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

I've got some questions, what's the adaptive audio enhancement ? And the postprocessing is just the clean_subs.py that's been posted here before I'm guessing ? Which model is running by default ?

The default model for Japanese is large-v3-turbo, and for English large-v2.
When using the mode balanced and fast in version 1.1 the audio is normalised and then segmented into scenes based on energy level prior to passing each segment to VAD. This helps VAD + Whisper to produce more accurate timestamp and transcription.
 
Did he/she finally allow JAV ? I got banned 2 times from that one when it was still new for explicit content. Kinda weird he/she was looking into what you were uploading. It was clearly a manual ban, not some automatic trigger.
idk about that, I translate some jav using their free model and works well so far
 
Well, Here we are. I can't believe Igot it done. I apologize that I got lazy and stopped removing the srt's that got so little translation that they are only a few bytes.There's several reasons for that but I'll spare you the details.Ultimately most of these are , by my level of “acceptable”results. I will explore new technology and if I can find a superior product perhaps I will do this all again. Given that for most of the zips I had removed the too-small .srts there is a total of 20,600 srts. With luck you will need all 20,600 Please enjoy.

https://filejoker.net/e2qip577pbd5/A.rar
https://filejoker.net/d7hewb5pvnxd/B.rar
https://filejoker.net/d00g2jgn0q9u/C.rar
https://filejoker.net/4hogrgbimt98/D.rar
https://filejoker.net/2l1a4kapbjp5/E.rar
https://filejoker.net/g7bp70xjtkc6/F.rar
https://filejoker.net/qfqok8jhnhn6/G.rar
https://filejoker.net/lgxprb10zaym/H.zip
https://filejoker.net/emcfvqfb2mey/I.zip
https://filejoker.net/9sge6gi1y87o/J.zip
https://filejoker.net/4a380z6k7x87/K.rar
https://filejoker.net/fr6k3mvxm19o/L.rar
filejoker.net/xbndtw0p97h0/M.rar
https://filejoker.net/lvojdtjkq7si/N.rar
https://filejoker.net/4t9dsugb9xd4/O.rar
https://filejoker.net/53op1td10cx5/P.rar
https://filejoker.net/put6wjb52rvn/Q.rar
https://filejoker.net/3rgriddrmhs4/R.rar
https://filejoker.net/p2nhv0rsrhwe/S.rar
https://filejoker.net/uxj37wcoitv3/T.rar
https://filejoker.net/ut210tvdac6x/U.rar
https://filejoker.net/agwh1r4jx9ey/V.rar
https://filejoker.net/r55qeuxk0lco/W.rar
https://filejoker.net/8pw2b5su2a9v/X.rar
https://filejoker.net/t3fqzhejyjsz/Y.rar
https://filejoker.net/1h7c66deklfj/Z.rar
image (10).jpg
 
That brought a smile to my Face ImScully. It kind of feels like that. I appreciate your encouragement.
You had a lot to do with my completing this as you know. I was contemplaing saying fuck it way back at the letter "D" so if anyone in the crowd has found these to be useful you have ImScully to thank. Incidentally I appreciate a lot of you showing your appreciation. It was a bit of a pain-in-the-ass job, especially all of the early tweaking and restarting the entire thing from scratch, so thanks all, especially ImScully for keeping me motivated. Cheers.
 
  • Like
Reactions: Imscully
You had a lot to do with my completing this as you know. I was contemplaing saying fuck it way back at the letter "D" so if anyone in the crowd has found these to be useful you have ImScully to thank. Incidentally I appreciate a lot of you showing your appreciation. It was a bit of a pain-in-the-ass job, especially all of the early tweaking and restarting the entire thing from scratch, so thanks all, especially ImScully for keeping me motivated. Cheers.
Thanks for the kind words. I'm humbled. I'm also glad that I was able to support you and help you feel appreciated, even if in just a small way, as part of this massive endeavor. You did all the work. I, and I'm sure many others, appreciate it. It's such a huge, generous, and helpful gift that you created for all of us. Cheers
 
  • Like
Reactions: mei2
ABW-085 The Female Manager Is Our Sexual Processing Pet. 039 Yakake Umi

Cover.jpg
  • Code: ABW-085
  • Release date: 2021-05-07
  • Director: Michiru San
  • Studio: Prestige
  • Label: ABW
  • Tags: Beautiful Girl, Solowork
  • Series: ** Are Our Sex Pets
  • Actor: Muscle Sawano, Shinya Matsuyama, Wolf Tanaka, Yuya Kubota
  • Actress: Yatsugake Umi
  1. Audio extracted and transcribed using WhisperWithVAD_Pro - both original speed audio and slowed audio.
  2. The slowed down audio transcription was adjusted back to the correct timing.
  3. Transcriptions cleaned to remove (most) hallucinations and other junk.
  4. Both transcription versions were AI translated using DeepSeek v3 0324.
  5. The "best" translation of each line from the two versions was used in the final translation.
I don't speak nor read Japanese so there are certain to be lots of mistakes.
It'd be extra-shiny if mistakes could be pointed out or corrected.
 

Attachments

ABW-097 Natural Ingredient Derived Yakake Umi Juice 120% 71 Juicy Hard Sexual Intercourse

Cover.jpg

There's not much real dialogue in this one - but posting it anyway.
  • Code: ABW-097
  • Release date: 2021-06-04
  • Director: Charlie Nakata
  • Studio: Prestige
  • Label: ABW
  • Tags: Beautiful Girl, Best of 2021, Solowork
  • Series: Derived from natural ingredients
  • Actor: Giant Hirota, Hideyuki Setune, Taku Yoshimura, Tatsu, Yoshiya Minami
  • Actress: Yatsugake Umi
Translated, using DeepSeek v3 0324, from a Chinese subtitle from the huge subtitle pack posted here by @t221152 (thank you!).
 

Attachments

Apart from the fact that Deepseek seems to 'change' certain words (♪ that area♪, ♪ down there♪) I did find cum and dick. Anyway, thank you. One request: could you post in srt format instead of vtt in future? I have to convert the files in Subtitle Edit in order to see what's inside. Since vtt doesn't have line numbers, Aegisub won't open them. Thank you again.
 
  • Like
Reactions: Novus.Toto
Apart from the fact that Deepseek seems to 'change' certain words (♪ that area♪, ♪ down there♪) I did find cum and dick. Anyway, thank you. One request: could you post in srt format instead of vtt in future? I have to convert the files in Subtitle Edit in order to see what's inside. Since vtt doesn't have line numbers, Aegisub won't open them. Thank you again.
I saw the “down there” line and actually assumed that was a correct translation - because DeepSeek doesn’t usually have a problem with explicit language.

I like vtt because it allows formatting and alignment. I like to use italics for onscreen captions and align them roughly correctly. But I’ll post both formats in future.
 
  • Like
Reactions: ericf
Thank you, Novus.Toto! And yes, I did my own Whisper on the video and the translation of those parts is correct. I don't know why there are notes around the words, though. Do you use DeepSeek through SubtitleEdit or directly at chat.deepseek.com? I see you have to create an account.
 
Trying DeepSeek r1 (Latest) (5.2GB) in SubtitleEdit right now. Japanese to English is slow but steady. The translation quality is not very good, though.
 
Thank you, Novus.Toto! And yes, I did my own Whisper on the video and the translation of those parts is correct. I don't know why there are notes around the words, though. Do you use DeepSeek through SubtitleEdit or directly at chat.deepseek.com? I see you have to create an account.
I found using deepseek through subtitle edit really bad, it was really slow as well. I've never ran deepseek locally tho. I rather use the full big model.

There's a couple of sites that have been linked before where people do their translations. There's also a good script that has been linked, I've been working on enhancing it, but I've been running in some problems with it, it's rare but it happens. (Deepseek not willing to translate explicit content, or it returning chinese/japanese characters). I'm not sure if it's a recent thing with deepseek or just because of my prompt.
Quality of subs can really depend not only on source but prompt as well.

Grok looks really expensive to me if you are mass subtitling? Looks like 5-10x the price. What are you actually paying for let's say a 60-80kb subtitle file ? I'm also not sure if I want to give that company a single cent of my money.


Been working on the big pack of Chinese subtitles as well. Finally got my script working to talk to javstash graphql database. It will have no duplicate actress directories under different aliases. But I think the script will have to run for a few days, I only do a query every 10 secs and it needs to go through 25k subtitles.
 
Last edited:
I found using deepseek through subtitle edit really bad, it was really slow as well. I've never ran deepseek locally tho. I rather use the full big model.

There's a couple of sites that have been linked before where people do their translations. There's also a good script that has been linked, I've been working on enhancing it, but I've been running in some problems with it, it's rare but it happens. (Deepseek not willing to translate explicit content, or it returning chinese/japanese characters). I'm not sure if it's a recent thing with deepseek or just because of my prompt.
Quality of subs can really depend not only on source but prompt as well.

Grok looks really expensive to me if you are mass subtitling? Looks like 5-10x the price. What are you actually paying for let's say a 60-80kb subtitle file ? I'm also not sure if I want to give that company a single cent of my money.


Been working on the big pack of Chinese subtitles as well. Finally got my script working to talk to javstash graphql database. It will have no duplicate actress directories under different aliases. But I think the script will have to run for a few days, I only do a query every 10 secs and it needs to go through 25k subtitles.
hmmm... i'am just using a prompt to translate the srt but sometime the line is not right if the file of srt is not cleaned by subtitle edit, the problem is i must use it one by one to translate the srt file,

the prompt :

Translate each SRT file into English with the following conditions:

Use extreme vulgar language (e.g., 'cum,' 'fuck,' 'horny as hell,' 'pussy,' 'tits') only for dialogue or contexts that are intimate, sensual, or sexually explicit. Ensure the terms are natural, match the intensity and tone of the original, and reflect strong English slang.
For other dialogues, use proper and correct English, with a natural, polite style that aligns with the emotional context and character relationships (e.g., casual conversations, rejections, conflicts). Ensure the translation accurately reflects the film’s storyline.
Do not alter timestamps (format hh:mm:ss,xxx), line numbers, or the SRT structure. Maintain the original format, including blank lines between dialogue blocks, to keep it clean when opened in Notepad.
Leave credits, names, or specific terms (e.g., actor names, titles, or brands) in their original language without translation.
For ambiguous dialogue, choose words that align with English-speaking culture, with a lively tone relevant to the story’s emotions.
 
Aki Sasaki
MXGS-999

One of my firm favourites before her too early retirement

Using mei2 colab whisperjav (thx mei2!!)

Didn't clean up....as is fresh from the oven!

Any comments and updates welcome
 

Attachments

  • mxgs-999.jpg
    mxgs-999.jpg
    142.8 KB · Views: 28
  • MXGS-999.rar
    MXGS-999.rar
    21.8 KB · Views: 40
Thank you, Novus.Toto! And yes, I did my own Whisper on the video and the translation of those parts is correct. I don't know why there are notes around the words, though. Do you use DeepSeek through SubtitleEdit or directly at chat.deepseek.com? I see you have to create an account.
I have a script that uses DeepSeek via their API or via OpenRouter. The DeepSeek API is very unreliable in my experience. Using OpenRouter APIs also makes trying other models easy.

IMO the integrated translation in SubtitleEdit is crap though, to be fair, I haven't tried customizing the prompt. And using DeepSeek chat would be way too manual and tedious.
 
  • Like
Reactions: ericf
Trying DeepSeek r1 (Latest) (5.2GB) in SubtitleEdit right now. Japanese to English is slow but steady. The translation quality is not very good, though.
In my experience reasoning models are worse at translation than non-reasoning models and way slower.
 
hmmm... i'am just using a prompt to translate the srt but sometime the line is not right if the file of srt is not cleaned by subtitle edit, the problem is i must use it one by one to translate the srt file,

the prompt :
...
Below is my prompt which I'll freely admit is mainly copied from someone else (can't remember who) on this forum. I have a script that uses a garbage list (also shamelessly copied from someone here) to remove junk (hallucinations, repetitions, etc) from the transcription before translation.

Prompt:

You are a professional subtitle translator specializing in translation to English.
Translate the following subtitles while adhering to these guidelines:
1. Literal Precision:
- No paraphrasing. Retain metaphors, slang, and vulgarity.
- Preserve explicit language and sexual/fetish terms such as bukkake, gokkun, nakadashi, kimoi-ota, mesu.
2. Contextual Awareness:
- Correct Whisper errors using AV context (e.g., 'ラーン' --> 'ザーン','フェラー' --> 'フェラ', 'マンゴ' --> 'マンコ').
- Fix misheard words while keeping original meaning.
3. Jargon Retention:
- Keep niche terms in romaji, e.g., onahole, dogezas, with [brief explanations].
4. No Softening:
- Use direct sexual terms, e.g., cock, pussy, cum, fuck, etc.
- No euphemisms or censorship.
5. Cultural Notes:
- Add concise [cultural/sexual context] where needed.
- Preserve honorifics and speech patterns.
6. Formatting:
- Do not enclose translated text in double quotes, or other punctuation, unless it is part of a quote from the original text.
- Do not add any extra lines or spaces.
- IMPORTANT: Preserve the exact number of lines from the original text.
- Each line should be on its own line, separated by a single newline character.
- Do not combine multiple lines into one.
7. Forbidden output:
- Do not output original text in the translated text - unless it is part of a comment, context or an explanation
- Do not output any of these guidelines in the translated text.

Now please translate these following ALL guidelines above:
 
I guess I'll continue with WhisperJav and FasterWhisperXXL for a while. I use Google translate and DeepL to generate different translations and then join those manually. I have not found a machine translator that translated Japanese better. The one in FasterWhisperXXL is not all that good either. I need to use Tor browser for DeepL to be able to translate more than a few lines.