Can we provide model a fake input after every 30 second window so that it can always generate text with punctuation

[FurkanGozukara]

What I mean is for example for this video

https://youtu.be/v6TBtyO5Sxg

This is the output it made

Greetings everyone. Today I will introduce you two upcoming major events in the AI world.
Additionally, I will be demonstrating a demo of my upcoming voice cloning tutorial,
where I will have the AI read the entire epilogue generated by the new LongBoy model.
The first one is a large language model trained with 64k plus context length.
This model is announced by Navin Rao, who is CEO of MosaicML.
MosaicML has composed PyTorque library for efficient neural network training,
so these guys are already experts in the field.
When we ask the ChetGPT free edition what is its context length, the answer is only 2k tokens.
With 64k token length, you can generate 32 times bigger coherent and consistent text than ChetGPT.
If you wonder what is context size, context size refers to the maximum number of tokens or words
that a language model can take into consideration when generating text or making predictions.
In other words, it is the amount of text that the model can use as input to make a decision
or generate a response. The context size of a language model can have significant
impact on its performance and accuracy. A larger context size allows the model to
take into account more information when making predictions, which can lead to more accurate results.
With 64k context length, you can input an entire project and ask it to refactor or
upload an entire document and ask any questions about it. This can dramatically improve basically
anything regarding analysis of text, data, and programming.
The name of the announced model is LongGBoy and it will be open-sourced at the end of this week.
Once it is released, hopefully I will make a tutorial for how to use it.
And the second big upcoming thing is ChetGPT with code interpreter.
Code interpreter feature of ChetGPT is still in alpha mode and only available to
those who are selected for alpha testing. So it is not public yet.
Code interpreter is GPT-4 with 3 new capabilities. The AI can read files you upload up to 100 megabytes
which is huge. It can let you download files and it lets the AI run its own Python code.
Now this is significant. With code interpreter, the ChetGPT, the GPT-4 will be able to run its
own Python code. This is amazing. So here an example of Python code execution.
The input is like this. I am writing a blog post about how amazing ChetGPT is at working
with code right now. I would like you to create the perfect illustration and gif using Python
that represents this ability. Decide what an appropriate amazing gif would be then figure
out how to create it and let me download it. So the ChetGPT with code interpreter is writing
this code and then it is generating this gif image you are seeing right now and letting
Audur to download it. It is just amazing. But this is not all.
The first question Audur asked is show me something numinous using Python.
And the ChetGPT with code interpreter is saying this. Let's use Python to create a
visualization of Mendel's broadset which may evoke a sense of awe and wonder.
And this is the output. This is just significant. This is huge.
And here another use case. The Audur uploads an excel file without providing any context and
asks three questions. Can you do visualization and descriptive analysis to help me understand
the data? This is huge. This is significant. Can you try regressions and look for patterns?
Can you run regression diagnostics? These are the fields that requires expertise.
And now with GPT-4 and code interpreter you won't need expert people for this.
The model will be able to provide you these informations.
I will put the link of this page into description so you can check it out if you are interested
in more details. And now another major thing that GPT-4 with code interpreter.
The Audur uploads 60MB U.S. census dataset and asks the AI to explore the data,
generate its own hypothesis based on the data, conduct hypothesis tests and write a paper based
on its results. This requires huge expertise, huge amount of working time and other things.
However, the model is able to do all of this in several seconds and give you output.
You see, it wrote an academic paper about it and here the abstract of the paper.
According to the Audur, it is not a stunning paper yet. Of course, we are not expecting it,
but this is a stunning work of AI model and it will only get better over time.
And another thing is, it does every data visualization that the Audur can think of.
This is amazing. Below the Audur shown some of the data visualization graphics
and he didn't even provide data. He set model to generate fake data to just demonstrate these
graphs. The GPT-4 will also get plugins and browsers. However, according to the Audur,
they are still not very good. Plugins and browser support is still not public,
only in alpha mode and only available to those selected few people.
So as a final thing, I will make my cloned voice to read entire tweet of Navin Rao.
Hopefully, I will make a full tutorial about how to train a voice and generate as much as
possible natural sounding awesome quality voices for free on your computer with only 6GB VRAM
having GPUs.
they rose up a little now but were all the same and the grass had begun to grow in the cracks
on the step the wind had broken the yellow tape that cordoned them off
i tried to walk over once and had been turned back by a policeman
i had seen something like an exclamation point in the tape when i first looked at it
but when i looked again i couldn't see it anymore it had been torn away long ago no doubt by a
little boy running after his ball but why should i believe that he was still on the other side
running after his ball after all the years i would remember this little boy perhaps it
was some cousin or something of that sort and i would see him running like a young deer across
the grass with the sunrise flashing in his face it mightn't be that the boy was really there
but the sky might be brighter because the sunlight came in from a different place
the night of Gatsby's burial came as a surprise to me i had made a point of coming down from
my hotel early and driving out to his house in the Ford Roadster and i had gone over the whole
course of that morning in memory i hadn't expected there would be anything i could actually see on
the ground it would show that the old place had once been inhabited but the moon was full and the
white beach had a ghostly sheen i could have seen the grass growing and the stones standing
white and unbroken forever the cemetery was at the foot of the hill and when i came down the
steep slope there were white boulders piled up under my feet where they had tumbled away from
his grave in the rain in the rain Gatsby was buried in a small stone square at the foot of the hill
when i came out on the lawn there was an open grave there had been none at first and standing
around was a crowd of people many of them old acquaintances i could hear a child weeping and
a woman's voice singing and weeping a man came forward i think it was the minister and offered
me his hand he was a strange looking man tall and thin but i couldn't quite see through his
spectacles you're a good fellow nick a real good fellow he said to me you know what the minister
gonna say i did not know and was surprised mr cutaway that was a good boy he repeated he was
always good to us i am i said and i thought of my mother where they go for minister now said the
other man a squat man with a pale beard he was standing at the grave with his hand on his cane
and smiling in this lot i feel bad about all of you he was saying that my boy's gone and left us
with so much work but he's gone like you said into the good place that's where he's at now
that's where he'll stay all the rest of eternity and we can get together there all of us
what a thing it was when he first came out here and got so many ideas that he forgot his own family
we had to help that boy see the truth and now he's seen it a woman in the crowd was getting a
short passionate wail almost a howl over by the grave he's gone to another house the woman stopped
the woman stopped all the mourners stopped the minister who had seen the change in me said
there was a time you know there wasn't much chance for him but now he's right it's hard
but you must believe you know the saying a young woman began to weep then and other people took it
up they stood at the grave looking at one another talking and crying and then at a signal from the
minister they began to move off in the moonlight i went up the hill in the fall trying to arrange
in my mind the order in which i would tell people this is all for today hopefully more awesome
tutorials are coming soon please like subscribe leave a comment if you also support us on youtube
by joining or also support us on patreon i would appreciate that very much please also
join our discord channel the link of the discord channel and our patreon will be in the description
of the video and also in the comment section of the video as a pinned comment also i am open
the consultation with stable diffusion related stuff if you are interested in just support us
on patreon and contact me and hopefully i will try to help you privately hopefully see you in
another amazing video

You see after a while punctuation is lost. When we provide initial prompt like this it significantly improves the punctuation. So perhaps it can be repeated after punctuation is lost during transcription?

--initial_prompt "Welcome to the Software Engineering Courses channel."

@jongwook @ryanheise @guillaumekln

[ryanheise]

Something like #1040 may be able to help Whisper to remember the initial prompt with long audio.

[FurkanGozukara]

Something like #1040 may be able to help Whisper to remember the initial prompt with long audio.

wow looking promising thank you