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.
When I want subtitles on the bottom and or on the top of the screen, I use Aegisub. It's free also.
You have full control of where you place the subtitles with the ass format aegisub uses by default(but others support too), you can even put both at the bottom, one left and one right, change the color, stuff like that: https://fileformats.fandom.com/wiki/SubStation_Alpha#Data_types
Burning subs into a video is more complicated(Only way I know is using avisynth which is pretty complicated but other easier software likely also have that function) and if it's just for comparison sake, much easier to use a .ass subtitle.
Edit: To give you an idea, this was done with subtitle edit by setting 2 styles(after converting the vtt to ass), one for top left and the other for top right with a 1000 pixel margin on the opposite side so they don't overlap. You set one style to your currently open sub for all lines, then you append your second subtitle(there's a thing for that in tools, don't sync anything, leave as-is) and you set the second style for all lines of that second subtitle(shift + end will select the lines from the currently selected one to the end, shift + home does the opposite) and it's that easy.
Burning subs into a video is more complicated(Only way I know is using avisynth which is pretty complicated but other easier software likely also have that function) and if it's just for comparison sake, much easier to use a .ass subtitle.
Edit: To give you an idea, this was done with subtitle edit by setting 2 styles(after converting the vtt to ass), one for top left and the other for top right with a 1000 pixel margin on the opposite side so they don't overlap. You set one style to your currently open sub for all lines, then you append your second subtitle(there's a thing for that in tools, don't sync anything, leave as-is) and you set the second style for all lines of that second subtitle(shift + end will select the lines from the currently selected one to the end, shift + home does the opposite) and it's that easy.
Last edited:
I watched an American xxx movie through Whisper and I realized that lewd language is detected by Whisper, not so in the Japanese language, so the error may be from the model on which whisper is based, possibly it is not included, not because it is not allowed, possibly someone did not see it necessary to include it in the Japanese language.
So it is possible that at some point someone will create a model with the most lewd words in the Japanese language, since the AI is still in training (it is worth dreaming)
So it is possible that at some point someone will create a model with the most lewd words in the Japanese language, since the AI is still in training (it is worth dreaming)
I used Whisper to produce these subtitle files for VENU-318 and VENU-223. These are two movies in the JAV series with the mothers swapping their sons. As always however, I still had to clean it up a bit and re-interpreted some of the meaningless/ "lewd-less" dialog. Again, I don't understand Japanese or Chinese so my re-interpretations might not be totally accurate but I try to match what is happening in the scene. Anyway, enjoy and let me know what you think.
Yea it may be in the Japanese speech recognition software and not in the translation software. Just guessing however!
I'm beginning to believe that Whisper just makes up shit when it's confused (kinda like I do when the text obviously doesn't fit)! For example phrases like..."I'm hungry", I'm sorry", and "It hurts". A direct replacement is not always possible because the real translation seems to vary from time to time! But like I've said before Whisper seems to be the best tool in our tool box for now.
No, srt is a very simple format with no fancy features.
But it's very easy to convert any srt to ass.
I have found that an ass file is a bit more difficult to edit however. So if you start with an srt file, I would suggest you first do your editing/cleanup there, and then convert it to ASS and then do your style formatting.
If you use a text editor, that's very true since there's a lot more information in the file and the text and the formatting isn't as clearly separated, but there should be no difference if you edit it using a subtitle software, at least nothing I can think of.
Just depends how you work. But I've only ever edited ass files so I could be bias and there's something I'm not seeing.
Just depends how you work. But I've only ever edited ass files so I could be bias and there's something I'm not seeing.
WOW!!! Two of my favorite movies!!! Four of the all-time hottest MILFS in porn history. Thanks for sharing your work!!!
Whenever I use the Subtitle Edit program I always like to convert to Subrip type file once the auto translate function is finished. Not even sure how I landed on that as a fav. Perhaps I'm missing out, but it seems to streamline the subs while maintaining the ability to edit properly. I'd be curious to know if there is a reason you prefer ASS (as opposed to Subrip or ASSA).
Right, I tried my first whisper translation. I got a lot of repeating lines, but not just a single line repeating (though there were some of those as well) but groups of lines. For example:
123 00:08:16,000 --> 00:08:18,000 Is it true?
124 00:08:18,000 --> 00:08:22,000 No, it's not.
125 00:08:22,000 --> 00:08:25,000 I'm still in the hospital.
126 00:08:25,000 --> 00:08:28,000 I'm still in the hospital.
127 00:08:28,000 --> 00:08:30,000 Is it true?
128 00:08:30,000 --> 00:08:32,000 No, it's not.
Does anyone have an idea what settings I should change to avoid these?
I am running it on my own computer instead of online, because the online thing kept giving me errors. This means I have to use the small model, I hope that's not what is causing this issue.
123 00:08:16,000 --> 00:08:18,000 Is it true?
124 00:08:18,000 --> 00:08:22,000 No, it's not.
125 00:08:22,000 --> 00:08:25,000 I'm still in the hospital.
126 00:08:25,000 --> 00:08:28,000 I'm still in the hospital.
127 00:08:28,000 --> 00:08:30,000 Is it true?
128 00:08:30,000 --> 00:08:32,000 No, it's not.
Does anyone have an idea what settings I should change to avoid these?
I am running it on my own computer instead of online, because the online thing kept giving me errors. This means I have to use the small model, I hope that's not what is causing this issue.
Set "condition_on_previous_text" or whatever it is to False. In theory, it is there to make it learn into consistent style and slightly bias the results towards specific topics that the entire source is about. In practice specifically for porn films of languages other than English, there's going to be a lot of scenes where it can't really make any good guess, which leads to the slight bias on previous text pushing it towards the exact same "answer", and then that bias for the previous bias layers with the bias from two lines ago, and so on, leading it to land in long ruts of the same sentence it it gets a nice clear answer for it to change its mind.
The Small model definitely contributes to this, but the condition_on_previous_text is probably the larger influence.
The Small model will be enough to get the general gist of plot scenes, but will do much worse on sex dialogue and will need quite a bit more editing and interpretations to get into a good spot. If you are limited, it can be good practice to run the same film through several different settings, making sure to save the outputs to different names, and reading them side by side and copying the best into a new file.
I'm less interested in the dialog during sex (as it is generally much the same anyway) but more in the dialog of the story surrounding the sex, so that's ok. However, github claims 8 GB of video memory should be enough for the medium model, so maybe I should try that next.
I will try the condition_on_previous_text option. I guess since it only takes a few minutes I can do a few runs with different settings and see how that affects things.
I will try the condition_on_previous_text option. I guess since it only takes a few minutes I can do a few runs with different settings and see how that affects things.
I made a thread for Whisper setup, parameters, and discussion
If you're trying to get away with just Small, and it only takes a few minutes, you can try to do runs with a low temperature (but not zero) and like best_of 10 or something. Part of the key to Whisper is doing settings that try to compensate for whatever your computational stuff is limited by.
Last edited: