I’m assuming that it worked for full and mergedvad transcription?
I’m surprised that it would work for those but not for singlevad, unless there is a weird .wav file that is created during the process, maybe an empty file or something.
Can you try running whisper-faster directly and tell me if there is an error or something?
In short, this command, in a command prompt, while replacing PATHTOPURVIEW, PATHTOVIDEO, and DATETIME with value for your machine/context:
Looks like it was actually processing, the 0/1969 wasn’t updating so I thought it was was looping. All good here! One thing I noticed for the AI prompts, is it explicitly states the man does not speak. I am using this method to translate a normal JAV scene. Do you have an pre-made verbiage that doesn’t have language regarding ignoring the man’s speech? If not I can just edit myself. Thanks!
Are you on an English OS? Because I’m parsing the output of whisper to show the progression. Right now, I’m looking for “Starting …filename…”. If whisper writes something in french, for example, “Démarrage …filename…”, I won’t be able to update the progression but, like you say, it will still work in the background.
Also, singlevad takes more time than the other type for transcription so I can understand why you thought it was stuck on a 1969 files batch.
As for the VR/Not-VR, if you use sonnet-3.5 or any ‘high quality’ AI, you can simply write it in the context.
Something like this in the first subtitle of the file: {Context:This is not a POV or VR scene, its a 2D scene. There is 3 peoples in the room that will talk. A woman, who's blah blah, her boyfriend, ...}
You might want to add {Talker:Boyfriend} on each subtitle but, with 1969 subtitles, it might be a serious pain in the ass so you can hope that the AI will be able to pick up who’s talking and keep a ‘coherent’ understanding of the scene.
If you have to change the context information later in the file (i.e. if the setup of the scene has changed or something), always start by repeating that part.
Yes I am using an English OS. It was running in the background so we’re all good.
Thanks for the advice with the context, I will try that, though I’m starting to feel the effort isn’t worth it for the length of the video. I might just stick to shorter VR scenes for now haha.
The main feature of this one is that it’s easier to get translations when a transcription item overlaps multiple timings (see Parts argument in the release note).
I’m curious if anyone has tried out the whisper model v3 turbo, it processes the files incredibly quickly, from my experience up to 4 times quicker. I don’t know how well it holds up in terms of accuracy though.
I’m having the same error as the other user. And am missing the
preprocessor_config.json from the folder. How do I change the name of the download you provided? can’t seem to get rid of the .txt at the end
I also can’t figure out how to edit the batch file in the other solution you provided
Best regards!
ignore that, I figured it out but am still getting the error
Hey @Zalunda how do we exactly install FunscriptToolbox? Are you supposed to only unzip it? Cause everytime i try to open or run the FunscriptToolbox.exe my command line instantly closes. I’ve followed the rest of the steps no problem and I seem to keep receiving this error messaging when I try to run --FSTB-CreateSubtitles.1.7.bat. I’ve downloaded FunscriptToolbox-1.3.9.zip from the github. Many thanks
When you say manually choose the which subtitle you prefer in the subtitle edit program do you just go in the textbox and delete the ones you don’t want for each line?
Yes, delete everything in the textbox except the one you like (and better fit what’s happening in the scene). Or use your own text, if you think of something that sounds better than the translations provided.
Yes, everything is controlled by the SubtitleGeneratorConfig.json file:
You could remove everything except “mergedvad” in the TranscriptionsOrder array (especially “*” which include all the transcription not listed in the array) and, at least, remove "** in the TranslationsOrder array (which, in this case, include “google”).
If you end up with a single Translation after you have filtered those lists, you could also ensure that “AutoSelectSingleChoice” is true. With those settings, unless there aren’t multiple transcriptions attached to a subtitle, or a single translation overlaps multiple subtitles, the text for a subtitle will only be the chosen translation.
You should be able to change the config file, and rerun the application, and the .wip.srt file will be generated with the new rules.
This won’t fix the problem because it is not in FunscriptToolbox but in the installation/configuration of Whisper. I added the full output of Whisper in FunscriptToolbox’s console output. It will also include the exact ‘command’ that was executed (line after “Command:”).
You could see (or tell me) what error is outputted by Whisper.
If there is no obvious error in the log, you might have to open a command prompt in the same folder as --FSTB-CreateSubtitles.1.6.bat and execute the command that FunscriptToolbox outputted. This will run Whisper directly. You might see other error messages that FunscriptToolbox didn’t have access to.
For example, stuff related to nvidia/cuda library,
If you have that specific error, you’ll have to install something like this:
The solution was to edit the --FSTB-SubtitleGeneratorConfig.json file, and under the path that points to faster-whisper-xxl.exe, change the next line to
“AdditionalParameters”: “–compute_type float32”
After that change, then the batch file works with no issue.
