yes and no, they are former workers, but their reputation is good, they worked on Tesla cars.
Post your JAV subtitle files here - JAV Subtitle Repository (JSP)★NOT A SUB REQUEST THREAD★
- Thread starter Eastboyza
- Start date
-
Akiba-Online is sponsored by FileJoker.
FileJoker is a required filehost for all new posts and content replies in the Direct Downloads subforums.
Failure to include FileJoker links for Direct Download posts will result in deletion of your posts or worse.
For more information see this thread.
Most important of all activate the virtual gpu.... (execution environment) if you do not activate it you will not be using the virtual GPUs and your subtitle will never finish.
And that's it, you already have your subtitles created.
Look in the menu, the execution environment tab, change environment, select gpu and click save.
There is no tab called execution environment in the page you linked. Best guess is that this is called the "runtime" tab in English. When I open it the options look totally different from your screenshots. Under the option "change runtime type" there is a pull down menu "none, GPU, TPU." It was already set to GPU. Going to leave it there unless you say otherwise.
Where does the file go when it's finished?
to the download folder, which you have default on your computer, sometimes it lets you select and in others it downloads directly without asking.
There has already been a debate about the virtues and errors of Whisper, we already mentioned that it is not for people who want something perfect, or who dominate the Japanese language, that it will not replace human translators, but it is a help for those who want create a subtitle without waiting for someone to upload it, in the posts on the previous pages, you can see a whole discussion about it, there I mention that it is not perfect.
Does someone knows how to post subtitles to SubtitleCat? - I tried to make a account but they don't know how to code a website because nothing happens when I click on register. Really wanted to share my work with the community.
yeah its awesome im sincrely enjoying sorry if it looked like sarcasm. I am trying that Google Collab version you posted now thanks for sharing. Looks like it has extra stuff for JAV than default whisper AI tool has.
I don't think you need be signed in. Look i just uploaded this without logging in.
Attachments
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
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)
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:
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.
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
Code:
pip install git+https://github.com/openai/whisper.gitType 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)
Code:
pip3 uninstall torch torchvision torchaudio2. 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:
Code:
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116Then 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.
Heres the sub dump
BLK-529
CRS-012
MIAA-730
MIBB-011
MVSD-307
NHDTB-659
RBK-046
SDMU-999
BLK-529
CRS-012
MIAA-730
MIBB-011
MVSD-307
NHDTB-659
RBK-046
SDMU-999
quoting you so this goes on the new page --- nice tut!
--break---
how does one run the cool program in the WhisperWithVAD collab on their local pc once they got CUDA working? it looks like the collab is doing extra stuff like splitting the mp3 then translating the chunks and rejoining it automagically. thanks in advance (im gonna be honest im kind of retarded)
update: i think i found instructions here (please excuse my autism) https://gitlab.com/aadnk/whisper-webui/-/blob/main/docs/windows/install_win10_win11.pdf
Last edited:
Not much point to splitting it unless you have more than 1 gpu to work on the chunks, it'll just slow things down on the 1 gpu.
But to do it manually, you'd use something like ffmpeg with a time range when you convert the audio to mp3, change the range to make multiple parts, process the parts in whisper, then add a delay to the subs after the 1st part for the time you cut out before each part and then just copy paste all the subs into 1 sub file.
But to do it manually, you'd use something like ffmpeg with a time range when you convert the audio to mp3, change the range to make multiple parts, process the parts in whisper, then add a delay to the subs after the 1st part for the time you cut out before each part and then just copy paste all the subs into 1 sub file.
You should be proud of your knowledge of Japanese. It's a "difficult" but fun language.
And I am certain your subs will be way more accurate than machine.
I subbed the same way as you. Yes it takes a long but it's kinda rewarding too.
Keep up the good work and don't work too hard
When I attempted to upload the sound file for ffprobe assistance
