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

[VoodooFX]

Whisper is a state of the art auto-transcription-translation model - Robust Speech Recognition via Large-Scale Weak Supervision

https://i.imgur.com/DYVm3u6.png

There are my compiled binaries for newbies: https://github.com/Purfview/whisper-standalone-win

If someone doesn't have fast CUDA GPU, you can use one for free in Colab.

Here I setup ready to use Jupiter's Notebook with Faster-Whisper-XXL (https://colab.research.google.com/drive/17EE-Ty6do7LKYGGUAoog-tz0QOx5V0q0).

Guide how to use it:
1) Press to run the first cell to download and setup Faster-Whisper-XXL. ["triangle at the front of the cell"]
2) When a session connects press "Files" icon at the left and drag & drop your audio file(s) there ( its "/content" folder)
Note: Do not drop video files as uploading is kinda slow. Remux video with MKVToolNix deselecting video and other not needed tracks.
3) When the first cell is done [stopped spinning] you can run the second cell to transcribe [on the first run a model will be downloaded].
Note: Adjust Faster-Whisper-XXL parameters to your liking.
4) When you are done working "Runtime" > "Disconnect and delete runtime".

[StainlessS]

WOW! VX, you be da man.

[VoodooFX]

@StainlessS How is internet at the pub, did you downloaded a release with GPU?

[StainlessS]

Not yet, I thought that it seemed a little bit wierd, what with all of the various downloads necessary.
I did not have a clue what to do with stuff on the github site, did not seem to be anything downloadable.
However, I did find some stuff here:- https://github.com/openai/whisper/discussions/63
which would seem to be the model thingies.
Maybe I down them in pub, but in no great hurry at the moment.
I'll also down the GPU thingy.

EDIT: Yes I know it can auto download the models, but I want offline download and want to know where they come from.

[VoodooFX]

I did not have a clue what to do with stuff on the github site, did not seem to be anything downloadable.

It seemed that you knew where to download:


EDIT: What kind of speed can one expect (I downed the 170MB-ish CPU version, 1.6-ish GB for GPU ver$ is a bit rich for me, is that much faster ?) ?.

Anyway, in GitGub at the right side you should see "Releases" button.

Model[s] are downloaded separately, automatically or manually, link for the models is in the front page of the repo.

You don't want "OpenAI" stuff, it's very slow.

[StainlessS]

OK, I got it working [with auto download of the model, I downloaded the pytorch models [.pt extension] by mistake, in pub].

I tested with both CPU and GPU versions, GPU pleasantly faster,
01:33:xx movie under GPU/medium.en model took 269 seconds for 933 subtiles.

Thanks for prodding me in this direction.

[Emulgator]

CPU: I get
2023-05-04 23:28:28.0660903 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1671 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.
but after that recognition starts. Aborted manually to see CUDA blow...

CUDA: the same report, then it starts munching...

Still it repeats some lines over and over, but
WOW IS THAT QUICK ! Like 10-fold going from a .wav file.
635s for a 1:43:40 musical movie in English, 1769 subs, songs included.
103 mins playing time transcribed in 10,5min with ~95% accuracy.
Found slang stuff I was helpless to translate before.

CPU 11900K 17%, GPU RTX3080 1% How, well...

Awesome work, many thanks, VoodooFX !

[VoodooFX]

That message from onnxruntime is "normal", expectable nonsense from Microsoft's lib. :)

Still it repeats some lines over and over
Can you cut and share shorter sample of that audio where it happens? [Test if cut sample still loops]

EDIT:

going from a .wav file
Use original audio, don't convert it to anything, results from ffmpeg conversion are noticeably worse for some reason.

EDIT2:

Btw, some people reported that on CPU it's a bit more accurate.

[Emulgator]

No time to continue right now but I guess it will be the same behaviour as with the other Whisper versions within SubtitleEdit:
If I just restrict and give only a smaller range it works most of the time.

[Emulgator]

Now let's have this engine on Android (I once had to help a hearing-disabled person using their mobile phone for live transcription),
and finally Big Goo's online-listening would be out of the water...

[StainlessS]

Btw, some people reported that on CPU it's a bit more accurate.
My CPU and GPU outputs were definitely different, GPU quite often split longer single CPU sub
into two shorter GPU subs. [I think]

EDIT:
I wonder how it would do on movie SNATCH, Brad Pitt's irish gypsy accent [fantastic job by Pitt to make it totally unintelligible].

Snatch/Pitt: https://www.youtube.com/watch?v=Gfzxz7asbZs

[VoodooFX]

On English audio I get better results with multilingual "medium" model than with "medium.en". :confused:


@Emulgator
@StainlessS
Could you test if new Faster-Whisper r117 runs OK on CUDA? [Executable is small]
And I would be interested in transcription accuracy and speed benchmark vs previous version.

[StainlessS]

[Executable is small]
Yeah, maybe, but requires
cuBLAS 11.x @ 3.4GB, and
cuDNN 8.x @ unknown size (I have an nVidia devs account somewhere, I'll havta find it).
I'm currently on 50GB data per month [EE @ £20/month], I think maybe I'll up it to 130GB/month next month [think next up is 130GB for £30/month].
Anyway, I'll down them in pub next time I'm there.

EDIT: The models were updated 22hours ago.
EDIT: Actually EE 125GB for £30/month for my 4G+ Router. https://shop.ee.co.uk/sim-only/pay-as-you-go-phones#

[VoodooFX]

Yeah, maybe, but requires
cuBLAS 11.x @ 3.4GB, and
cuDNN 8.x @ unknown size (I have an nVidia devs account somewhere, I'll havta find it).

EDIT: The models were updated 22hours ago.

Maybe it would work out of the box. Shouldn't that be already installed with CUDA drivers/stuff?

EDIT:
Actually all that stuff should be present in previous version, copying dlls to the same folder from there should work.

[VoodooFX]

I'm currently on 50GB data per month [EE @ £20/month], I think maybe I'll up it to 130GB/month next month [think next up is 130GB for £30/month].

Get GiffGaff PAYG, unlimited* for £25. [GiffGaff is basically O2]

*Full 4G speed till 80GB, after that it limits to 386kb at daytime, but at night it's full speed again.

[StainlessS]

Thanx VFX, but I'll stick with faster EE, says in my given link that speed is max 25mbps.
EtherNet, USB etc, tend to have a management overhead of 20%, I assume same for 4G,
So to convert mbps to MB/s, just divide by 10.
Despite what EE says (max 25 mbps) I regularly get 3 or 4 MB/s (as for 30 or 40 mbps), and have
once noticed it at 8MB/s during the night.
Thats pretty good speed considering that I'm quite a way from city urban area (I'm near green parkland),
and only get 2 out of 5 bar signal.

EDIT: I presume that we get charged for the management overhead, and that it is included in max 25 mbps.

*Full 4G speed till 80GB, after that it limits to 386kb at daytime, but at night it's full speed again.
Did not know that, thanx.

[VoodooFX]

@StainlessS
I could make a release [or separate download] including Nvidia libs, but I don't know which libs are actually needed, I don't wanna include whole 4GB stuff.
Could someone check which libs are actually needed by copying dlls [to same folder with whisper.exe from "r117"] one by one on error from "b103" release, there libs are located at "Whisper-Faster\torch\lib"?
That would need Windows with only Nividia drivers installed without CUDA Toolkit & cuDNN.

[Emulgator]

If swapped into the same python-laden folder as r103, r117 throws error:
"Could not load cudnn_ops_infer64_8.dll. Error code 126.
Make sure that cudnn_ops_infer64_8.dll is in your path."
That file was indeed in torch\lib, together with 36 more .dlls.
I copied that side by side to 117, then
"Could not load cudnn_cnn_infer64_8.dll. Error code 126.
Make sure that cudnn_cnn_infer64_8.dll is in your path."
I copied it side by side, then still the same fault.

Win10P64, i9-11900K, RTX3080, cudart64_110.dll 6.14.11.11080 in system32.
P.S. This is my replacement system, so no CUDA 11.8 installed yet.

[VoodooFX]

@Emulgator Thanks for testing it.

r117 is standalone single executable, no need to copy it to r103 folder. [It's not some incremental patch]

"cudnn_cnn_infer64_8.dll" has dependency on "zlibwapi.dll", so copy it too.

[Emulgator]

Ah, ok. Continuing.
Removed cudart64_110.dll 6.14.11.11080 from system32,
(still no CUDA 11.8 installed).

Now running from a separate folder, containing only the .exe, the .bat and the _models folder,
and adding dependencies as we speak.

We had
cudnn_ops_infer64_8.dll
cudnn_cnn_infer64_8.dll

You hinted
zlibwapi.dll
I added that.

Now it asked for
cublasLt64_11.dll
I added that.

Then it asked for
cublas64_11.dll
I added that.

Start: Success ! Now it runs with just these 5 dependencies.
14..17..18% on CPU, 3 of 16 cores (1 is 90%, 1 is 66%, 1 is 33%), 1% GPU.
Load distribution looks the same as with r103.

Speed: will tell when it is finished. Feels the same range as with r103.
Then I will compare again r103 vs. r117 apples-to-apples.

Finished: 949s for the same movie. 50%slower.
Was stuck quite a bit at 01:37:40.700 (song beginning)
generating of subtitles ended there at #1757,
so it did not reach the movie's end at 01:43:40

Repeated r103: 633s for the same movie, ran until the end.
At the moment r103 within its full dependency bag looks better.

nVidia Driver on this (older, clone father, now replacement) system SSD: 462.75

[VoodooFX]

Removed cudart64_110.dll 6.14.11.11080 from system32
Why did you removed it? Maybe it's present in other folder?


generating of subtitles ended there at #1757,
so it did not reach the movie's end at 01:43:40
Subtitle numbers doesn't mean anything, some lines could be in one sub, you need to check actual subtitles.


At the moment r103 looks better.
Did you check transcription differences?

By default r117 runs int8 quantization on GPU, r103 runs float16. [on CPU both use int8]
I changed that because few users reported that int8 is more accurate than float16 and that speed is same.

Quantization can be set by "--compute_type".

EDIT:
@Emulgator
Could you do tests these 2 short files with "medium": https://we.tl/t-S5gnRvMuQB , with "--compute_type=float16" & "--compute_type=int8" on CUDA and share 4 srt files?

[Emulgator]

Originally Posted by Emulgator View Post
Removed cudart64_110.dll 6.14.11.11080 from system32

Why did you removed it? Maybe it's present in other folder?

To make sure that only the .dlls I should introduce are loaded and not an additional dependency not accounted for.

Ah, well, 8bit vs. 16bit can make all the difference !
I give a .wav 32bit float decode from the DVD .ac3 track and use the large multilingual model only.

Comparing the 3 runs from a 25fps-speed-up 1961 musical movie English soundtrack,
quick, cockney and other slang talking, interleaved with songs
using WinMerge triple comparison:

r103 GPU from 04.05.2023
r103 GPU from 17.05.2023
r117 GPU from 17.05.2023

All versions have their uses and guess differently.
Which is good for me: a wealth to choose from.
Now it is up to the subtitler (me) just to merge the best parts.

Will have to talk Nikse into having 3 editor tabs in SubtitleEdit, muhahaha ;-)

Downloaded your sample, testing soon.

[Emulgator]

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>whisper.exe "C:\_PROG\! Subtitle Tools\! Testfile VoodooFX 2023 05 18\test_original.aac" --language en --model "large" --compute_type=float16

Standalone Faster-Whisper r117 running on: CUDA

Estimating duration from bitrate, this may be inaccurate
2023-05-18 15:05:00.1132781 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1671 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.

[00:00.760 --> 00:02.760] Feeling inspired yet?
[00:02.760 --> 00:03.760] No.
[00:03.760 --> 00:08.890] Thank you.
[00:08.890 --> 00:10.890] I thought you said you were hungry.
[00:12.890 --> 00:17.890] There's a boat tour of the Trakla Island formations this afternoon.
[00:17.890 --> 00:22.890] I was thinking we could go on that and make reservations in town for dinner.
[00:23.890 --> 00:25.890] You could try the Chinese place.
[00:25.890 --> 00:28.890] I don't think I'd survive another dinner in town.
[00:29.890 --> 00:31.890] Even the idea that...
[00:31.890 --> 00:33.890] Does anyone think it's a real town?
[00:36.890 --> 00:38.890] Why would they have a Chinese place?
[00:43.280 --> 00:46.280] Is it okay if I go? I'll meet you on the beach.
[00:47.280 --> 00:49.280] Yeah, sure.
[01:22.270 --> 01:24.270] Someone's making a statement.
[01:24.270 --> 01:26.270] One of the locals, I guess.
[01:29.270 --> 01:31.270] What do you think he's trying to say?
[01:31.270 --> 01:35.270] He's saying that he wants to put a long knife right through her.
[01:35.270 --> 01:40.270] And after you die, he'll hang your body at the airport to scare off the other tourists.
[01:42.270 --> 01:44.270] Seems a bit extreme.
[01:46.270 --> 01:49.270] The Latokans are a melodramatic people.
[01:54.740 --> 01:56.740] I loved your book.
[01:58.740 --> 01:59.740] Sorry?
[02:00.740 --> 02:03.740] You're James Foster. I loved your book.
[02:06.740 --> 02:09.740] Sorry, is that good? I don't mean to put you in the spot.
[02:09.740 --> 02:11.740] No, thank you.
[02:11.740 --> 02:13.740] It's just, um...
[02:13.740 --> 02:15.740] Not a lot of people read my book.
[02:15.740 --> 02:17.740] I'm Gabby Bauer.
[02:17.740 --> 02:19.740] I'm James Foster.
[02:21.740 --> 02:22.740] Alvin!
[02:25.520 --> 02:27.520] This is James Foster.
[02:27.520 --> 02:29.520] Hi, nice to meet you. Albon Bauer.
[02:29.520 --> 02:30.520] Pleasure.
[02:30.520 --> 02:32.520] He wrote your book that I love, The Variable Sheath.
[02:32.520 --> 02:34.520] Oh, yeah, I remember.
[02:34.520 --> 02:36.520] I thought it was brilliant.
[02:36.520 --> 02:37.520] Yes.
[02:37.520 --> 02:41.520] James, do you think I could convince you to join us for dinner this evening?
[02:42.520 --> 02:46.520] I've been seeing you around the resort for a few days now and I would love to get to know you.
[02:46.520 --> 02:49.520] We have a reservation tonight at Yang's.
[03:00.450 --> 03:02.450] Yeah, it was a good...
[03:04.450 --> 03:06.450] ...learning experience.
[03:06.450 --> 03:07.450] All right.
[03:07.450 --> 03:10.450] Is there anything else I can get you?
[03:10.450 --> 03:12.450] Um, that's all I think.
[03:12.450 --> 03:14.450] All right, everyone, please have a great meal.
[03:14.450 --> 03:15.450] Thank you.
[03:15.450 --> 03:19.450] And let me know any time if I can make your experience even more enjoyable.
[03:22.450 --> 03:24.450] He's an interesting guy.
[03:24.450 --> 03:25.450] Yes.
[03:25.450 --> 03:29.450] This resort is labelled in the resort guide as a multicultural dining experience.
[03:30.450 --> 03:32.450] Well, it certainly is an experience.
[03:33.450 --> 03:36.450] So, Albon, what is it you do for a living?
[03:36.450 --> 03:39.450] Oh, architecture. But I'm mostly retired.
[03:39.450 --> 03:42.450] Now I run a journal out of Los Angeles called Glass Pane.
[03:42.450 --> 03:43.450] You're French?
[03:43.450 --> 03:46.450] Oh, no. Swiss first, from Geneva.
[03:46.450 --> 03:48.450] Then Paris, then LA.
[03:49.450 --> 03:52.450] I'm from London first. Then Paris.
[03:52.450 --> 03:53.450] We met there.
[03:53.450 --> 03:54.450] That's how we met.
[03:54.450 --> 03:57.450] But I couldn't get work there, so I made Albon move with me.
[03:58.450 --> 04:00.450] And what do you do?
[04:00.450 --> 04:03.450] Well, I'm an actress, of course.
[04:03.450 --> 04:05.450] Oh, really? She's great.
[04:06.450 --> 04:07.450] For commercials.
[04:07.450 --> 04:09.450] I have a contract with an LA company.
[04:09.450 --> 04:11.450] They've been grooming me.
[04:11.450 --> 04:13.450] I specialize in failing naturally.
[04:14.450 --> 04:17.450] What does that mean? Failing naturally?
[04:18.450 --> 04:22.450] Finding a natural-seeming way to fail at any given task.
[04:22.450 --> 04:24.450] In each of the commercials that I'm in,
[04:24.450 --> 04:27.450] I'm the one who simply can't go on without the product.
[04:27.450 --> 04:29.450] It's ridiculous for me not to have the product.
[04:30.450 --> 04:31.450] Okay.
[04:31.450 --> 04:32.450] Show them.
[04:32.450 --> 04:33.450] No.
[04:33.450 --> 04:34.450] No, you should.
[04:34.450 --> 04:35.450] Yeah.
[04:35.450 --> 04:36.450] Please.
[04:36.450 --> 04:37.450] Do you want to see?
[04:37.450 --> 04:38.450] I want to see.
[04:38.450 --> 04:39.450] Here.
[04:42.450 --> 04:43.450] She's amazing.
[04:56.660 --> 05:02.450] I just...
[05:04.450 --> 05:05.450] I...

Standalone Faster-Whisper operation finished in: 25 seconds

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>pause
Drücken Sie eine beliebige Taste . . .

[Emulgator]

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>whisper.exe "C:\_PROG\! Subtitle Tools\! Testfile VoodooFX 2023 05 18\test_original.aac" --language en --model "large" --compute_type=int8

Standalone Faster-Whisper r117 running on: CUDA

Estimating duration from bitrate, this may be inaccurate
2023-05-18 15:08:01.9382416 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1671 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.

[00:00.760 --> 00:02.760] Feeling inspired yet?
[00:02.760 --> 00:08.890] No, thank you.
[00:08.890 --> 00:10.890] I thought you said you were hungry.
[00:12.890 --> 00:17.890] There's a boat tour of the Trakla Island formations this afternoon.
[00:17.890 --> 00:22.890] I was thinking we could go on that and make reservations in town for dinner.
[00:23.890 --> 00:25.890] You could try the Chinese place.
[00:25.890 --> 00:28.890] I don't think I'd survive another dinner in town.
[00:29.890 --> 00:31.890] Even the idea that...
[00:31.890 --> 00:33.890] Does anyone think it's a real town?
[00:35.890 --> 00:38.890] Why would they have a Chinese place?
[00:43.280 --> 00:46.280] Is it okay if I go? I'll meet you on the beach.
[00:47.280 --> 00:49.280] Yeah, sure.
[01:22.270 --> 01:24.270] Someone's making a statement.
[01:24.270 --> 01:27.270] One of the locals, I guess.
[01:29.270 --> 01:31.270] What do you think he's trying to say?
[01:31.270 --> 01:35.270] He's saying that he wants to put a long knife right through her.
[01:35.270 --> 01:40.270] And after you die, he'll hang your body at the airport to scare off the other tourists.
[01:42.270 --> 01:44.270] Seems a bit extreme.
[01:46.270 --> 01:49.270] The Latokans are a melodramatic people.
[01:54.740 --> 01:56.740] I loved your book.
[01:58.740 --> 01:59.740] Sorry?
[02:00.740 --> 02:03.740] You're James Foster. I loved your book.
[02:06.740 --> 02:09.740] Sorry, is that good? I don't mean to put you in the spot.
[02:09.740 --> 02:11.740] No, thank you.
[02:11.740 --> 02:13.740] It's just, um...
[02:13.740 --> 02:15.740] Not a lot of people read my book.
[02:15.740 --> 02:17.740] I'm Gabby Bauer.
[02:17.740 --> 02:19.740] I'm James Foster.
[02:21.740 --> 02:22.740] Alvin!
[02:25.520 --> 02:27.520] This is James Foster.
[02:27.520 --> 02:29.520] Hi, nice to meet you. Albon Bauer.
[02:29.520 --> 02:30.520] Pleasure.
[02:30.520 --> 02:32.520] He wrote your book that I love, The Variable Sheath.
[02:32.520 --> 02:34.520] Oh, yeah, I remember.
[02:34.520 --> 02:36.520] I thought it was brilliant.
[02:36.520 --> 02:37.520] Yes.
[02:37.520 --> 02:41.520] James, do you think I could convince you to join us for dinner this evening?
[02:42.520 --> 02:46.520] I've been seeing you around the resort for a few days now and I would love to get to know you.
[02:46.520 --> 02:49.520] We have a reservation tonight at Yang's.
[03:00.450 --> 03:02.450] Yeah, it was a good...
[03:04.450 --> 03:06.450] ...learning experience.
[03:06.450 --> 03:07.450] All right.
[03:07.450 --> 03:10.450] Is there anything else I can get you?
[03:10.450 --> 03:12.450] Um, that's all I think.
[03:12.450 --> 03:14.450] All right, everyone, please have a great meal.
[03:14.450 --> 03:15.450] Thank you.
[03:15.450 --> 03:19.450] And let me know any time if I can make your experience even more enjoyable.
[03:22.450 --> 03:24.450] He's an interesting guy.
[03:24.450 --> 03:25.450] Yes.
[03:25.450 --> 03:29.450] This resort is labelled in the resort guide as a multicultural dining experience.
[03:30.450 --> 03:32.450] Well, it certainly is an experience.
[03:33.450 --> 03:36.450] So, Albon, what is it you do for a living?
[03:36.450 --> 03:39.450] Oh, architecture. But I'm mostly retired.
[03:39.450 --> 03:42.450] Now I run a journal out of Los Angeles called Glass Pane.
[03:42.450 --> 03:43.450] You're French?
[03:43.450 --> 03:46.450] Oh, no. Swiss first, from Geneva.
[03:46.450 --> 03:48.450] Then Paris, then L.A.
[03:49.450 --> 03:52.450] I'm from London first. Then Paris.
[03:52.450 --> 03:53.450] We met there.
[03:53.450 --> 03:54.450] That's how we met.
[03:54.450 --> 03:57.450] But I couldn't get work there, so I made Albon move with me.
[03:58.450 --> 04:00.450] And what do you do?
[04:00.450 --> 04:03.450] Well, I'm an actress, of course.
[04:03.450 --> 04:05.450] Oh, really? She's great.
[04:06.450 --> 04:07.450] For commercials.
[04:07.450 --> 04:09.450] I have a contract with an L.A. company.
[04:09.450 --> 04:11.450] They've been grooming me.
[04:11.450 --> 04:13.450] I specialize in failing naturally.
[04:14.450 --> 04:17.450] What does that mean? Failing naturally?
[04:18.450 --> 04:22.450] Finding a natural-seeming way to fail at any given task.
[04:22.450 --> 04:24.450] In each of the commercials that I'm in,
[04:24.450 --> 04:27.450] I'm the one who simply can't go on without the product.
[04:27.450 --> 04:29.450] It's ridiculous for me not to have the product.
[04:30.450 --> 04:31.450] Okay.
[04:31.450 --> 04:32.450] Show them.
[04:32.450 --> 04:33.450] No.
[04:33.450 --> 04:34.450] No, you should.
[04:34.450 --> 04:35.450] Yeah.
[04:35.450 --> 04:36.450] Please.
[04:36.450 --> 04:37.450] Do you want to see?
[04:37.450 --> 04:38.450] I want to see.
[04:38.450 --> 04:39.450] Here.
[04:42.450 --> 04:43.450] She's amazing.
[04:56.660 --> 05:02.450] I just...
[05:04.450 --> 05:05.450] I...

Standalone Faster-Whisper operation finished in: 38 seconds

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>pause
Drücken Sie eine beliebige Taste . . .

[Emulgator]

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>whisper.exe "C:\_PROG\! Subtitle Tools\! Testfile VoodooFX 2023 05 18\test_ffmpeg6.wav" --language en --model "large" --compute_type=float16

Standalone Faster-Whisper r117 running on: CUDA

2023-05-18 15:09:37.3092070 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1671 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.

[00:00.760 --> 00:02.760] Feeling inspired yet?
[00:02.760 --> 00:03.760] No.
[00:03.760 --> 00:08.890] Thank you.
[00:08.890 --> 00:10.890] I thought you said you were hungry.
[00:12.890 --> 00:17.890] There's a boat tour of the Trakla Island formations this afternoon.
[00:17.890 --> 00:22.890] I was thinking we could go on that and make reservations in town for dinner.
[00:23.890 --> 00:25.890] You could try the Chinese place.
[00:25.890 --> 00:28.890] I don't think I'd survive another dinner in town.
[00:29.890 --> 00:31.890] Even the idea that...
[00:31.890 --> 00:33.890] Does anyone think it's a real town?
[00:36.890 --> 00:38.890] Why would they have a Chinese place?
[00:43.280 --> 00:46.280] Is it okay if I go? I'll meet you on the beach.
[00:47.280 --> 00:49.280] Yeah, sure.
[01:22.270 --> 01:24.270] Someone's making a statement.
[01:24.270 --> 01:26.270] One of the locals, I guess.
[01:29.270 --> 01:31.270] What do you think he's trying to say?
[01:31.270 --> 01:35.270] He's saying that he wants to put a long knife right through her.
[01:35.270 --> 01:40.270] And after you die, he'll hang your body at the airport to scare off the other tourists.
[01:42.270 --> 01:44.270] Seems a bit extreme.
[01:46.270 --> 01:49.270] The Latokans are a melodramatic people.
[01:54.740 --> 01:56.740] I loved your book.
[01:58.740 --> 01:59.740] Sorry?
[02:00.740 --> 02:03.740] You're James Foster. I loved your book.
[02:06.740 --> 02:09.740] Sorry, is that good? I don't mean to put you in the spot.
[02:09.740 --> 02:11.740] No, thank you.
[02:11.740 --> 02:13.740] It's just, um...
[02:13.740 --> 02:15.740] Not a lot of people read my book.
[02:15.740 --> 02:17.740] I'm Gabby Bauer.
[02:17.740 --> 02:19.740] I'm James Foster.
[02:21.740 --> 02:22.740] Alvin!
[02:25.520 --> 02:27.520] This is James Foster.
[02:27.520 --> 02:29.520] Hi, nice to meet you. Albon Bauer.
[02:29.520 --> 02:30.520] Pleasure.
[02:30.520 --> 02:32.520] He wrote your book that I love, The Variable Sheath.
[02:32.520 --> 02:34.520] Oh, yeah, I remember.
[02:34.520 --> 02:36.520] I thought it was brilliant.
[02:36.520 --> 02:37.520] Yes.
[02:37.520 --> 02:41.520] James, do you think I could convince you to join us for dinner this evening?
[02:42.520 --> 02:46.520] I've been seeing you around the resort for a few days now and I would love to get to know you.
[02:46.520 --> 02:49.520] We have a reservation tonight at Yang's.
[03:00.450 --> 03:02.450] Yeah, it was a good...
[03:04.450 --> 03:06.450] ...learning experience.
[03:06.450 --> 03:07.450] All right.
[03:07.450 --> 03:10.450] Is there anything else I can get you?
[03:10.450 --> 03:12.450] Um, that's all I think.
[03:12.450 --> 03:14.450] All right, everyone, please have a great meal.
[03:14.450 --> 03:15.450] Thank you.
[03:15.450 --> 03:19.450] And let me know any time if I can make your experience even more enjoyable.
[03:22.450 --> 03:24.450] He's an interesting guy.
[03:24.450 --> 03:25.450] Yes.
[03:25.450 --> 03:29.450] This resort is labelled in the resort guide as a multicultural dining experience.
[03:30.450 --> 03:32.450] Well, it certainly is an experience.
[03:33.450 --> 03:36.450] So, Albon, what is it you do for a living?
[03:36.450 --> 03:39.450] Oh, architecture. But I'm mostly retired.
[03:39.450 --> 03:42.450] Now I run a journal out of Los Angeles called Glass Pane.
[03:42.450 --> 03:43.450] You're French?
[03:43.450 --> 03:46.450] Oh, no. Swiss first, from Geneva.
[03:46.450 --> 03:48.450] Then Paris, then LA.
[03:49.450 --> 03:52.450] I'm from London first. Then Paris.
[03:52.450 --> 03:53.450] We met there.
[03:53.450 --> 03:54.450] That's how we met.
[03:54.450 --> 03:57.450] But I couldn't get work there, so I made Albon move with me.
[03:58.450 --> 04:00.450] And what do you do?
[04:00.450 --> 04:03.450] Well, I'm an actress, of course.
[04:03.450 --> 04:05.450] Oh, really? She's great.
[04:06.450 --> 04:07.450] For commercials.
[04:07.450 --> 04:09.450] I have a contract with an LA company.
[04:09.450 --> 04:11.450] They've been grooming me.
[04:11.450 --> 04:13.450] I specialize in failing naturally.
[04:14.450 --> 04:17.450] What does that mean? Failing naturally?
[04:18.450 --> 04:22.450] Finding a natural-seeming way to fail at any given task.
[04:22.450 --> 04:24.450] In each of the commercials that I'm in,
[04:24.450 --> 04:27.450] I'm the one who simply can't go on without the product.
[04:27.450 --> 04:29.450] It's ridiculous for me not to have the product.
[04:30.450 --> 04:31.450] Okay.
[04:31.450 --> 04:32.450] Show them.
[04:32.450 --> 04:33.450] No.
[04:33.450 --> 04:34.450] No, you should.
[04:34.450 --> 04:35.450] Yeah.
[04:35.450 --> 04:36.450] Please.
[04:36.450 --> 04:37.450] Do you want to see?
[04:37.450 --> 04:38.450] I want to see.
[04:38.450 --> 04:39.450] Here.
[04:42.450 --> 04:43.450] She's amazing.
[04:56.660 --> 05:02.450] I just...
[05:04.450 --> 05:05.450] I...

Standalone Faster-Whisper operation finished in: 21 seconds

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>pause
Drücken Sie eine beliebige Taste . . .

[Emulgator]

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>whisper.exe "C:\_PROG\! Subtitle Tools\! Testfile VoodooFX 2023 05 18\test_ffmpeg6.wav" --language en --model "large" --compute_type=int8

Standalone Faster-Whisper r117 running on: CUDA

2023-05-18 15:11:27.5628509 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1671 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.

[00:00.760 --> 00:02.760] Feeling inspired yet?
[00:02.760 --> 00:08.890] No, thank you.
[00:08.890 --> 00:10.890] I thought you said you were hungry.
[00:12.890 --> 00:17.890] There's a boat tour of the Trakla Island formations this afternoon.
[00:17.890 --> 00:22.890] I was thinking we could go on that and make reservations in town for dinner.
[00:23.890 --> 00:25.890] You could try the Chinese place.
[00:25.890 --> 00:28.890] I don't think I'd survive another dinner in town.
[00:29.890 --> 00:31.890] Even the idea that...
[00:31.890 --> 00:33.890] Does anyone think it's a real town?
[00:36.890 --> 00:38.890] Why would they have a Chinese place?
[00:43.280 --> 00:46.280] Is it okay if I go? I'll meet you on the beach.
[00:47.280 --> 00:49.280] Yeah, sure.
[01:22.270 --> 01:24.270] Someone's making a statement.
[01:24.270 --> 01:26.270] One of the locals, I guess.
[01:29.270 --> 01:31.270] What do you think he's trying to say?
[01:31.270 --> 01:35.270] He's saying that he wants to put a long knife right through her.
[01:35.270 --> 01:40.270] And after you die, he'll hang your body at the airport to scare off the other tourists.
[01:42.270 --> 01:44.270] Seems a bit extreme.
[01:46.270 --> 01:49.270] The Latokans are a melodramatic people.
[01:54.740 --> 01:56.740] I loved your book.
[01:58.740 --> 01:59.740] Sorry?
[02:00.740 --> 02:03.740] You're James Foster. I loved your book.
[02:06.740 --> 02:09.740] Sorry, is that good? I don't mean to put you in the spot.
[02:09.740 --> 02:11.740] No, thank you.
[02:11.740 --> 02:13.740] It's just, um...
[02:13.740 --> 02:15.740] Not a lot of people read my book.
[02:15.740 --> 02:17.740] I'm Gabby Bauer.
[02:17.740 --> 02:19.740] I'm James Foster.
[02:21.740 --> 02:22.740] Alvin!
[02:25.520 --> 02:27.520] This is James Foster.
[02:27.520 --> 02:29.520] Hi, nice to meet you. Albon Bauer.
[02:29.520 --> 02:30.520] Pleasure.
[02:30.520 --> 02:32.520] He wrote your book that I love, The Variable Sheath.
[02:32.520 --> 02:34.520] Oh, yeah, I remember.
[02:34.520 --> 02:36.520] I thought it was brilliant.
[02:36.520 --> 02:37.520] Yes.
[02:37.520 --> 02:42.520] James, do you think I could convince you to join us for dinner this evening?
[02:42.520 --> 02:46.520] I've been seeing you around the resort for a few days now and I would love to get to know you.
[02:46.520 --> 02:49.520] We have a reservation tonight at Yang's.
[03:00.450 --> 03:02.450] Yeah, it was a good...
[03:04.450 --> 03:06.450] learning experience.
[03:06.450 --> 03:07.450] All right.
[03:07.450 --> 03:10.450] Is there anything else I can get you?
[03:10.450 --> 03:12.450] Um, that's all I think.
[03:12.450 --> 03:14.450] All right, everyone, please have a great meal.
[03:14.450 --> 03:15.450] Thank you.
[03:15.450 --> 03:20.450] And let me know any time if I can make your experience even more enjoyable.
[03:22.450 --> 03:24.450] He's an interesting guy.
[03:24.450 --> 03:25.450] Yes.
[03:25.450 --> 03:30.450] This resort is labeled in the resort guide as a multicultural dining experience.
[03:30.450 --> 03:33.450] Well, it certainly is an experience.
[03:33.450 --> 03:36.450] So, Albon, what is it you do for a living?
[03:36.450 --> 03:39.450] Oh, architecture. But I'm mostly retired.
[03:39.450 --> 03:42.450] Now I run a journal out of Los Angeles called Glass Pane.
[03:42.450 --> 03:43.450] You're French?
[03:43.450 --> 03:46.450] Oh, no. Swiss first, from Geneva.
[03:46.450 --> 03:48.450] Then Paris, then LA.
[03:49.450 --> 03:52.450] I'm from London first. Then Paris.
[03:52.450 --> 03:53.450] We met there.
[03:53.450 --> 03:54.450] That's how we met.
[03:54.450 --> 03:57.450] But I couldn't get work there, so I made Albon move with me.
[03:58.450 --> 04:00.450] And what do you do?
[04:00.450 --> 04:03.450] Well, I'm an actress, of course.
[04:03.450 --> 04:05.450] Oh, really? She's great.
[04:06.450 --> 04:07.450] For commercials.
[04:07.450 --> 04:09.450] I have a contract with an LA company.
[04:09.450 --> 04:11.450] They've been grooming me.
[04:11.450 --> 04:13.450] I specialize in failing naturally.
[04:14.450 --> 04:17.450] What does that mean? Failing naturally?
[04:17.450 --> 04:22.450] Finding a natural-seeming way to fail at any given task.
[04:22.450 --> 04:24.450] In each of the commercials that I'm in,
[04:24.450 --> 04:27.450] I'm the one who simply can't go on without the product.
[04:27.450 --> 04:29.450] It's ridiculous for me not to have the product.
[04:30.450 --> 04:31.450] Okay.
[04:31.450 --> 04:32.450] Show them.
[04:32.450 --> 04:33.450] No.
[04:33.450 --> 04:34.450] No, you should.
[04:34.450 --> 04:35.450] Yeah.
[04:35.450 --> 04:36.450] Please.
[04:36.450 --> 04:37.450] Do you want to see?
[04:37.450 --> 04:38.450] I want to see.
[04:38.450 --> 04:39.450] Here.
[04:42.450 --> 04:43.450] She's amazing.
[04:56.660 --> 05:02.450] I just...
[05:04.450 --> 05:05.450] I...

Standalone Faster-Whisper operation finished in: 38 seconds

C:\_PROG\! Subtitle Tools\Whisper-Faster_Win.x64_2023.05.13.b117_GPU>pause
Drücken Sie eine beliebige Taste . . .

[Emulgator]

Tiny differences, float16 was quicker then int8, ffmpeg6.wav float16 was quickest.
.aac was slower.
As I thought: Precision pays off ?
After all it is about cross-comparing spectrograms,
and tiny losses in density differences can lead to costlier because more exhausting searches.

Alle these on model large, only this was available on that system for now,
and I did not want to let that one go into internet again after being bluescreened twice
by the last 2 forced M$ Win10 updates, the last time leaving me with unrepairable system.

I was not aware that M$ had decided the unspeakable from W10 r1803 on:
NOT to perform any registry backups anymore by default...
To save HDD space. WTF?

https://learn.microsoft.com/en-us/troubleshoot/windows-client/deployment/system-registry-no-backed-up-regback-folder

NOT to perform any system restore points anymore by default...
Even deleting manually made ones. WTF?

https://answers.microsoft.com/en-us/windows/forum/all/windows-10-restore-points-are-being-deleted/4ea28db7-105e-420d-924e-b605ea095ab1

https://answers.microsoft.com/en-us/windows/forum/all/why-is-system-restore-off-by-default-for-many/3049a3ac-f77f-4bff-af19-f6fd51184185

https://learn.microsoft.com/en-us/troubleshoot/windows-client/deployment/system-restore-points-disabled

[VoodooFX]

I need and asked for medium model and srt files. [uploaded somewhere like Wetransfer] :)
But I'll check these large tests too. [saved, so those posts are not needed anymore]


Ah, well, 8bit vs. 16bit can make all the difference !
There are many other quantization types, run --verbose to see all supported on your device.


I give a .wav 32bit float decode from the DVD .ac3 track
Don't. Use original audio.


r103 GPU from 04.05.2023
r103 GPU from 17.05.2023
r117 GPU from 17.05.2023

All versions have their uses and guess differently.

But there was only one "b103" version. Why you need old version?


Will have to talk Nikse into having 3 editor tabs in SubtitleEdit, muhahaha ;-)

You can open other SE instances.


Tiny differences, float16 was quicker then int8
Benchmarks on short files doesn't mean much.

As I thought: Precision pays off ?

Did you meant compute types? I'm not sure how they correlate to accuracy or speed. So far for me int8 looks best when float32 is fastest. Some users reported opposite effects.

EDIT:
Or did you meant something with audio? That "wav" test file is only to check some quirks with FFmpeg v6. For some reason results from v6 can be worse or different, it affects int types.

[Emulgator]

Originally Posted by Emulgator View Post
r103 GPU from 04.05.2023
r103 GPU from 17.05.2023
r117 GPU from 17.05.2023

All versions have their uses and guess differently.
But there was only one "b103" version. Why you need old version?

These were my test dates, not the .exe dates.
Sorry for the ambiguity.

Originally Posted by Emulgator View Post
I give a .wav 32bit float decode from the DVD .ac3 track
Don't. Use original audio.

This (in this case .ac3) will have to be decoded to uncompressed before FFTing anyway,
and I want to be in control about the decoding precision.

[VoodooFX]

@Emulgator Could you do few more tests on aac with CUDA: "--language en --model=large --compute_type=float32" and "--language en --model=medium --compute_type=float16"?
[Results in the same form like you did previous tests.]

Btw, for your own tests you can try "--beam_size=5", it's slower but should produce better results.

[Emulgator]

Soon (...still trying to get my main system up and running as before)

[StainlessS]

These are basically the two that I've tried [only on a few occasions, maybe 5 or 6],

Whisper-Faster\whisper.exe --model_dir ".\_models" --language en --model "large-v2" ".\audio.wav"

Whisper-Faster\whisper.exe --model_dir ".\_models" --language en --model "large-v2" ".\audio.dts"

I just use above to paste into command line.
Its weird how some subs are flagged <during non talkative periods> maybe up to a minute ahead of the actual start of speech, and stop pretty much at end of speech.
Also,

EDIT: I did one recently on music video {live gig} containing Eng and Spanish, some of the Spanish speech
came out in Spanish, some of it came out translated to English. {& Eng came out Eng}.

EDIT: A few hiccoughs can occur, in one instance, the name "Hiller" was transformed throughout video, into "Hitler" :)
{Perhaps "Captain Steve Hitler" rings a bell}

EDIT: I wonder if its worth giving it a go on some Star Trek with lots of Klingon, I bet that some of that stuff was
scanned during A.I. training, might auto convert to earthling English.
Spanish/English thingy is Odd.

[VoodooFX]

whisper.exe --model_dir ".\_models" --language en --model "large-v2" ".\audio.wav"

I think you are using an old version, current is r134.6.
model_dir parameter is redundant in your example, at least in latest version.

...up to a minute ahead of the actual start of speech

Probably in latest version you'll not see that.

Spanish/English thingy is Odd.
Not odd, Whisper models doesn't support transcription of multilingual audio. You can try to process it twice, first with English then with Spanish parameter.

[SaurusX]

Does this have the word-level timing feature of the original Whisper? I've yet to find a version of this with that word-level timing, CUDA, and the ability to use the HF models.

[VoodooFX]

Does this have the word-level timing feature of the original Whisper? I've yet to find a version of this with that word-level timing, CUDA, and the ability to use the HF models.

Yes, it's enabled by default. It includes all those things.

[SaurusX]

But the examples shown in the OP screenshot and by Emulgator do not show this. They're all specific second-based intervals that are seemingly locked into a particular fraction-of-a-second start point.

[VoodooFX]

But the examples shown in the OP screenshot and by Emulgator do not show this. They're all specific second-based intervals that are seemingly locked into a particular fraction-of-a-second start point.

No idea what you mean by that, it shows same thing as original Whisper.
Post your screenshot of what your "original Whisper" shows.

[SaurusX]

No idea what you mean by that, it shows same thing as original Whisper.
Post your screenshot of what your "original Whisper" shows.

"Original Whisper" as in from OpenAI's github repo.

https://github.com/openai/whisper

When using their CLI I add "--word_timestamps True" and the timing of each sentence or segment is more precise. To the fraction of a second usually, though it can hiccup.

I'll add some screenshots later today when I get to my computer.

[VoodooFX]

When using their CLI I add "--word_timestamps True" and the timing of each sentence or segment is more precise.
Yeap, it includes that. In the first post is the old screenshot.

[SaurusX]

I was getting a dll error saying that I was missing "cudnn_ops_infer64_8.dll" and to put it into my system path. I downloaded it from this zip and dropped into by CUDA bin folder.

https://developer.download.nvidia.com/compute/redist/cudnn/v8.3.0/

The word_timestamps is working as you said it would be. Doing other tests now with the different model sizes.

http://i.ibb.co/pW5yrcr/Whisper-faster.jpg
OK, that's fast. Using the large-v2 model!

http://i.ibb.co/jkDf0mF/whisper-medium-en.jpg
Using the medium.en model.

[StainlessS]

I think you are using an old version, current is r134.6.
Yeah, probably bout 5 weeks since update.

Not odd, Whisper models doesn't support transcription of multilingual audio. ...

Well whether it supports it or not, some (but not all) of it (Spanish) was translated to English.

[VoodooFX]

Compiled Linux and Mac OS X executables. Enjoy it.

[xarzu]

I got an error which, I assume, is due to the fact that my input is a 4 hour long video, or maybe I have too many windows open, or both.
https://www.likablelogic.org/images/VUE.JS/whisper-faster.png

[Emulgator]

I can only suggest to split long files into multiple jobs, it helps a great deal with everything whisper.
For sequences which are hard to guess: restrict a whisper job to only that part, and repeats or overlooked, bad guesses can be mended.

[VoodooFX]

I got an error which, I assume, is due to the fact that my input is a 4 hour long video, or maybe I have too many windows open, or both.

No, that's irrelevant.
From the screenshot you can see that it's out of the video memory.
How much of VRAM there is in your GPU, and what is the model of your GPU?

[VoodooFX]

Released Standalone Faster-Whisper-XXL (https://github.com/Purfview/whisper-standalone-win/discussions/231) with the additional features.
You want to use them on movies or noisy podcasts containing music & ect.

[Yosho]

I could use some help with the syntax if you wouldn't mind..

So far I've got C:\Users\Downloads\Faster-Whisper-XXL_r192.3.4_windows\Faster-Whisper-XXL\faster-whisper-xxl.exe "C:\Users\Downloads\blah.mkv" --language English -m large -d CPU -o "C:\Users\Downloads" -f srt --task transcribe

Additionally, is there a way to include this in subtitle edit by chance? Or would it need to be put in by the programmer themselves of the app?
Thanks for the help!

[VoodooFX]

I could use some help with the syntax if you wouldn't mind..

I don't mind.

Additionally, is there a way to include this in subtitle edit by chance? Or would it need to be put in by the programmer themselves of the app?

That you should ask the developer of Subtitle Edit.

[Yosho]

I don't mind.
Great, thanks! What am I missing from the commands I posted to run it to first download the _models and then do the transcription with the whisper?

So far I've got C:\Users\Downloads\Faster-Whisper-XXL_r192.3.4_windows\Faster-Whisper-XXL\faster-whisper-xxl.exe "C:\Users\Downloads\blah.mkv" --language English -m large -d CPU -o "C:\Users\Downloads" -f srt --task transcribe

Thank you for your help!

[VoodooFX]

What am I missing from the commands...

No idea what you are missing there, you tell me what you are missing... only the input is needed to run it.

I can tell you what I'm missing - I don't see you posting your problem, if you have any.

[Yosho]

No idea what you are missing there, you tell me what you are missing... only the input is needed to run it.

I can tell you what I'm missing - I don't see you posting your problem, if you have any.

I figured it out.
I now have subtitles. They are out of sync, and needing to be synced to the dialog.
Do you have something you regularly use for automatic subtitle syncing, or advice on what's best in your educated opinion to use for automatic subtitle syncing?

[VoodooFX]

I now have subtitles. They are out of sync, and needing to be synced to the dialog.

For me it produces mostly in sync results, can you share an audio sample where it's out of sync?


Do you have something you regularly use for automatic subtitle syncing, or advice on what's best in your educated opinion to use for automatic subtitle syncing?

There is no perfect automatic subtitle syncing.

[VoodooFX]

If someone doesn't have fast CUDA GPU, you can use one for free in Colab.

EDIT: Look at the first post.

[TR-9970X]

Thanks for directing me here:-

So I have been spending a LOT of time with the 6 episode near 5 hour's of Das Boot.

Have downloaded so many variants, I'm getting lost & confused.

So to cut a very long story short, I got 2 different sets, as one was 1080p. and the 720p had the good dubbed engish audio, but each episode was minutes shorter, so I had to overcome that issue, and did, the audio overdub is preety damn good :)

So once I trimmed all the episodes of the useless intro, outro & recaps, I then wanted to transcribe the dubbed english audio. to get matching subtitles. as the original audio & english subs are crap.

I tried Whisper @ Google Colab, and that did a pretty good job on the majority, but there a few really tricky bits that I want to get as correct as I can, and this one I've sent you is a little song, either in French or German. and I just can't quite get it.

I tried to set up WhisperX on my PC, but I got stuck at some error that I couldn't get any help on. so I gave up.

Using SE, the only model that came close to getting this clip, was const-me large. ALL the other's didn't find anything :(

I'd really like to be able to post my final compilation somewhere for anyone that wants a good "ENGLISH" copy of Das Boot, the massive near 5 hours of it.

Here's the file, I sent a video, so you can see what you're dealing with.

https://www.mediafire.com/file/s8kbobp1sv30p5v/Das+Boot+(1985)+S01E01+la+belle+song.7z/file

BTW, I figured out how to use waveforms, what a godsend that is :)

Cheers & thanks again.

[VoodooFX]

https://www.mediafire.com/file/s8kbobp1sv30p5v/Das+Boot+(1985)+S01E01+la+belle+song.7z/file


The command used:

-m large-v2 --vad_method pyannote_v3 -o source --standard --max_gap 1 --realign --ff_vocal_extract mb-roformer --multilingual true --batched



Subs:

1
00:00:01,076 --> 00:00:01,701
Exactly.

2
00:00:03,608 --> 00:00:04,080
Me too.

3
00:00:04,705 --> 00:00:09,019
Avec les marins s'attendent, les ponts
cassant leur aveugle.

4
00:00:09,419 --> 00:00:14,500
Moi, je sais bien ce qui leur manque à
tous ces mondes et leurs généraux.

5
00:00:14,859 --> 00:00:21,917
Allez, je m'appelle la reine, la reine du
pays de la Rochelle.

6
00:00:22,120 --> 00:00:29,492
Côle bleu, sentinelle, m'appelle... M
'appelle la reine de la Rochelle.

7
00:00:32,447 --> 00:00:36,042
Come on now, he's too young to play games
with you, Monique, huh?




I'd really like to be able to post my final compilation somewhere for anyone that wants a good "ENGLISH" copy of Das Boot


Why? There are retail English subs for it.

[TR-9970X]

The command used:

-m large-v2 --vad_method pyannote_v3 -o source --standard --max_gap 1 --realign --ff_vocal_extract mb-roformer --multilingual true --batched



Subs:

1
00:00:01,076 --> 00:00:01,701
Exactly.

2
00:00:03,608 --> 00:00:04,080
Me too.

3
00:00:04,705 --> 00:00:09,019
Avec les marins s'attendent, les ponts
cassant leur aveugle.

4
00:00:09,419 --> 00:00:14,500
Moi, je sais bien ce qui leur manque à
tous ces mondes et leurs généraux.

5
00:00:14,859 --> 00:00:21,917
Allez, je m'appelle la reine, la reine du
pays de la Rochelle.

6
00:00:22,120 --> 00:00:29,492
Côle bleu, sentinelle, m'appelle... M
'appelle la reine de la Rochelle.

7
00:00:32,447 --> 00:00:36,042
Come on now, he's too young to play games
with you, Monique, huh?





Why? There are retail English subs for it.

Of course I'm guessin' that's with your Pro version ??

Can it do translations??

I let Google translate, and now I should be able to add that.

I have searched far & wide, and all the English subtitles are crap, the dubbed english transcript is pretty much spot on.

And the 6 part Das Boot is pretty rare, as well.

So you've all but convinced me that your Pro version is pretty damn good.

So, not to be a pain, but how do I get it, how much is it going to cost me, and how to integrate it in SE.

Oh, and thanks for doing that little job for me so quickly:)

[VoodooFX]

Of course I'm guessin' that's with your Pro version ??

Can it do translations??

I let Google translate, and now I should be able to add that.

So, not to be a pain, but how do I get it, how much is it going to cost me, and how to integrate it in SE.

Yes.
Yes, it does translation to English.
Its translation is better than Google translate.
Look there: https://github.com/Purfview/whisper-standalone-win/discussions/456
Just copy it to the same folder where the regular version is in SE. (Delete the old files there, excluding the models)


I have searched far & wide, and all the English subtitles are crap, the dubbed english transcript is pretty much spot on.

The retail subs are for the original German audio, I guess you're comparing them to the dubbed audio, which is different from the original.

[TR-9970X]

Yes.
Yes, it does translation to English.
Its translation is better than Google translate.
Look there: https://github.com/Purfview/whisper-standalone-win/discussions/456
Just copy it to the same folder where the regular version is in SE. (Delete the old files there, excluding the models)




The retail subs are for the original German audio, I guess you're comparing them to the dubbed audio, which is different from the original.

OK, so if you're minimum "donation" is £50, that calculates to nearly AU$100...is that correct ??

From what I've seen, the english that comes with the video, isn't that good, and the subtitles don't match either.

The dubbed english was done by the actors that were in the movie, so it's pretty good.

[VoodooFX]

OK, so if you're minimum "donation" is £50, that calculates to nearly AU$100...is that correct ??
Yes, it should be around that.

[TR-9970X]

Yes, it should be around that.

OK, well, I'm going to have to give that some serious thought.

Regards.

[TR-9970X]

Yes, it should be around that.

Hi Voodoo,

Well, I have been wasting my time trying to setup various Whisper versions, and even after following the YouTube instructions as best I can, the end result is pretty much the same, they don't work :(

And it's hard to get support when a lot of the clips are 12 months old, or older....

So I think that you have proven to me what your build can do, I should just "bite the bullet", and donate to you, to get the Pro version.

I'm pretty sure you will provide good support, if I have any issues, or need some experienced assistance.

So I just want to confirm, that the minimum "donation" to be eligible for Pro is £50, is that correct ??

Regards

[VoodooFX]

Hi Voodoo,

Well, I have been wasting my time trying to setup various Whisper versions, and even after following the YouTube instructions as best I can, the end result is pretty much the same, they don't work :(

Hi. That's why I made it, because the original Whisper and other implementations weren't good enough for me.



So I think that you have proven to me what your build can do, I should just "bite the bullet", and donate to you, to get the Pro version.

I'm pretty sure you will provide good support, if I have any issues, or need some experienced assistance.

So I just want to confirm, that the minimum "donation" to be eligible for Pro is £50, is that correct ??

The Pro version has some extra features, if you want them, it's £50 at the moment.

[TR-9970X]

hi. That's why i made it, because the original whisper and other implementations weren't good enough for me.




The pro version has some extra features, if you want them, it's £50 at the moment.

sold !!!

[VoodooFX]

sold !!!
Thanks for the donation, enjoy the Pro version! :thanks:

[TR-9970X]

Thanks for the donation, enjoy the Pro version! :thanks:

OK, successfully downloaded & unpacked.

Turned out to be AU$103.21.

So you have already mentioned how to add this to SE,

Just copy it to the same folder where the regular version is in SE. (Delete the old files there, excluding the models)


Are there any other instructions?

Be aware, that I could end up asking quite a few "stupid" questions, until I get the hang of it, so sorry in advance.

[VoodooFX]

Are there any other instructions?

Be aware, that I could end up asking quite a few "stupid" questions, until I get the hang of it, so sorry in advance.

No.
There are no stupid questions, as it's a pretty technically sophisticated app. :)

[TR-9970X]

No.
There are no stupid questions, as it's a pretty technically sophisticated app. :)

OK, here's my first "question's". Since sending this I have figured out most of my questions :)

I've just run it for the first time running at your defaults, dragging the audio file to a shortcut on the Desktop, it downloaded the medium model, so now I know where they go, and what the directory looks like :)

How to copy the models I downloaded for your app, within SE ?? sorted

Hopefully I don't need to download them again, although that would ensure they were the correct ones. don't

To change the transcription commands. is that here :- confirm this, tho :)

:: Start processing
"%dp%faster-whisper-xxl.exe" %file_list% -pp -o source --batch_recursive --check_files --standard -f json srt -m medium

And just to confirm, adding this to SE so it can be run from there (which probably isn't necessary) (see attached screenshot)

https://imgur.com/eyLGzwt

Does it go in Users\Appdata\Roaming, or Program Files.? also sorted

That's all for now. :rolleyes:

PS:- It would nice to have SE display that it's now the Pro version.

EDIT:- OK, I have done several passes on a Das Boot audio track, and it's doing a pretty good job, but there might be some more advanced commands that might improve it even more.

It's miss pronouncing a few words, but nothing a little manual editing won't fix.

Can a form of SDH sub's be generated, for example if I use const-me large, it does, to a degree.

[VoodooFX]

Can a form of SDH sub's be generated, for example if I use const-me large, it does, to a degree.

Forget that const-me, it's a subpar implementation and abandonware.
It can, but to get "SDH" you need to disable some quality settings/safety measures, basically you are asking for hallucinations.

Use, --suppress_tokens="" or --suppress_tokens=None, both should've different behavior at the low level. [I don't remember differences, empty list [""] is not intended behaviour, but there were reports that it was useful for something]

Then you may want to disable VAD audio preprocess, --vad_filter=false, and don't enable other audio preprocess.

Then probably you want to enable -hst=2 to combat hallucination.



Hopefully I don't need to download them again

You can set --model_dir to the path of a models folder if you don't want it to look in the default location.


And just to confirm, adding this to SE so it can be run from there (which probably isn't necessary) (see attached screenshot)

That site doesn't work for me. Anyway, about SE, ask at the SE thread.

[TR-9970X]

Forget that const-me, it's a subpar implementation and abandonware.
It can, but to get "SDH" you need to disable some quality settings/safety measures, basically you are asking for hallucinations.

Use, --suppress_tokens="" or --suppress_tokens=None, both should've different behavior at the low level. [I don't remember differences, empty list [""] is not intended behaviour, but there were reports that it was useful for something]

Then you may want to disable VAD audio preprocess, --vad_filter=false, and don't enable other audio preprocess.

Then probably you want to enable -hst=2 to combat hallucination.

Excellent, I will give that a try tomorrow



You can set --model_dir to the path of a models folder if you don't want it to look in the default location.



That site doesn't work for me. Anyway, about SE, ask at the SE thread.

I've been able to figure out where the models go, and to get Pro working within SE, was pretty easy once I checked out the folder & files within the Subtitle Edit default location.

I am watching Pt 5 of Das Boot, in which I transcribed the audio track with 5 different models, Medium, Large v1, v2 & v3, and each one has slightly different results, so I will be able to go thru and use the best or most correct subtitle for each line, tedious, but accurate.

I'm just being VERY particular with this movie/series.

So with the drag & drop onto the desktop shortcut, can the default command line be changed, like using the Advanced command line used in SE ??

Although I will probably prefer to use SE, it would be nice to customise the drag & drop process.

So now that I have Pro, I can run several models of the transcription, and get the subs spot on, and it's interesting to see how much the GPU is used during the process....

Still got a lot of testing to do, but so far, pretty happy :)

Cheers

[VoodooFX]

So with the drag & drop onto the desktop shortcut, can the default command line be changed, like using the Advanced command line used in SE ??
Although I will probably prefer to use SE, it would be nice to customise the drag & drop process.


Of course, the commands can be changed, added, or removed however you like.
Like I said before, be aware that on some files SE doesn't work as expected, the results can be worse then.

[TR-9970X]

Of course, the commands can be changed, added, or removed however you like.
Like I said before, be aware that on some files SE doesn't work as expected, the results can be worse then.

Doom9 has been down for most of today (my time)

Hi, so I've tried to get some SDH stuff working, but I don't think it's producing what I thought it should..the only thing I think I noticed where a lot of "speech marks" (these things ")

Here's the command I used, it's probably quite wrong :-

"%dp%faster-whisper-xxl.exe" %file_list% -pp -o source --batch_recursive --check_files --standard --vad_method pyannote_v3 -o source --standard --max_gap 1 -hst 2 -ct float16 --ff_vocal_extract mb-roformer --realign -f srt -m large-v2 --language en -suppress_tokens"" --vad_filter=false

And another question, is there a way to transcribe foreign language parts, into english, or the language of the part ?? (Would you need to know what the language was to start with?)

OR, if you transcribed the video to catch the english parts, then ran a different script to capture the foreign parts ??

Regards.

[TR-9970X]

Got an error whilst trying to transcribe a long ac3.

Audio filtering is in progress...
Estimating duration from bitrate, this may be inaccurate
Estimating duration from bitrate, this may be inaccurate
MB-RoFormer model running on CUDA: 1% | 31/2927 | 11:34<<18:00:48

Traceback (most recent call last):
File "__main__.py", line 212, in ffmpeg_audio
File "faster_whisper\roformer_infer.py", line 234, in RoFormer_separator
File "faster_whisper\roformer_infer.py", line 83, in demix_track
torch.AcceleratorError: CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

Press any key to continue . . .

[VoodooFX]

I noticed where a lot of "speech marks" (these things ")

I don't know what that means.
Anyway, remove ff_vocal_extract, what "SDH" do you expect when all non-voice is removed from the audio. :)

And I think, maybe you need to use one from these too: -prompt None or --reprompt false or --prompt_reset_on_no_end 0 [a former will disable the latter args]
EDIT: Or maybe there will be no harm in not disabling prompt_reset_on_no_end.


And another question, is there a way to transcribe foreign language parts, into english, or the language of the part ?? (Would you need to know what the language was to start with?)

Try --task translate
The model is not meant to transcribe multi-language audio, those measures are workarounds.

[VoodooFX]

long

Let's not operate with abstractions. What "long" means? What "speech marks" means?

I guess you run out of RAM/VRAM. Try --roformer_vram 6 or other value.

[TR-9970X]

I don't know what that means.
Anyway, remove ff_vocal_extract, what "SDH" do you expect when all non-voice is removed from the audio. :)
And I think, you need to use one from these too: -prompt None or --reprompt false [the former will disable the latter]

OK, will give it a try :)

I don't know what to expect, I was just asking.


Try --task translate
The model is not meant to transcribe multi-language audio, those measures are workarounds.

Lots of question's, sorry.

[TR-9970X]

Let's not operate with abstractions. What "long" means? What "speech marks" means?

I guess you run out of RAM/VRAM. Try --roformer_vram 6 or other value.

By long, nearly 5 hours, 1.3Gb !!!!

I had never heard of "speech marks" until I heard a guy on YouTube saying it.

I used to always call them inverted comma's.... " "

I'm running a 4080 Super, surely there won't be a VRAM issue.

[VoodooFX]

By long, nearly 5 hours

I'm running a 4080 Super, surely there won't be a VRAM issue.

For example, when running mb-roformer on CPU with 3:26:00 long audio, it eats ~28GB RAM.




I had never heard of "speech marks" until I heard a guy on YouTube saying it.

I used to always call them inverted comma's.... " "

I don't know what " " abstraction means too. Please spare me from any abstractions. :)
If you have an issue, please post showing the exact problem, preferably with an audio example to reproduce it.

[TR-9970X]

For example, when running mb-roformer on CPU with 3:26:00 long audio, it eats ~28GB RAM.

OK, so can you please provide the command needed to use the CPU instead of the GPU ?



I don't know what " " abstraction means too. Please spare me from any abstractions. :)
If you have an issue, please post showing the exact problem, preferably with an audio example to reproduce it.

I don't think I've heard this word "abstraction" before.

What I was trying to explain, that when I used one of your commands, it appeared to produce a lot of extra " " throughout the subtitles.

Here's a Google explanation:-

Speech marks, also known as quotation marks or inverted commas, are punctuation marks used to indicate direct speech or quotations in writing.

[VoodooFX]

I don't think I've heard this word "abstraction" before.

Aren't you a native English speaker?
https://en.wikipedia.org/wiki/Abstraction


What I was trying to explain, that when I used one of your commands, it appeared to produce a lot of extra " " throughout the subtitles.
Here's a Google explanation:


I know what quotes are, still, I've no idea what the issue is. Or there is no issue?

OK, so can you please provide the command needed to use the CPU instead of the GPU ?

--voc_device cpu
Why you need it when you have CUDA GPU?

[TR-9970X]

Aren't you a native English speaker?
https://en.wikipedia.org/wiki/Abstraction

Yes, Australian, but in all my years in the workplace, and my small circle of friends, I can safely say that "abstraction" has NEVER been in any conversation or discussion.



I know what quotes are, still, I've no idea what the issue is. Or there is no issue?

Again, I thought I noticed a lot of extra "'s, when I used one of your commands to attempt SDH, that's all.

--voc_device cpu
Why you need it when you have CUDA GPU?

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

Anyway, another day of discovery & learning.

[VoodooFX]

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]

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.


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.


Would increasing the volume of the audio track help ?

Most likely that it would not.



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]

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/yahfak2vt9t0g6d/New_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/l1hv4ia2kp4rffv/Das_6_track2_%255Beng%255D_DELAY_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]

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.cpp/tree/master/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]

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?


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]

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]

I would like you to transcribe the .ac3 file

Sorry, I'm not interested.

[TR-9970X]

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]

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.cpp/tree/master/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]

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.

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] :D

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]

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.

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]

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]

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]

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]

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. :D
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. :D

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. :D
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]

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...

[TR-9970X]

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...

Well, I think you ought to shut up, you're revealing your true colours.

How can you judge that it's not true, that was my objective, and you have taken the word "play" so far out of context.

I use that word as meaning to having a good look at something that needs to be investigated, sorted out, etc.

But when you came up with this rarely used word "abstraction" when I was trying to describe the extra characters that were produced with one of your command's, I knew there was something basic being lost in translation.

[VoodooFX]

Well, I think you ought to shut up, you're revealing your true colours.

How can you judge that it's not true, that was my objective, and you have taken the word "play" so far out of context.

I use that word as meaning to having a good look at something that needs to be investigated, sorted out, etc.

But when you came up with this rarely used word "abstraction" when I was trying to describe the extra characters that were produced with one of your command's, I knew there was something basic being lost in translation.

Think less, my color, summer or winter, is always the same.

Of course, I judge by what you wrote, not by what you imagined in your head.

"abstraction" is international word, with its origins in Latin, it's used in many languages and it's not some rare word.
Anyway, I don't care if some character is produced more or less in the output, such info doesn't tell me anything.

[VoodooFX]

Many people assume we have crystal balls and can read minds. Unfortunately we don't.

It's simple, universal, how to state the issue clearly:
1) Show the problematic output/result.
2) The way to reproduce that output/result.


EDIT:
Usually they say "It doesn't work" or "I got error". That's it, whole issue ticket...

I met another rare extremity of a spectrum too [only twice in my life].

One guy messaged me a huge wall of text describing his problem in details (~8000!!! characters in the message), not a single word was actually describing the issue, just some abstract, vague nonsense. I asked to make a screenshot of the issue. He replied that the issue is "invisible". Then I asked if it's invisible then how he knows that there is an issue. He replied with some insults. I blocked the guy.

Another one, messaged me super huge text describing his problem in super tiny details. What his cat ate in the morning, how many watts his PC draws, that he had a virus 10 years ago [not this exact nonsense, but no less nonsensical]. Not a single sentence on actual description of the issue. After reading his novella I understood that his issue is something simple. I asked to state his problem in few sentences. He replied with not so much shorter message, basically like the first one just in different nonsense, not a single sentence describing the actual issue. Told him to write his issue in one sentence, no more than 5 words, and that I'll ban him if his message will be longer than that.
Then he replied with one short sentence, stating clearly the issue. He instantly got a solution in a reply. It was some very simple mistake on his side (nevertheless, the guy had genuine eureka moment).
His messages contained over 40000(!!!) characters, in vain trying to describe something that could be described in few words. That must be some record in the craziness. :D

EDIT2: Those messages were hand written, I mean not AI produced....

[StainlessS]

Got dozens of messages from this guy (he's at the lower side of the spectrum):
Yip, nearly 4 hours of talkin', not a single comment in return.
(Wish I could say that I listened to that broadcast, well I did but not for more than about 3 or 4, 10 second bursts).

I guess that the only real +ve thing to extract from such real life experiences is that you/we aint quite as fukkin crazy as some.
(although I probably is/are/am a bit crazy at times, mostly after a good skin full of beer [EDIT: Just returned home from 7 hours in the pub <had breakfast there>, I wanna go back])

[VoodooFX]

Yip, nearly 4 hours of talkin'

As I like experimental films, I find that video hilarious, better than Warhol's film where a guy sleeps for five hours. :D

[StainlessS]

Hi VFX,
AI Server that Doesn't Need the Internet :- https://www.youtube.com/watch?v=P_wt-2P-WBk
looks quite interesting, I've been wondering what to do with my
GMKtec NucBox K9 Mini PC Intel® Ultra 5 125H :- https://www.gmktec.com/products/intel-ultra-5-125h-mini-pc-nucbox-k9
EDIT: Above link no longer works, https://www.gmktec.com/products/intel-ultra-5-125h-mini-pc-nucbox-k9?_pos=1&_sid=268380311&_ss=r

and 96GB ddr5 (bought before the crazy price explosion).
I might give this a go at some point.

I thought that you might find it of interest too.

EDIT: Project N.O.M.A.D.

EDIT: Damn, 7 months I've had that GMKtek thingy and not switched it on since installing W10.

EDIT: With 96GB, W10 telling me has 54GB shared memory for NPU/GPU/CPU, so I'm assuming that I can use close to that much (total) for AI stuff.
(Project Nomad works under Debian based Linux, eg Ubuntu, Mint, etc)