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

Zephlol said:
Agree. Whisper timing is fixed, and gets annoying if the lines are either too short or too long. Premiere captures the duration of dialogue a little better, but is imperfect and tends to make some glaring errors (like a line lasting for faaaar too long).

For the translation itself, whisper wins. Premiere spews out nonsense from time to time.

I do find following the dialogue from Whisper to be a lot easier however
Click to expand...
Yeah, had a look at the premiere subs on the video and it's not great either, they often start and end too early and it does miss the end sometimes, like that line that lasts for over 4 minutes 12 mins in.

You can see why Gokkun Punch insist on getting a human timer, neither whisper nor premiere produce even remotely close to quality timing. Good enough to follow if you don't want to put in hours of time doing it yourself though.
 
SamKook said:
Yeah, had a look at the premiere subs on the video and it's not great either, they often start and end too early and it does miss the end sometimes, like that line that lasts for over 4 minutes 12 mins in.

You can see why Gokkun Punch insist on getting a human timer, neither whisper nor premiere produce even remotely close to quality timing. Good enough to follow if you don't want to put in hours of time doing it yourself though.
Click to expand...
Yep. AI is not ready yet
 
What is the syntax for Temperature on the command line? in Python it is temperature=(0.2, 0.4, 0.5) and best_of=3 to use those three different temps, but I can't get a specific spread like that to work on the command line.
 
If you do whisper --help it'll show you all the options and how to use them(kinda).

This is part of what it says:
Code: 
--temperature TEMPERATURE                        temperature to use for sampling (default: 0)
  --best_of BEST_OF     number of candidates when sampling with non-zero temperature (default: 5)

Doesn't say how it can use multiple but I'd assume something like whisper --temperature (0.2, 0.4, 0.5) from your python example. Maybe " instead of ( and ).
I haven't messed with extra options at all so no idea how they work.
 
Zephlol said:
Mei's IPX-998 is pretty damn good in terms of translation, was this manually edited?
Click to expand...

I used DeepL pro (API calls) for IPX-998 translation --I too was surprised how good the translation became. I did not expect such a difference between pro (API calls) and the web version. In terms of manual post-edits, I needed to do roughly 10 edits or so.
 
SamKook said:
If you do whisper --help it'll show you all the options and how to use them(kinda).

This is part of what it says:
Code: 
--temperature TEMPERATURE                        temperature to use for sampling (default: 0)
  --best_of BEST_OF     number of candidates when sampling with non-zero temperature (default: 5)

Doesn't say how it can use multiple but I'd assume something like whisper --temperature (0.2, 0.4, 0.5) from your python example. Maybe " instead of ( and ).
I haven't messed with extra options at all so no idea how they work.
Click to expand...

I looked at the help, and tried all combintaions of "" (), and []. Searching for help with Whisper online is just extremely difficult because it is new, the name sucks, and because virtually nobody seems to be using the command line. https://blog.deepgram.com/exploring-whisper/ has examples for Python with:

beam_size=5
best_of=5
temperature=(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)

so I guess that makes temperature a Tuple of Integers? Seems really sloppy on how that interacts with command line. Since the command line --help doesn't even give the suggestion of multiple values, it just might not be possible.
 
panop857 said:
I looked at the help, and tried all combintaions of "" (), and [].
Click to expand...

Have you tried with nothing around? So like --temperature 0.2, 0.4, 0.5 or even --temperature 0.2 0.4 0.5
 
Gokkun Punch said:
The people who DM me asking me to do this or that for them, on the other hand…
Click to expand...
That was sure lol. People don't even read they see "subtitles" and think "oh, he'll do subs for me ... for free of course".
 
  • Like
Reactions: Gokkun Punch and mei2
panop857 said:
I looked at the help, and tried all combintaions of "" (), and []. Searching for help with Whisper online is just extremely difficult because it is new, the name sucks, and because virtually nobody seems to be using the command line. https://blog.deepgram.com/exploring-whisper/ has examples for Python with:
Click to expand...

cmd> whisper --model tiny --language ja --task translate --temperature 0.4 --temperature_increment 0.1 .\inputfile.wav
 

DVDES-626 Sex Education 4 For I Want To Tell The Son Of Incest Planning Beloved Issues In The Ultimate To Be ... Pregnancy​

1dvdes626pl.jpg

I used Whisper to produce this subtitle file for DVDES-625. A word of caution: I downloaded the first part and then down loaded the second part from a different site so the timing might require adjustment. 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.​

 

Attachments

  • Like
  • Love
Reactions: shinjixx, mugul, xsf27 and 2 others

DASS-091 My Son Is A Libido Monster --Hana Himesaki​


This is a file I got from subtitlecat. It was already very good, so I just polished it up a bit mostly by fixing pronouns and dealing with all the "so comfortable" comments. I also chose to substitute the more natural sounding "sex fiend" for "libido monster." This is one of the subgenre of JAVs in which a mother doesn't know what to do with her continually-masturbating son who is so horny he is beginning to get tired of his blow-up doll and starting to eye mom lasciviously. In this particular case mom is in luck because a young woman living in her building is also a sex fiend and offers to help out. For a darker and more twisted take on the same theme, check out the recently released HUNBL-126. As far as I know, no subtitles exist yet for that one, so if anyone is feeling ambitious it might make a good project.dass00091pl.jpg
 

Attachments

  • Like
Reactions: shinjixx, noolek, xsf27 and 3 others
Zephlol said:
This is the srt for RKI-606. Its my most recent completed raw srt. Ran the video through premiere on japanese detection and translated to english using subtitle edit. Zero touch-up. Can someone with whisper run the same video and post it here? Im curious how they compare.
Link to the video
Click to expand...
Are you using a legit adobe premiere pro or just a cracked one?

I am planning to try it myself but I don't want to pay the expensive subscription of adobe products. :aghh:
 
Has anybody tested how whisper translation compares to deepl (free version)? Up to know I found whisper doing a very good job but since I can't save a japanese version for deepl and let whisper translate it for he same file, it's hard to tell.
 
porgate55555 said:
Has anybody tested how whisper translation compares to deepl (free version)? Up to know I found whisper doing a very good job but since I can't save a japanese version for deepl and let whisper translate it for he same file, it's hard to tell.
Click to expand...

change the option of translation_mode : No translation
 
  • Like
Reactions: Prinsipe
You can test it yourself by running whisper twice on the same file, once with translation and once without.
 
SamKook said:
You can test it yourself by running whisper twice on the same file, once with translation and once without.
Click to expand...
This will not work as Whisper generates different subtiltes every time you run it, so there is no one-to-one comparison unless you get the japanese version with no translation and the translated one from the same run.
 
porgate55555 said:
I know how it workes, the question is if you get better results using whisper or deepl.
Click to expand...


The good things with Whisper end-to-end translation are:
(a) It uses context for translation. It tries to build a context for example guessing gender (he, she), and punctuations for translation task.;​
(b) It makes the entire Whisper output faster. Translate tsak is faster than transcribe task. It is funny but their main sw engineer was saying that the way the algorithm is written, the end-to-end trasnlation task is performed faster than just transcribe task :)​
​
The good things with DeepL is that It is just a better translator. Fullstop. One bad thing with DeepL is that it often mixes up he/she, it/they, sir/ma'am.

For me I decided to just stick with DeepL. I did some comparisons during the early days of Whisper (v1). I haven't done any comparison with v2 but I understand that the translation capability did not change from v1 to v2. To me, DeepL translations came out better. But then again, I don't speek Japanese so my read might be quite wrong.

In terms of being able to compare the outputs as @SamKook suggested, one can make Whisper to be more deterministic by setting both temperature and beam to zero. That makes the output close to determinstic. But the pitfal is that it produces more halucination and repeating lines in the output.
 
  • Like
Reactions: porgate55555
You must log in or register to reply here.
Top Bottom