! I'd like to know if you:
1) used the whisper v3 model? or the v2?
2) If you have seen the demos from gpt4, they also showed that gpt ASR is better than whisper v3, wonder if it will be open like whisper.
Gerçekten çok iyisiniz.
Amazing and inspiring work! Kris what about something less powerful but better accessible in terms of hardware?
What if, instead of putting the headphones over the mic, to receive the signal, you want to send the voice from another app, like UA-cam or Zoom?
Is there a way to connect a live streaming url?
I have tried to get this to run on M1 MacBook. No joy. The CPU maxes out even with the tiny model. But then I tried with the Whisper.cpp implementation which is compiled for apple silicon. I found a whisper-cpp-python wrapper for that library. That actually runs and is far less CPU bound. It has a bit of a stutter, it is not as clean, it misses words between the chunk processing but you can see that with just a little bit more power it could work.
Hi Seven, could you please share your code with me? Thank you very much!
Great video! Thanks for going through this in such an easy-to-understand way! Can you share the python scripts?
@Kris : I already joined as an Adept member on Jan 18th 2024 and requested access to the Github Repo via email and also via Discord but have not had any response from you yet ?
I became a member how do I get access to the code and the github for this
hello :D send me a e-mail at kris@allabtai.com
how can i get this code which you used in this videos same code i need.
How does the transcription performance compare to assemblyAI?
Heja Sverige ! Bra jobbat
Thanks for sharing your knowledge/experience.
I'm bit perplexed. The description here mentions 45+ prompts in the PDF book, the newsletter website says 40+, and the PDF doc says 35+. Which number is correct?
none, its a scam.
Interesting stuff on the image creation at the end while talking, not sure if you are taking into consideration puctuation in you sentences? Im pretty sure this would have to do with something cool, maby keeping an overview of all the text that has been moving out of the "buffer" for style ? Looks like something I could have a lot of fun with, do not have the GPU though :/ Colab however.
running fully local is one thing ... doing this via webaudio api towards a backend is a different topic - is there any implementation for that as well foreseen?
I have been looking where to start, fantastic work, where can I have the code for testing
Now make it translate and do phone-cals
Noooo…pls nooo. We got plenty auto callers already.
@@rne1223
Where?
Hello ur computer has a virus
Which gpu are you using ?
Hi,
Can get the github repo of the above code ?
Thanks
Would it be possible to do speaker recognition then pipe it into translation
where do I get the code sir?
Hi Kris! I love what you do, I would like to become a member of your channel, but I can't access the page to subscribe, do you have a direct link? the one in description doesn't work for me.. have a good day!
Hello and great to see this kind of contents.
I actually have a question about speech to text in another language and for example Swedish.. and passing it throw llama for correction ,.. maybe for a meeting conference or something like that .. what do you suggest ?
Do you think this could be used to transcribe, for example, phone calls made through the browser? I would greatly appreciate your response :)
wow !! great video !!! Thank you for being so generous and teaching this to us, this is epic stuff! I can already start see all kinds of use cases, I cant wait to get it running, I'm really looking forward to Wednesday's video . Thanks again from Canada
I think there's an even faster whisper module but I forget what it's called
did you find out?
i love your videos man , please video about fastwhisper on docker api please
faster whisper or whisper turbo?
Can I did this with javascript?
how can we identify different speakers?
Microsoft co-pilot in a teams call recording transcription. Cant simply call, needs to he a meeting call... subtle difference. Try 'meet now' in teams calender view, or make calendar event.
thanks this is great! Where can I find the actual code you have on your screen? Struggling to find it on the github
You get it?
Hi, I'm a subscriber but I do not have access to your github ,can you helpme please?
Hello. I’m beginner in this major. How can I get your code to refer? Thank you
confused can you please create step by step video and provide the code as well.
Impresario thank you
where do i get the setup/python code
where can we get the code
github linked in the description.
How do we join your community?
Link in desc :) youtube member
@@AllAboutAI just subscribed to your channel but not getting GitHub code..
Can this run on raspberry pi?
I want to do speech to text Audio from the browser speaker and not from the mic , how can we do that in real time ?
It's easily done via running virtual audio cable (VAC) you can google it and there's a lot of resources out there on how to use this software.
how to access your sourcecode as a paid channel member?
Faster whisper and Insanely Fast Whisper don't seem to have AMD gpu support yet. So I had to go with an alternative for the 7900xt. I used wishper.cpp with cuda/HIP + distilled whisper model. Seriously this combination is kinda real-time too, even when using the distil large v2. Though there is a downside to that, the TTS and Whisper on the GPU gobble up like 8GB or vram. This put some limit to the LLM model I can use at same time.
This will be a good tool for language immersion chinese / japanese / indonesian along with the deepl clipboard tool, edge browsers tts engine.
Can i convert this code to cpp and implement using Arduino without api
does it support speaker diairzation?
I want to do speech to text Audio from the browser speaker and not from the mic , how can we do that in real time ?
i cant find the script of the realtime translation pls help me finding it :((
If there any way to translate this text to another languages it will be awesome
that is awesome. Sooo i am trying to do something like this. My sister is deaf and i want something that can also just label the who is speaking. So for a small group it will say user 1 user 2 user 3. and who ever is speaking it will let person know. Do you think that is possible.. How could i do that. I got everything but that last part.
How can i get acess to this code?
The accuracy sucks. Many words are incorrect which you can see in the image itself.
This isn't usable in the real world.
Can we get the code used in this video that would be really helpful
Can I get the code of it?
Has anyone updated the code from the previous video to use this recording method instead?
cannot find the code in github
where can we find the code that you used?
github linked in the description
Can you pls share you code?
what is a transcribe_chunk function in the code? Seems that it's not from faster_whisper?
It's model.transcribe() from faster-whisper example
Hey, it's in your video description, therefore easily fixed: the word is "transcription". Why not avoid the irony of a video that extols modern AI voice to text ... transcription ... in which the AI engine will surely avoid this mistake, and at the speed of light.
just joined. would be good to get my grubby paws on the files for this.
could you do another demo to see how it can translate in real time?
yes! there are no really good or fast translation apps available. UA-cam auto translate is horrible!
how can we download this script?
All I get is "Thank you! Thank You! Thank you! as my transcribed output....so weird
hey, same problem here, actually exact same problem, have you figured it out?
@@naczelnyh8rpolskiegoyt167 Yes I did. I went to Sound Recorder and made a test to see what was actually being recorded and playing it back. There was No Sound. Windows wasn't recording anything for some reason. I guess when nothing is recorded, Whisper hallucinates "Thank You" or sometimes just "You." So weird. But anyway, had to find a way to get the mic that this app was working with to record sound. So I would investigate that route, find out if the mic that this app is accessing is actually hearing anything at all.
The sentiment analysis really scares me. I mean, there's absolutely no chance that'll be abused by big tech in terms of political marketing. I mean, like, there's no way in hell right?
Can we take source code ?
Can you use different languages?
iam a member but i cant acces the github pls HELP
this i my github
maxaxaxaxxaxaxaax
doesn´t work because calls supertools and any file is called supertools, thanks for your time but ...
Kris, you are a genius. Real-time speech transcription can do a lot of things. The last example is great. I can’t wait to watch the video released on Wednesday. My computer is a Mac M chip computer. I found the code in your github and changed it to run on the CPU. Later, some problems occurred, such as incomplete transcribed content and OSError. Can you release a version suitable for Mac computers? grateful
I might be jaded but... I mean really, how about an AI that calculates the probability of drone attacks or artillery attacks? How about an AI that calculates the probability of soldiers hiding in terrain? I mean, there are already good search algorithms out there, that one may-or-may-not use to carry out artillery strikes. I'm just thinking aloud here. Probably nothing.
Bro can you put th video about live streaming voice to text
Waiting for the in deep video :) Btw your discord invite link is expired.
Please provode the code
welldone
ma è gratuito?
This is Presentation not tutorial
how do i get access to the github?? TAKE MY MONEY!
lol no but seriously how
pip install patience and kindness
Zero latency? I have been check your video timeline. terminal output and audio is not correspond. you must be living a world 1-2 second ahead our timeline. 😅
Where is the link to this source code ? Thanks amazing
did you get the code
no @@nafila5084
@@nafila5084 Can share the code to me as well?
transcriPtion
🧡
🎈
What a disgusting practice of hiding very basic and poorly written code behind a paywall. No effort, no skill, GPT generated based on million dollar investments shared for free - slamming behind a paywall is as low as you can get as a UA-camr. But you don't care.
BROOOO 🎉 FIRST
This video is so bad, yo ass did not explain anything