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

[ElliotAlderson]

I got curious so I looked up MIAE-208. It looks like a good movie --good choice. One thing that might help you with your work is to use an algorithm like Whisper to produce a baseline transcription with timestamps. Then use the baseline to layer (your) human translation on it. I'm guessing that can speed up the work quite a bit.

As I'm writing this I started thinking that I can just run the baseline right away and can pm you that version. Will be fun.

I don't know how to use Whisper, sounds really complicated, and it sounds really GPU heavy (the notebook I use to translate this is not that good at all) but If I managed to get it working yes it could theorically speed up my work by a significant margin.

The translation is very easy to me, they speak cleary and close to the microphone so I can tell with 100% accuracy what they are saying. I've translated about 50 minutes of the movie and only had trouble with one specific Sora Shiina line that I couldn't hear because the girls were laughing, so I had to use machine translation on that line and it also didn't helped much, so I had to improvise something that made sense.

My main problem with MIAE-208 is that is a 3h20m dialogue heavy movie (the girls talk every 3 seconds even when having hardcore sex) - every NTR movie is like that because of their gimmick. So it takes a looong time to translate because I have to make the timestamps too.

 

[ElliotAlderson]

Guys, use Whisper if you can, translating using my arcaic method is like trying to play piano with knife and fork.

 

[Chuckie100]

URE-074 Ayumi Ryo X Ripe Komi! !! Original: Everyone Didn't Go To The Spot Sale Silently To His Wife​

I found a machine translation for URE-074. I cleaned it up a bit and re-interpreted some of the meaningless 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. Not my favorite genre but I liked the actress. Oh yea, I also twisted the storyline to be Aunt-Nephew relations to spice it up, my apologies to the purists out there! Anyway, enjoy and let me know what you think.​

 

[maelstrom9999]

Whisper just seems to die on me like almost immediately after I load the audio file. Does it work with all audio files or does it just crash with some of them? I could always try some other videos.

 

[SamKook]

Whisper just seems to die on me like almost immediately after I load the audio file. Does it work with all audio files or does it just crash with some of them? I could always try some other videos.

Should handle pretty much any audio file type, pretty sure it install ffmpeg as a dependency to deal with that. Without an error message, it's impossible to say what the problem actually is, but a likely cause would be that you're using a model too big for your GPU VRAM or you don't have an nvidia gpu or you're using the wrong cuda version for your gpu.

Edit: I checked and it does indeed install a python version of ffmpeg so except maybe some super rare audio formats, it'll be able to use anything as long as it's not corrupt.

 

[maelstrom9999]

Should handle pretty much any audio file type, pretty sure it install ffmpeg as a dependency to deal with that. Without an error message, it's impossible to say what the problem actually is, but a likely cause would be that you're using a model too big for your GPU VRAM or you don't have an nvidia gpu or you're using the wrong cuda version for your gpu.

Edit: I checked and it does indeed install a python version of ffmpeg so except maybe some super rare audio formats, it'll be able to use anything as long as it's not corrupt.

I have a geforce 2070. Pretty sure that's good enough?

Whisper isn't even outputting anything. I just load the file and arrow turns red, then when I put the pointer on it, it says the last attempt was unsuccessful and lasted for .4 seconds. This is the web based version.

 

[SamKook]

The RTX 2070 "only" has 8GB of VRAM so the large model wouldn't work with it since it requires 10, but any other model will be ok and the cuda version should be fine although I can't find out the exact requirement for whisper.

I have no clue how the web based version works, but it likely hides the output error if there's one so that makes figuring the issue a lot harder. If you can also call whisper from the command line, you should give that a try to see if you get a more descriptive error message, assuming you weren't using the large model before.

In command line, you just navigate to where your audio/video is(or specify the full path of the audio in the command) and type something like this to get it working:

whisper "audio_or_video_file.whatever" --language Japanese --task translate --model medium

 

[maelstrom9999]

The RTX 2070 "only" has 8GB of VRAM so the large model wouldn't work with it since it requires 10, but any other model will be ok and the cuda version should be fine although I can't find out the exact requirement for whisper.

I have no clue how the web based version works, but it likely hides the output error if there's one so that makes figuring the issue a lot harder. If you can also call whisper from the command line, you should give that a try to see if you get a more descriptive error message, assuming you weren't using the large model before.

In command line, you just navigate to where your audio/video is(or specify the full path of the audio in the command) and type something like this to get it working:

whisper "audio_or_video_file.whatever" --language Japanese --task translate --model medium

In the web based version, I click the arrow key where it says "run Whisper" then a few seconds later the arrow key turns red. Placing the pointer on it reveals the following tooltip:

"run cell (ctrl+enter)
cell executed since last change
previous execution ended unsuccessfully

executed at 7:11 p.m. (1 minute ago)
executed in .334s"

Pretty sure I'm supposed to cut and paste the path of the audio file I loaded in the previous step into the "audio path" field under run Whisper. Which I did. But I still feel that I'm not doing the right thing.

 

[SamKook]

Ok, so it's not running it on your own pc but it the colab thing? If so, your gpu is irrelevant, unless you followed what Epinwinrar posted to install the webUI locally, in which case do what I suggested in my previous post to test it.

It tells you it failed for some reason but doesn't say why so unless there's a log somewhere else with more information, there's no way to tell what the issue is.

 

[ElliotAlderson]

I translated 1/3 of MIAE-208.

Tiresome, but feeling pretty good about the results.

I'll finish in about a week.

 

[maelstrom9999]

Ok, so it's not running it on your own pc but it the colab thing? If so, your gpu is irrelevant, unless you followed what Epinwinrar posted to install the webUI locally, in which case do what I suggested in my previous post to test it.

It tells you it failed for some reason but doesn't say why so unless there's a log somewhere else with more information, there's no way to tell what the issue is.

Sorry, I had missed it, but it does describe the error more fully below. That last line is telling me that it couldn't find my audio file. Not sure what to do to make it find the file. I followed the instructions for how to upload it. It pops up in a second window and plays.

NameError Traceback (most recent call last)

<ipython-input-4-8dadf0f27685> in <module>
56 try:
---> 57 audio_path = uploaded_file
58 if not os.path.exists(audio_path):


NameError: name 'uploaded_file' is not defined


During handling of the above exception, another exception occurred:


ValueError Traceback (most recent call last)

<ipython-input-4-8dadf0f27685> in <module>
59 raise ValueError("Input audio not found. Is your audio_path correct?")
60 except NameError:
---> 61 raise ValueError("Input audio not found. Did you upload a file?")
62
63 out_path = os.path.splitext(audio_path)[0] + ".srt"


ValueError: Input audio not found. Did you upload a file?

You can try it yourself here:

Google Colab

colab.research.google.com

Takes about 2 minutes to get it started. See what happens.

 

[asledan]

more subs for yall, requests can go to DM but I don't do movies that I'm not interested in. All subs are done through collab with no additional touch ups.

RBD-975

RBK-786

JUC-899

PRED-135

PRED-151

EBOD-721

 

[SamKook]

Sorry, I had missed it, but it does describe the error more fully below. That last line is telling me that it couldn't find my audio file. Not sure what to do to make it find the file. I followed the instructions for how to upload it. It pops up in a second window and plays.



You can try it yourself here:

Google Colab

colab.research.google.com

Takes about 2 minutes to get it started. See what happens.

You probably didn't copy the path properly. If you upload to the colab, it should be like this:


Click the 3 dots you see when you hover over the file, copy path and then paste in the input.


Doesn't seem very happy with an opus file for some reason(ffmpeg 100% support it) or I did something wrong but I'm not getting an input error.
Edit: Because I improperly demuxed it and it's a garbage file that doesn't work so that explains that.

 

[maelstrom9999]

You probably didn't copy the path properly. If you upload to the colab, it should be like this:
View attachment 3127558

Click the 3 dots you see when you hover over the file, copy path and then paste in the input.


Doesn't seem very happy with an opus file for some reason(ffmpeg 100% support it) or I did something wrong but I'm not getting an input error.
Edit: Because I improperly demuxed it and it's a garbage file that doesn't work so that explains that.

How are you physically uploading the file? I have done it by moving the file into the frame on the left, and I have also done it by hitting the upload button then navigating its file path. Both with the same result: the file appears at the bottom of the window, not in the file list like it is in yours. And you can't copy the path. It says they are in "session storage."

 

[SamKook]

I just dragged it there. Could be ad or script block extensions causing upload issues or a browser that doesn't support the upload procedure so trying a different one might help, i used brave which uses the chrome engine.

Could also be you're not waiting for the file to finish uploading, the circle on the right of it when it's at the bottom needs to fully become yellow for the upload to be complete.

 

[avatarthe]

Anyone have succeeded using the option to separate vocals from background sounds in the whisper Colab? Everything I try it I get an error after the separation it’s done and it crashes

 

[Prinsipe]

Below is a sample of transcription from Whisper. I clean it up a little bit with the pronouns like I/you, he/she, etc. I also transcribed the same movie in Capcut and the result is similar in meaning. If someone wants to review if the transcriptions are correct or wrong, then just message me so I can give you the file.

I believe that the Whisper transcriptions are correct because they convey similar meanings after testing the same movie with Capcut. In addition to that, the transcription matches the scenario of the scene.

If the transcription results of whisper did not satisfy you after using it, then maybe it satisfied someone else. Just don’t expect too high that the result is close to human transcriptions.

And to those who are getting repeated lines, it happened to me too. The solution to that is to run the same file again, maybe there are some errors since I am running the whisper with the web version. After running it again, the lines don’t repeat anymore, and you can compare your first result to the second one. Also, I am converting the video file to MP3 with the highest volume possible in the converter. I don’t know if this will work for you, but it worked for me.

The sample below is a 41-minute video that generated 600+ lines.

 

[SamKook]

Even direct english transcriptions aren't perfect with whisper, it can invent stuff it didn't hear but makes sense in the sentence.

A funny one I encountered was before a song the guy said 1,2,1,2,3,4 to start it, but whisper continued counting until 13.

 

[Prinsipe]

It makes sense in a sentence, but does it make sense in a scenario? In my experience, the sentence makes sense with the scenario. I am not saying that the whisper is perfect and will transcribe all the words correctly and accurately. The important thing is that the context of the scenario or story is there.

My question is, how often does Whisper invent stuff based on your experience?

Thank you for your input about Whisper inventing stuff, I will post it here if ever I encounter that scenario.

 

[alverick]

Hi everyone.
Finally, after been reading this thread for quite a long time, I'm in the position to start giving back.

I always wanted to translate JAV but because I have no knowledge at all of Japanese language it was nearly imposible for me to get some results with a minimun of quality ( imo ) further that a google translation, which in many times, the result was nearly a comedy in my experience.

In the last few days that I was catching up with the thread I discovered the Whisper ( thanks to everyone involved in bringing it up to this forum ) and last night I tried my very first translation with a movie I always was courious about.

I have noticed that there are some lines missing and at some points, the trtanslation is not accurate, but still, is a great move foward to get something with quality.

My translation is a work in progress, and I invite everyone who can improve it to do so. My intention is to provide "a base file", so people who actually can provide quality subs can work with them and fill the blanks faster that having to do the whole proccess from the beginning.

So from now on, everyone who knows more about, fell free to take "my" files and make them better so the comunity can enjoy them.

Have a great day guys, thanks to Whisper, a new shiny era is starting.