Post your JAV subtitle files here - JAV Subtitle Repository (JSP)★NOT A SUB REQUEST THREAD★

[mei2]

Do you not like Whisper? Which one is better for you?

I use Arctime for editing subs that are produced by Whisper. Similar to SubtitleEdit, Arctime does have its video-to-text sub generator module, but I have not used it.

 

[Taako]

I use Arctime for editing subs that are produced by Whisper. Similar to SubtitleEdit, Arctime does have its video-to-text sub generator module, but I have not used it.

Yes. I see.
I really like Aegisub thanks to Imscully recommendation. The builds by some in the anime community has been very useful.

 

[Taako]

Recently, people are interested in whisper as subtitles and encountered some errors when installing.
I will guide you to install Whisper with VAD on colab. (no need to install python, git, pytorch... If you want to install whisper python see Post #4,513 by @SamKook)

Google Colaboratory

colab.research.google.com

-Upload the mp3 file to colab. (many of you fail at this step)

Thank you for trying to help.

I think "many" are failing with either method not because 100% user error.
Personally, I think it has to do with Whisper itself. It simply doesn't work for everyone.
Most software are like that.
I suspect Whisper will just be another software that won't be user friendly to the masses and fade into obscurity.

Wasn't there another software, that was talk about a lot here? 5-6 months ago?
Many wanted to try it, but it wasn't user friendly? What happen to that one? No it's not capcut

But anyways good luck to those using it. I don't see Whisper adding the increase to subs here.
We still got many subbers here like Chuckie, Imscully, myself and the rest.
Praise the subbers and appreciate them please.

P.S. Maybe more funding will make Whisper better, hopefully.

 

[jameseptemb]

I don't want to be mean since not everyone is good with computers, but whisper is actually very easy to install.

What's most likely happening to most people who failed is they did a small mistake somewhere because they're not familiar how command line works or they needed administrator rights or they didn't select the add python or git to the PATH environment variable during the installation or something else like that and it ends up not working.

Since nobody gave me enough information here to actually diagnose the installation problem they were having or created a thread in the tech support section of the forum, who knows where you're all failing.


Here's a quick guide with the required steps which will hopefully help some(just tested it in a fresh win11 VM to make sure it really is that simple, but I can't test the usage from that fresh install since the VM doesn't see my GPU):

1. Whisper works with python 3.7 to 3.10(not 3.11 yet which is currently the latest) so go to python.org, download python 3.10.9(or whatever 3.10 version is the current one when you read this), just scroll down a bit in the downloads page to find a download link for it. Most will want the "Windows installer (64 bit)" version.
When you install it, you can use the default everything but make sure to check "add python.exe to PATH" to launch python from any folder. Extending the character limit at the end isn't a bad thing either.

2. Install git from git-scm.com and use the default except where it ask to install it to PATH which you want.

3. Open a command line window(open start menu and type cmd) and type the following in it and press enter

pip install git+https://github.com/openai/whisper.git

Type whisper in that same command line to make sure it really worked(should type a bunch of stuff like the usage help and an error that says missing audio) and that's it, whisper is installed.


By default, it'll likely only work with your cpu so if you see it says it uses the cpu(gives an error cpu doesn't support FP16 when it starts so easy to tell) but if you have an nvidia gpu, then there's 2 extra steps(or just do the extra step 2 before step 2 and 3 from the installation instructions above, assuming you never tried to install whisper before):

1. In the command line type the following to uninstall 3 modules whisper installed(don't know why pip has a 3 here, might not be required but I'm far from a python pro so I'm following pytorch instructions and not questioning it)

pip3 uninstall torch torchvision torchaudio

2. Go to pytorch.org and on the main page, in the "INSTALL PYTORCH" section, choose stable, windows, pip, python and whichever version of cuda your gpu support, lowest one in case of doubt, copy the pip3 command it creates below and type that command in the command line.
Mine looked like this:

pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116

Then whisper should use your gpu properly instead of defaulting to the cpu. Be warned that there's a 2.4GB download or so for the cuda t

I don't want to be mean since not everyone is good with computers, but whisper is actually very easy to install.

What's most likely happening to most people who failed is they did a small mistake somewhere because they're not familiar how command line works or they needed administrator rights or they didn't select the add python or git to the PATH environment variable during the installation or something else like that and it ends up not working.

Since nobody gave me enough information here to actually diagnose the installation problem they were having or created a thread in the tech support section of the forum, who knows where you're all failing.


Here's a quick guide with the required steps which will hopefully help some(just tested it in a fresh win11 VM to make sure it really is that simple, but I can't test the usage from that fresh install since the VM doesn't see my GPU):

1. Whisper works with python 3.7 to 3.10(not 3.11 yet which is currently the latest) so go to python.org, download python 3.10.9(or whatever 3.10 version is the current one when you read this), just scroll down a bit in the downloads page to find a download link for it. Most will want the "Windows installer (64 bit)" version.
When you install it, you can use the default everything but make sure to check "add python.exe to PATH" to launch python from any folder. Extending the character limit at the end isn't a bad thing either.

2. Install git from git-scm.com and use the default except where it ask to install it to PATH which you want.

3. Open a command line window(open start menu and type cmd) and type the following in it and press enter

pip install git+https://github.com/openai/whisper.git

Type whisper in that same command line to make sure it really worked(should type a bunch of stuff like the usage help and an error that says missing audio) and that's it, whisper is installed.


By default, it'll likely only work with your cpu so if you see it says it uses the cpu(gives an error cpu doesn't support FP16 when it starts so easy to tell) but if you have an nvidia gpu, then there's 2 extra steps(or just do the extra step 2 before step 2 and 3 from the installation instructions above, assuming you never tried to install whisper before):

1. In the command line type the following to uninstall 3 modules whisper installed(don't know why pip has a 3 here, might not be required but I'm far from a python pro so I'm following pytorch instructions and not questioning it)

pip3 uninstall torch torchvision torchaudio

2. Go to pytorch.org and on the main page, in the "INSTALL PYTORCH" section, choose stable, windows, pip, python and whichever version of cuda your gpu support, lowest one in case of doubt, copy the pip3 command it creates below and type that command in the command line.
Mine looked like this:

pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116

Then whisper should use your gpu properly instead of defaulting to the cpu. Be warned that there's a 2.4GB download or so for the cuda thing.

I installed step 1 python and step 2 git.but my computer is used Nvidia geforce GTX 1650 and I can't find cuda version in my program file.my computer haven't installed cuda tools kid before. so I can't installed pytorch and show error in command box . anybody know how to installed pytorch in GTX 1650 nvidia.

 

[maelstrom9999]

Since MrKid didn't mention this method, here's exactly how I did the drag and drop method, for those having difficulties, if you want to make sure the issue is something else.

0. DO NOT run the Mount Google Drive step.

1. Click the folder icon to open the Files column on the left of the webpage.

2. Drag your audio file on an empty spot in that column(make sure there's enough free space written at the bottom to store your file).
View attachment 3128474

3. Wait for the file to finish uploading. The orange in the circle is the progress and once it's completed, the filename at the bottom will disappear.
View attachment 3128485

Then you put the audio filename in the input(it's what the page says to do) or copy it like I did in my previous post which is how I did it.

Weird. I do the exact same thing, and there is never a progress bar. In fact, the circle is red rather than white.

It still looks like this 15 minutes later.

 

[mei2]

Weird. I do the exact same thing, and there is never a progress bar. In fact, the circle is red rather than white.

It still looks like this 15 minutes later.

You are attempting to upload your file to Colab which is more restrictive in terms of storage size and such. This is a wild guess but may be worth trying: change the file name to sometghing more standrd like: JUX-045.mp3 --espaecially make sure you remove the brackets in the name. Sometimes those special characters make trouble.

 

[maelstrom9999]

You are attempting to upload your file to Colab which is more restrictive in terms of storage size and such. This is a wild guess but may be worth trying: change the file name to sometghing more standrd like: JUX-045.mp3 --espaecially make sure you remove the brackets in the name. Sometimes those special characters make trouble.

LOL thanks. It worked. Who knew something as inconsequential as a file name would cause such a problem. Now we'll see if it exactly produces a subtitle file. I have my doubts that it's going to work the first time.

 

[mei2]

I installed step 1 python and step 2 git.but my computer is used Nvidia geforce GTX 1650 and I can't find cuda version in my program file.my computer haven't installed cuda tools kid before. so I can't installed pytorch and show error in command box . anybody know how to installed pytorch in GTX 1650 nvidia.

Here: https://pytorch.org/get-started/locally/

Meanwhile, cause I myself have been through this pain (I have a GTX 1050ti): in my experience for JAV one needs the large model, so the 4GB RAM is an obstacle. That's why I use the cloud --which btw ends up to be cheaper in electricity bill too

 

[SamKook]

I installed step 1 python and step 2 git.but my computer is used Nvidia geforce GTX 1650 and I can't find cuda version in my program file.my computer haven't installed cuda tools kid before. so I can't installed pytorch and show error in command box . anybody know how to installed pytorch in GTX 1650 nvidia.

The GTX 1650 has cuda v7.5(same as the RTX 2070) capabilities which is likely supported by either version pytorch has to offer. Telling us the error you're getting is the first step to getting support to fix the problem, not much we can do without that information.

But as mei2 said, the 4GB of RAM will be locking you out of both the large and medium model so the result might not be that good.

 

[SamKook]

Weird. I do the exact same thing, and there is never a progress bar. In fact, the circle is red rather than white.

It still looks like this 15 minutes later.

It is a very long filename and depending on how the system on the other side is configured, some characters ca be misinterpreted which can cause issues like you experienced.
That's why you should always give as much information as possible when you're trying to get help, makes finding potential problems much easier sine we don't have to guess.
Glad you got it fixed.

 

[maelstrom9999]

It is a very long filename and depending on how the system on the other side is configured, some characters ca be misinterpreted which can cause issues like you experienced.
That's why you should always give as much information as possible when you're trying to get help, makes finding potential problems much easier sine we don't have to guess.
Glad you got it fixed.

Good code is agnostic towards file names.

In any event, I'm not getting prematurely excited. For this past hour, it's been sitting like this. When I put the pointer on "run whisper" arrow, it says the file was "queued" at 11:31 a.m. Meanwhile, that circular line around the "upload audio file" icon just keeps moving round and round. No idea if it is actually producing something. I guess if it is, I'll eventually see something in my download folder.

 

[SamKook]

If you scroll down, where you were seeing more information about the error before, it'll tell you if it's doing anything.

But since it says it's queued, that likely means the gpu is unavailable or something like that and it's waiting for a free spot to do its thing.

If it completes, it'll open a save file dialog with the srt or auto save it since it's chrome default behavior.

 

[Taako]

Good code is agnostic towards file names.

In any event, I'm not getting prematurely excited. For this past hour, it's been sitting like this. When I put the pointer on "run whisper" arrow, it says the file was "queued" at 11:31 a.m. Meanwhile, that circular line around the "upload audio file" icon just keeps moving round and round. No idea if it is actually producing something. I guess if it is, I'll eventually see something in my download folder.

View attachment 3128950

Good luck my friend.
If it works maybe you can do a better guide to the process

 

[maelstrom9999]

If you scroll down, where you were seeing more information about the error before, it'll tell you if it's doing anything.

But since it says it's queued, that likely means the gpu is unavailable or something like that and it's waiting for a free spot to do its thing.

If it completes, it'll open a save file dialog with the srt or auto save it since it's chrome default behavior.

There is nothing to scroll down to this time. No error message. I did hit the show code button, and it expands to show me a bunch of code, but there are no indications of errors or problems in it.

I feel that moving line around the "upload audio file" arrow is indicating that the file upload is still in progress? It's over 2 gb, so I suppose that could still be the case.

I'm just going to let it run all day and see what happens.

 

[Taako]

There is nothing to scroll down to this time. No error message. I did hit the show code button, and it expands to show me a bunch of code, but there are no indications of errors or problems in it.

I feel that moving line around the "upload audio file" arrow is indicating that the file upload is still in progress? It's over 2 gb, so I suppose that could still be the case.

I'm just going to let it run all day and see what happens.

Maybe you should try a small audio file and test it??
Did you try another audio file type besides .mp3, maybe try .aac?

The software work for me but I just find the subs intolerable. The time code is more useful if anything.
If I find something to help you, I'll let you know.

PyTranscriber has it issues but not like this for many people....maybe?
Whatever, can't wait until we start talking about the newest one next year hahaha
I'm sorry guys just sarcasm and some fun but still... Whisper still has bugs.

 

[MrKid]

Whisper speech translation from audio or video files. Are you using Whisper to create sub from jux045.jpg file? It is more suitable for OCR software.
In the picture you are uploading the file for more than 30min, it is not finished so you "Run Whisper" and there are no results.

Whisper isn't bad but you have to follow the steps right and it should be easy.
1. Upload mp3 files
2. Setup Whisper
3. Run Whisper

And this is the result

 

[Outlaw69]

Whisper speech translation from audio or video files. Are you using Whisper to create sub from jux045.jpg file? It is more suitable for OCR software.
In the picture you are uploading the file for more than 30min, it is not finished so you "Run Whisper" and there are no results.
View attachment 3128989
Whisper isn't bad but you have to follow the steps right and it should be easy.
1. Upload mp3 files
2. Setup Whisper
3. Run Whisper
View attachment 3128990
And this is the result
View attachment 3128991View attachment 3128992

I tried to use google translate and have tried whisper with no success. Can anyone tell me where to get a subtitle for this movie? I am willing to pay as I am not having much luck myself. This is 2009 and I saw one place that won't do older vids. TIA

 

[Chuckie100]

I posted a "cleaned-up" copy of a machine translation for URE-019 about a year agao. Over the Holidays I was bored and was wtching the DVD I had made of URE-019 and decided it could use a lot more clean-up! It could probably still use some more clean-up as the name for the same individual seems to change throughout the video in the machine translation version. Anyway, here is my latest version if you are interested. Enjoy and let me know what you think.

 

[Epinwinrar]

Guys whisper has changed my life and the AI is only going to get smarter over time. The nuance it provides is incredible compared to translating from chinese subs into english. Those feel like garbage now and I must translate everything through whisper. I think it's even better than human translators from erojapanese or other sites offering that service (sorry guys you'll have learn to code now).

--break---
I wanted to mention this software l I use to extract audio.

Pazera Free Audio Extractor 2.11 Free Download - VideoHelp

Pazera Free Audio Extractor is an absolutely free application that extracts audio tracks from video files without loss of sound quality or convert them to MP3, AAC, AC3, WMA, FLAC, OGG or WAV format.

www.videohelp.com

You can save to wav, mp3 , flac etc and its easy to boost the volume.

Lots to experiment with the AI. Gosh I am having so much fun with whisper what a great time to be alive. Now i got an excuse to upgrade my graphics card lol lmao

 

[Taako]

I posted a "cleaned-up" copy of a machine translation for URE-019 about a year agao. Over the Holidays I was bored and was wtching the DVD I had made of URE-019 and decided it could use a lot more clean-up! It could probably still use some more clean-up as the name for the same individual seems to change throughout the video in the machine translation version. Anyway, here is my latest version if you are interested. Enjoy and let me know what you think.

Chuckie, you might have done enough with this sub, unless you're doing it for personal best
There seems to be subs of this, so with your sub and those others, I'm sure it's enough.

Thank you so much. Happy holidays.