Standalone Faster-Whisper-XXL - AI auto-transcription-translation

[VoodooFX]

Originally Posted by TR-9970X

You just told me that a 3:26:00 long audio can use 28Gb of RAM, so that would require a CPU, as the 4080 "only" has 16Gb

That was just for an example, use the command that I wrote.

[TR-9970X]

Hi Voodoo, I would like to propose a challenge.

I have only been using Pro for about a week, and it's proving to be very good, of course depending what model is used, and I think on a straight forward english transcribe, it's probably the best available, atm.

I have asked for your help with several issues, and you've provided appropriate suggestions, but as a true newbie, I get confused, as it is very complex, and some of your suggested commands have not yielded what I expected , but that's alright.

The SDH commands didn't really provide and SDH (well the type I'm familiar with) results, but again, that's not important.

As you know I have been transcribing the dubbed english audio for the 5 hours Das Boot series, and it's VERY time consuming, and I am still having to do a huge amount of manual editing & adding of lines of text.

What I have done is run the audio track thru Pro, with the medium, large v1, v2 & v3 models, and then having the results open in notepad, and also having the video open in SE, and going thru using Waveform to compare between ALL the models.

This has turned out to be a very accurate way of getting all possible subtitles, even if I have to listen to certain lines, over, & over, & over again to get it correct.

There is a reasonable amount of dialogue that is loud & clear enough to be picked up during the transcription, but isn't, but then there's some that is, but there are also sections that are very fast & confusing & noisy, that is a big problem.

Would increasing the volume of the audio track help ?

So anyway, enough of that, what I would really appreciate is, if I sent you the audio for one full part of the series, (a difficult part) along with the .srt that I have edited, could you do a transcription, and do as many commands as you know, to get it as close (or better) to my .srt ??, and maybe an SDH test.

If your not interested, I'll understand, but you ARE the creator of this, and this would be a very good "test"/challenge for Pro.

Regards.

[VoodooFX]

Originally Posted by TR-9970X

The SDH commands didn't really provide and SDH (well the type I'm familiar with) results, but again, that's not important.

Post the problem with all info to reproduce.

Originally Posted by TR-9970X

There is a reasonable amount of dialogue that is loud & clear enough to be picked up during the transcription, but isn't,

Post the problem with all info to reproduce.

Originally Posted by TR-9970X

Would increasing the volume of the audio track help ?

Most likely that it would not.

Originally Posted by TR-9970X

So anyway, enough of that, what I would really appreciate is, if I sent you the audio for one full part of the series, (a difficult part) along with the .srt that I have edited, could you do a transcription, and do as many commands as you know, to get it as close (or better) to my .srt ??

I'm not interested. Of course, AI-generated subtitles can't compare to human produced ones.

[TR-9970X]

Originally Posted by VoodooFX

Post the problem with all info to reproduce.



Post the problem with all info to reproduce.



Most likely that it would not.




I'm not interested. Of course, AI-generated subtitles can't compare to human produced ones.

OK, fair enough, so to cover all queries, I would like to send you an .ac3 of part 6 of Das Boot, that will provide some dialogue that isn't recognised, also an opportunity to try an SDH transcription, and to attempt to extract as much dialogue as possible.

If you could do that for me, and provide some commands/scripts you used, that will a HUGE help to my ongoing use of Pro, which IS going to get a LOT of work.

I spent nearly 7 hours on this part, today, and I've still got a few lines I can't figure out.

I've been pretty much using the command from post #56, with the additions from post #68 & #73.

You may still have the original files I uploaded:-

https://www.mediafire.com/file/yahfa...folder.7z/file
this is the 1st one I uploaded, contains part 1 as a .flac, and a few other small files.

https://www.mediafire.com/file/l1hv4...Y_0ms.ac3/file
this one is part 6 as a .ac3.

Thanks.

[VoodooFX]

Post the command to reproduce the issue on the first file.
Why would I need that bare ac3 file?

[TR-9970X]

Originally Posted by VoodooFX

Post the command to reproduce the issue on the first file.
Why would I need that bare ac3 file?

I doubt that I have that command anymore, as it didn't work for me, but I said that I was using a combo of the command(s) that are here :-

I've been pretty much using the command from post #56, with the additions from post #68 & #73.

The .ac3 was the file I wanted you to "play" with, as you'd already downloaded the other files, last week.

[Jamaika]

As an amateur, I don't know where to download the latest Whisler with CUDA. What version of CUDA is it? Should I care?
cublas64_13.dll cudart64_13.dll
I don't know why ffmpeg doesn't have CUDA? Is it complicated? Does it have a lot of bugs? It's definitely being modified constantly. Strangely, it's not Whisler's GitHub that's being modified, but Llama, and then every month there's a mirror with a patch list.
The much-derided OpenCL, Vulkan, and many other systems are also heavily modified.
https://github.com/ggml-org/llama.cp...aster/ggml/src
Is OpenCL recommended for smartphones? Who knows?
Where can I download the latest multilingual .bin translation files for the latest versions?
There is another question that has been puzzling me for years, don't use the "shit" GCC UCRT because it doesn't have CUDA.

[VoodooFX]

Originally Posted by TR-9970X

I doubt that I have that command anymore, as it didn't work for me, but I said that I was using a combo of the command(s) that are here :-

I've been pretty much using the command from post #56, with the additions from post #68 & #73.

I looked at the txt included, it's same as you asked before. And was answered already. Why you sent it again?

Originally Posted by TR-9970X

The .ac3 was the file I wanted you to "play" with, as you'd already downloaded the other files, last week.

I don't want to "play" anything.

[TR-9970X]

Originally Posted by VoodooFX

I looked at the txt included, it's same as you asked before. And was answered already. Why you sent it again?



I don't want to "play" anything.

I would like you to transcribe the .ac3 file, to extract as much dialogue as possible, (and SDH if possible) using the commands you sent me that are on the posts on your thread, that I quoted before.

[VoodooFX]

Originally Posted by TR-9970X

I would like you to transcribe the .ac3 file

Sorry, I'm not interested.

[TR-9970X]

Originally Posted by VoodooFX

Sorry, I'm not interested.

Not surprised.

You created a very complex transcription app, that seems to way better than anything currently available, and so easy to use.

However, having to pay good money for this, and get NO instructions, NO examples, and as it's turned out, very piss poor after sales service.

You've spent just as much time "helping", as you have questioning my English !!

All I was after was a command that might help in extracting as much text as possible, that I could use for future projects.

And all I get is:- "Sorry, I'm not interested".

So may this be a warning for current & future users of this fine app.

VERY disappointed.

[TR-9970X]

Originally Posted by Jamaika

As an amateur, I don't know where to download the latest Whisler with CUDA. What version of CUDA is it? Should I care?
cublas64_13.dll cudart64_13.dll
I don't know why ffmpeg doesn't have CUDA? Is it complicated? Does it have a lot of bugs? It's definitely being modified constantly. Strangely, it's not Whisler's GitHub that's being modified, but Llama, and then every month there's a mirror with a patch list.
The much-derided OpenCL, Vulkan, and many other systems are also heavily modified.
https://github.com/ggml-org/llama.cp...aster/ggml/src
Is OpenCL recommended for smartphones? Who knows?
Where can I download the latest multilingual .bin translation files for the latest versions?
There is another question that has been puzzling me for years, don't use the "shit" GCC UCRT because it doesn't have CUDA.

WTF are you on about, none of this makes much sense!!!

I think you're in the wrong place!!!

And get your info correct, what's Whisler ??

[VoodooFX]

Originally Posted by TR-9970X

All I was after was a command that might help in extracting as much text as possible, that I could use for future projects.

No, you was asking to create the subtitles for you. I don't offer such services.
There is no such magic command.

Originally Posted by TR-9970X

You've spent just as much time "helping", as you have questioning my English !!

That's wrong assumption. Failing to formulate an issue isn't an "English" problem, it's a logical one.
I can even understand Nania's "English", which is the most "encrypted" English I've encountered in my life. [Now he is using AI tools for the posts]

Originally Posted by TR-9970X

get NO instructions, NO examples, and as it's turned out, very piss poor after sales service.

Wrong assumption again, I don't offer any services.
The GitHub repo is full of examples and instructions. Actually, all your questions were already answered there.

[VoodooFX]

Originally Posted by Jamaika

As an amateur, I don't know where to download the latest Whisler with CUDA. What version of CUDA is it? Should I care?

Those Python repos are not meant for the amateur end users.
At my repo you can find a download which is ready to run.

Originally Posted by Jamaika

Strangely, it's not Whisler's GitHub that's being modified

Yes, there is not much of activity on OpenAI Whisper repo. I had to insist for months to merge my PR fixing a critical bug...

[StainlessS]

Originally Posted by VoodooFX

No, you was asking to create the subtitles for you. I don't offer such services.

Good for you.

I once (long ago) had a cry for help from a user of my software, after talking to him on the phone, I travelled down to Guildford,
(some tens of miles south of London) and I phoned him back, "I'm outside of the station" he said, "so am I", I said, but no-one in sight.
Turned out that my destination should have been "Ilford", some miles north of London.
Back on the train and went to N.London, and within 10 seconds of him showing me his problem, it became clear he was doing something
totally unexpected and very silly. {I dont recall what it was but just really daft action by him}.
So after many hours of travel, problem sorted in 10 seconds.

You just cant really go out of your way to help to such a degree, it dont make sense.
(I later got a company to do disk duplication and sales and such, much better for me as I am just too damn nice for my own good).
Dont ever make the same mistakes as me {stay mean, keep em keen}.

EDIT: The train fares cost quite a bit more than the cost of the software. {but the real cost was my time}

[TR-9970X]

Originally Posted by StainlessS

Good for you.

I once (long ago) had a cry for help from a user of my software, after talking to him on the phone, I travelled down to Guildford,
(some tens of miles south of London) and I phoned him back, "I'm outside of the station" he said, "so am I", I said, but no-one in sight.
Turned out that my destination should have been "Ilford", some miles north of London.
Back on the train and went to N.London, and within 10 seconds of him showing me his problem, it became clear he was doing something
totally unexpected and very silly. {I dont recall what it was but just really daft action by him}.
So after many hours of travel, problem sorted in 10 seconds.

You just cant really go out of your way to help to such a degree, it dont make sense.
(I later got a company to do disk duplication and sales and such, much better for me as I am just too damn nice for my own good).
Dont ever make the same mistakes as me {stay mean, keep em keen}.

EDIT: The train fares cost quite a bit more than the cost of the software. {but the real cost was my time}

Well, you got REALLY sucked in with that then...

All I wanted was a good command for a reference point, as I have only had the software for a week, and it just got out of hand, so "stay mean, keep 'em keen" won't work, he's lost a "customer".

[StainlessS]

won't work, he's lost a "customer".

I doubt he cares, he's the one doing you a favour.

This is the only command (.BAT) file that I use,

DropAudioOnME.bat

Whisper-Faster\whisper.exe --model_dir ".\_models" --language en --model "large-v2" %*

EDIT: Large v3 is out, but I aint gotten around to using it.

[TR-9970X]

Originally Posted by StainlessS

I doubt he cares, he's the one doing you a favour.

This is the only command (.BAT) file that I use,

DropAudioOnME.bat

Whisper-Faster\whisper.exe --model_dir ".\_models" --language en --model "large-v2" %*

EDIT: Large v3 is out, but I aint gotten around to using it.

Thanks.

That's a pretty basic command, but I'll give it a go.

The more commands I get collect, the better it will be for me

I have been using medium, large v1, v2 & v3, and they all come up with different results, so you can pick & choose what lines you want to use, that is closest to the audio.

[VoodooFX]

Originally Posted by StainlessS

I once (long ago) had a cry for help...
So after many hours of travel, problem sorted in 10 seconds.

You just cant really go out of your way to help to such a degree, it dont make sense.

I've worked in sales and marketing fields, I can write an academic paper on human craziness.
Once a company sent me on a field trip, to fix an issue, they didn't offer such support services but the equipment sold was expensive, it took seconds to show where to press the button...

Fun story, I sold my used laptop on Ebay to a lady. After 6 months, she contacted me claiming she had caught a virus and demanded a refund. After I explained that it's not my problem, I was bombarded with various threats, the police, the low and high courts, you name it. I just blocked her.
Two years later, I got a desperate message from Ebay support, that the same lady is bombarding them, they offered me her contacts and asked if I could deal with her. My response was short: "I don't give a flying fuck", and asked them not to contact me anymore.

Well, sometimes I go out of my way, and offer a remote desktop help. And sometimes people compensate the time wasted.


EDIT:
And don't get me started what crazy emails I get from the GitHub projects alone.
Usually from various religion organizations/cults, with crazy offers, demands, threats.

Got dozens of messages from this guy (he's at the lower side of the spectrum): https://www.youtube.com/watch?v=N8JwbmFY_zE

[VoodooFX]

Originally Posted by TR-9970X

All I wanted was a good command for a reference point

That's not true, you asked me to "play" with some file, then asked to produce the subtitles for you.
What makes even less sense, is that you have multiple commands for a reference already...