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

[soloporhoy666]

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)

 

[Prinsipe]

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.

View attachment 3163790

You can't do this trick with srt format right?

 

[Chuckie100]

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.​

 

[Chuckie100]

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)
View attachment 3163914

Yea it may be in the Japanese speech recognition software and not in the translation software. Just guessing however!

 

[Chuckie100]

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.

 

[SamKook]

You can't do this trick with srt format right?

No, srt is a very simple format with no fancy features.

But it's very easy to convert any srt to ass.

 

[Chuckie100]

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.

 

[SamKook]

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.

 

[Imscully]

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.​

WOW!!! Two of my favorite movies!!! Four of the all-time hottest MILFS in porn history. Thanks for sharing your work!!!

 

[Imscully]

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.

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).

 

[Electromog]

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.

 

[panop857]

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.

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.

 

[Electromog]

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.

 

[panop857]

I made a thread for Whisper setup, parameters, and discussion

https://www.akiba-online.com/threads/whisper-openai-automatic-english-subtitles-for-any-film-in-any-language-an-intro-guide-to-subtitling-jav.2115103/

 

[panop857]

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.

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.

 

[Makkdom]

APNS-305 As long as it's for the sake of the person I love, I don't mind being circulated, defiled, or seeded by people I don't know... Jun Suehiro​

Another file I found and worked on for a while. A young girl agrees to help her boyfriend pay off some debts and spirals into a pretty degrading life.

 

[SamKook]

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).

ASSA is the same thing as .ass btw.

Unless you want to do something more than just basic text on a video, there's really no good reason to use .ass over subrip(.srt) which is likely the most supported subtitle format.

.ass just gives you a lot of control over how the text is displayed. You can change the font of individual lines, color them, move them to a specific position, scale them bigger or smaller, add gradients to the text, fade effects, stuff like that. You can even draw shapes if you want to block some text on screen and add subtitles over that part.

Here's an example of something fancy I did back in the day, the "B&L's Style Romance!" text in that picture is 100% soft sub, you can toggle it on and off. It's 9 different subtitle lines(and possibly 2 more lines for the gradient and something else, forgot how that works 7 of which are to create the gradient effect, it only shows a slice of each line of different colors) stacked onto each other to mimic the style of the japanese title.


Edit: One thing I forgot about that could be useful with .ass even if you only want basic text is that you can set an actor name for each line which doesn't get displayed into the subs so if you find it helpful to know who is saying what when editing, that's one thing .srt can't do.

 

[ironfevers]

A bit of off topic question: does anyone know how I can brun 2 subtitlles into a video (one on top and one on bottom of the screen)? Thanks.

Merge two subtitle files in different languages into one

This online tool will combine two subtitle files into one. You will see the dialogues in two languages at the same time.

easypronunciation.com

 

[ironfevers]

Just a tip on Whisper about translation: Don't use it. Just choose No Translation and do that later in Google translate or DeepL translate

I have experimented with VAD-Threshold and have settled on 0.3. What does Chunk_Threshold (3.0) do? Size of the audio parts analyzed? I'll try to lower and raise the number to see if there are improvements. Source separation didn't work for me. I get error messages.

I also arrived at the same conclusions. After extensive testing, I've settled on 3.2 chunk_threshold and 0.3 vad_threshold for a good balance between catching short sentences and natural sounding speech. Source separation also fails to work. The spleeter package is to blame.

I have increased volume with all three types of audio to text and if you don't go overboard with the volume increase it has always yielded better results. Amplification is also better than compression. Some software doesn't like clipping so you may have to think about that, too.

I also use amplification. I amplify 1 db in Audacity and export as wav.


I have Whisper with VAD installed locally for long duration videos such as HUNTB, but I use the medium model with an RTX 3070 as large requires more VRAM. I also tested max_retries. One file gave me 256 chunks. 52 chunks (20%) needed a retry. Of those 52 chunks, 45 (87%) still failed with a max_attempts of 24. The rest succeeded within 3 retries. Conclusion, stick with a max_attempts value of 1, 2 or 3. I stick with no translation and just translate using DeepL. No one talked about the garbage_list. It'll save you so much time from cleaning up the subtitle. I added over 1000 Japanese words to the garbage list. https://drive.google.com/file/d/1AwJ-VdxA4jM6yJS37Tdxrbj1uAgaU08j/view?usp=share_link. Anything that sounds like laughing, screaming, moaning, etc. get deleted from the subtitle. The garbage list is not complete, there is always more to add. Also I changed the out_path filename so that it includes the settings used. No need to upload to the sidebar in Colab. If mounting your google drive, an example audio_path is "/content/drive/My Drive/temp/abc-123-1db.wav".

 

[Chuckie100]

RCTD-505 If You Can Endure Ejaculation With Your Mother's Doskebe Fellatio,
A Prize Of 1 Million Yen If You Explode Incest Punishment Game 2

I used Whisper to produce this subtitle file for RCTD-505. This is the latest mother-son JAV from Rocket. 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.​