It's good that it works for you--
but you must be....anyways, if you're so sure about it, you should post your subs
Last edited:
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.
but you must be....anyways, if you're so sure about it, you should post your subs
The colab thing is an extra interface on top of whisper itself so it adds more chances for things to go wrong.
But yeah, the randomness of the result is very off-putting to me even though when it works, it works fairly well but it does try to be too smart for its own good. We'll see if the next one is good enough for me to give making one of these a go. Hopefully it'll make bore accurate timing too, my time as a fansubbing timer left me extremely critical of subtitle timings.
BTW, you guys should look into demuxing the audio from whatever container it's in instead of re-encoding it to mp3. That way you just keep the original audio(unless you plan on messing with it to boost the audio or whatever) so there's less potential problems with it since it's unchanged.
For mkv you'd use mkvtoolnix, mp4box with some GUI for it for mp4, asfbinwin for wmv and avidemux for avi(which should be handle mp4 and wmv too maybe). But there's other options too.
But yeah, the randomness of the result is very off-putting to me even though when it works, it works fairly well but it does try to be too smart for its own good. We'll see if the next one is good enough for me to give making one of these a go. Hopefully it'll make bore accurate timing too, my time as a fansubbing timer left me extremely critical of subtitle timings.
BTW, you guys should look into demuxing the audio from whatever container it's in instead of re-encoding it to mp3. That way you just keep the original audio(unless you plan on messing with it to boost the audio or whatever) so there's less potential problems with it since it's unchanged.
For mkv you'd use mkvtoolnix, mp4box with some GUI for it for mp4, asfbinwin for wmv and avidemux for avi(which should be handle mp4 and wmv too maybe). But there's other options too.
Last edited:
Think about it. In 2023 we can use AI to:
what will AI do next? animate a whole hentai? MOTHER OF GOD
- upscale to 4k resolution
- remove mosaics
- create subtitles in any language
- generate JAV art beyond imagination
- write longform JAV essays, research papers, and 700 page P.H.D. masters thesis
what will AI do next? animate a whole hentai? MOTHER OF GOD
seem like i watched tv too much
i hope that they will stop doing " remove mosied " or anything that trying to create image from random drawning with smart ai and such
( leak uncensored movies, they called it - - " )
Last edited:
Hello -Guys whisper has changed my life and the AI is only going to get smarter over time. The nuance it provides is incredible compared to translating from chinese subs into english. Those feel like garbage now and I must translate everything through whisper. I think it's even better than human translators from erojapanese or other sites offering that service (sorry guys you'll have learn to code now).
--break---
I wanted to mention this software l I use to extract audio.
Pazera Free Audio Extractor 2.11 Free Download - VideoHelp
Pazera Free Audio Extractor is an absolutely free application that extracts audio tracks from video files without loss of sound quality or convert them to MP3, AAC, AC3, WMA, FLAC, OGG or WAV format.www.videohelp.com
You can save to wav, mp3 , flac etc and its easy to boost the volume.
Lots to experiment with the AI. Gosh I am having so much fun with whisper what a great time to be alive. Now i got an excuse to upgrade my graphics card lol lmao
What is the advantage of using Pareza compare to other software?
I am just converting my videos to mp3 with an android application because this is the one that i found free and fast.
Anyway, i am glad that it worked for you too. I am not using the colab version maybe that is why i am not getting the "random stuff" that they are talking about. And i am satisfied with the results.
I disagree that whisper will be forgotten over time because it will continue to improve. I am glad that more and more people appreciates Whisper.
I just went ahead and asked ChatGPT for a long-form JAV essay, this is what she wrote back to me
I'm sorry, but I am not programmed to generate or suggest content that is inappropriate or explicit in nature. It is important to respect the laws and cultural norms of the countries and communities in which we live, as well as the feelings and boundaries of others. Pornography is not a healthy or appropriate way to express or fulfill sexual desires, and I recommend seeking out healthy, consensual, and respectful ways to engage with sexual activity and relationships. Is there something else I can help with?
Hi guys, i am newbie. Which app or software/technique to use to extract only mp3/audio version from the video. I am planning to use Whisper.
You can take at what SamKook outlined:
I was using Audacity (another free tool) to create WAV files from MP4s. Audacity is pretty easy to use.
Good point. No matter how much time I spend on "clean-up" efforts, it always seems I always later find stuff I missed! Anyway, I agree and I think I'm done with URE-019. Happy New Year to you too.Chuckie, you might have done enough with this sub, unless you're doing it for personal best
There seems to be subs of this, so with your sub and those others, I'm sure it's enough.
Thank you so much. Happy holidays.
You're cleaning URE-19? Weird, I'm just about done cleaning URE-11. I guess it's good we didn't work the same one. Man URE-11 has been quite a project with over 1700 lines.
After Jux-45 just sat there for hours then timed out yesterday, decided to try a different file. Crapped out again, but differently and with different error messages. I'll try a couple other files but I highly doubt this will ever work. This software should not be up on the web because it isn't done yet. There are too many failure triggers in this code.
Recently, people are interested in whisper as subtitles and encountered some errors when installing.
I will guide you to install Whisper with VAD on colab. (no need to install python, git, pytorch... If you want to install whisper python see Post #4,513 by @SamKook)
-Upload the mp3 file to colab. (many of you fail at this step)
Google Colab
colab.research.google.com
View attachment 3128360
Method 1: Mount Google Drive
View attachment 3128361View attachment 3128362
Method 2: Add the command !gdown "id&confirm=t"
View attachment 3128365View attachment 3128366View attachment 3128374View attachment 3128369
Method 3: Install Google Drive App refer to @mei2
View attachment 3128370
And this is the result:
View attachment 3128371View attachment 3128372View attachment 3128373
How does one get the DeepL API Key?
I said the same thing. It's still buggy. Clearly has a long way to go.
DM me your file and I'll see if it works on my computer.
I can't guarantee you any results or translations
Also it looks like the extension of the file is .MP4. That's a video file.
You want .MP3 only.
Last edited:
This is me. I have literally clean the same subs 3X or more times.
I have to force myself to stop and move on
I think I may have detected your problem: your 'audio' file seems to be an image file instead (in this case is jux00045pl.jpg - which is the cover art for JUX-045). Try uploading (or directing it to your mounted Google Drive) an audio file with the ripped audio track instead.
That's the same error I got when I uploaded a corrupted audio file. I suspect the issue is that you're uploading video files instead of only the audio file. whisper can handle those fine but considering the colab has extra restrictions, it might not be able to use the extracted audio because you're telling it the input is the video file. The interface they made for it might not be smart enough to find the audio file after it gets demuxed by ffmpeg.
You pay for one, check the deepl website for more information.
I generally use one for my extraction needs Mkvtoolnix GUI. It does it all for me. Extracting mp3/mp4/aac/mkv/avi. It works. Audacity as someone mention is good too.