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

Electromog said:
I use standard whisper, any idea whether faster-whisper results are better, worse or about the same? Since they use hte same models I'd expect similar results, but I'd like to be sure.
Click to expand...
I can't speak for accuracy, but I assume it will be faster? Using RTX 3050 with 8GB vram and the large-v2 model, a typical 2-hour movie takes about 10–15 minutes to complete. How about yours?
 
I guess I should try to do the same movie with both and compare both time and sub quality. I may have some spare time for that this weekend. It will most likely be faster, but I don't use it that often so quality is more important to me than speed.
 
  • Like
Reactions: krack
krack said:
edited: On the latest version, the standalone .7z file comes with a One Click Transcribe.bat file. Now you can drag and drop file or files or folder onto this shortcut to do automatic one click transcriptions. So you can skip steps 3,4,5 below.

If you're on Windows, here is a standalone version:
  1. Go to Faster Whisper XXL Releases and download the latest Windows version.
  2. Extract the .7z file and navigate to the folder: Faster-Whisper-XXL.
  3. Place your movie file inside this folder.
  4. In the folder, type cmd in the address bar and press Enter.
  5. In the command prompt, type the following command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt​
6. This will start the process using your CPU.​

For NVIDIA GPU Acceleration:​

  1. Download the required CUDA files from CUDA Dependencies for Faster Whisper and extract all contents into the same Faster-Whisper-XXL folder.
    The files are:
    • cublas64_11
    • cublasLt64_11
    • cudnn_cnn_infer64_8
    • cudnn_ops_infer64_8
    • zlibwapi
  2. Run the same command as above and the process will start with CUDA, If it doesn't, add --device cuda to the command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt --device cuda

Additional Information:​

For more details about arguments and options, type the following in the command prompt:

Faster-Whisper-XXL -h​
​
This should get you started. For more accurate results, you might want to try the medium or large model with a capable GPU.
Click to expand...

the large model with CUDA looks good, the tiny is fast as hell but gives me zero words inside the srt
it took 30mins to create the full sub using my relic computer, or maybe it'll be faster if i'm not multi-tasking on it. lol
and the sub itself? (ZOZO-060) ... yes it's good, some words are kinda off like using the words cool instead of great, mixing-up those I and You, write instead of draw and some minor bs. but hey! that's why we are here. haven't try the medium yet. tell us if some of you have time.
 

Attachments

  • cmd - large.PNG
    cmd - large.PNG
    56.3 KB · Views: 26
Last edited:
  • Like
  • Wow
Reactions: Askender, krack and skici31

[Reducing Mosaic]JUY-928 I Could Never Tell My Wife That I Had A Pregnancy Fetish For My Mother-in-law… I Went On A 2-Day, 1-Night Hot Springs Resort Vacation, And Lost My Mind Creampie F**king Her My Mother. Maki Hojo​

juy928pl.jpg

I recently downloaded this reduced mosaic of an oldie Mother-Son themed JAV movie starring one of my favorite MILFs. I used Whisper Colab to create this Sub and I also found a Sub on SubtitleCat.com that I used to fill in missing dialog and provide better clarification in several places...and oh yea, I enhanced it a tad! Finally, I attempted to clean it up a bit and re-interpreted some of the meaningless/ "lewd-less" dialog. Again, I don't understand Japanese so my re-interpretations might not be totally accurate but I try to match what's happening in the scene. Anyway, enjoy and let me know what you think​

 

Attachments

  • Like
Reactions: xsf27, Sedas, Taako and 5 others
krack said:
edited: On the latest version, the standalone .7z file comes with a One Click Transcribe.bat file. Now you can drag and drop file or files or folder onto this shortcut to do automatic one click transcriptions. So you can skip steps 3,4,5 below.

If you're on Windows, here is a standalone version:
  1. Go to Faster Whisper XXL Releases and download the latest Windows version.
  2. Extract the .7z file and navigate to the folder: Faster-Whisper-XXL.
  3. Place your movie file inside this folder.
  4. In the folder, type cmd in the address bar and press Enter.
  5. In the command prompt, type the following command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt​
6. This will start the process using your CPU.​

For NVIDIA GPU Acceleration:​

  1. Download the required CUDA files from CUDA Dependencies for Faster Whisper and extract all contents into the same Faster-Whisper-XXL folder.
    The files are:
    • cublas64_11
    • cublasLt64_11
    • cudnn_cnn_infer64_8
    • cudnn_ops_infer64_8
    • zlibwapi
  2. Run the same command as above and the process will start with CUDA, If it doesn't, add --device cuda to the command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt --device cuda

Additional Information:​

For more details about arguments and options, type the following in the command prompt:

Faster-Whisper-XXL -h​
​
This should get you started. For more accurate results, you might want to try the medium or large model with a capable GPU.
Click to expand...
This is great stuff, and a fantastic tutorial but wanted to mention that faster-whisper-xxl is integrated into SubtitleEdit, which has a great GUI Interface, the only think to be cautious about is not to us the .7z file that SE point for you to download it still points to to 192.3.4 version but the latest currently 194.5 and the follow the instructions. The other point is that it's no longer necessary to download CUDA files xxl folder. XXL will detect CUDA and use it automatically. I tested that and can follow the usage using GPU TWEAK tool.
 
  • Like
Reactions: krack and Imscully
krack said:
I can't speak for accuracy, but I assume it will be faster? Using RTX 3050 with 8GB vram and the large-v2 model, a typical 2-hour movie takes about 10–15 minutes to complete. How about yours?
Click to expand...
That is my experience as well faster whisper is faster and 10-15 minutes for 2 hour movie is average, but you need a good gpu have rtx3060 made a huge difference
 
krack said:
edited: On the latest version, the standalone .7z file comes with a One Click Transcribe.bat file. Now you can drag and drop file or files or folder onto this shortcut to do automatic one click transcriptions. So you can skip steps 3,4,5 below.

If you're on Windows, here is a standalone version:
  1. Go to Faster Whisper XXL Releases and download the latest Windows version.
  2. Extract the .7z file and navigate to the folder: Faster-Whisper-XXL.
  3. Place your movie file inside this folder.
  4. In the folder, type cmd in the address bar and press Enter.
  5. In the command prompt, type the following command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt​
6. This will start the process using your CPU.​

For NVIDIA GPU Acceleration:​

  1. Download the required CUDA files from CUDA Dependencies for Faster Whisper and extract all contents into the same Faster-Whisper-XXL folder.
    The files are:
    • cublas64_11
    • cublasLt64_11
    • cudnn_cnn_infer64_8
    • cudnn_ops_infer64_8
    • zlibwapi
  2. Run the same command as above and the process will start with CUDA, If it doesn't, add --device cuda to the command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt --device cuda

Additional Information:​

For more details about arguments and options, type the following in the command prompt:

Faster-Whisper-XXL -h​
​
This should get you started. For more accurate results, you might want to try the medium or large model with a capable GPU.
Click to expand...
Thanks for the tutorial. However I'm not able to get it up and running get error saying "app cannot run on your computer. contact creator"! I'm running a ASOCK Z77 Extreme 4 MB with a i5 (3.4 GHz) CPU and 16GB RAM and running Windows 10 Pro. Also have a NVIIDIA GTX1060. Error message occurs even without using CUDA. Maybe my computer is just too old?? Anyway there is always Colab Whisper...at least so far.

I did a little more research and I think my computer, GPU and Window 10 Pro operating system should handle faster-Whisper-XXL I probably am missing something in the download/install but too brain dead to explore anymore tonight! Any other thoughts out there?

Good Morning! I think I may have messed up on the installation after installation I moved Faster-Whisper to my "C" drive may have lost something in the move. Am retrying the install. Will keep this saga alive until I get it or give up!

UPDATE:
Reinstalling Faster-Whisper-XXL and CUDA seemed to help...at least I didn't get the error message that the Program could not run on my computer; however, there seems to be some files missing; eg, Whisper reported that it could mot find the "models" file. I did a little more Google searching and found this ad: https://apps.microsoft.com/detail/9nmms8xgx8vn?hl=en-US&gl=US . Decided to give it a try to save what little hair I have left! Once purchased the MS Store will download it and install it on your computur (~4GB). It looks promising it ran for 10-12 mins and produced a srt file similar to what WhisperColab produces. Excited to try varing some of the advanced setting to see what effect they might have.. It's kinda neat...it even has a GUI interface for software dummies like me!
 
Last edited:
  • Like
Reactions: freshmilk69, krack, Taako and 1 other person
Chuckie100 said:
Thanks for the tutorial. However I'm not able to get it up and running get error saying "app cannot run on your computer. contact creator"! I'm running a ASOCK Z77 Extreme 4 MB with a i5 (3.4 GHz) CPU and 16GB RAM and running Windows 10 Pro. Also have a NVIIDIA GTX1060. Error message occurs even without using CUDA. Maybe my computer is just too old?? Anyway there is always Colab Whisper...at least so far.

I did a little more research and I think my computer, GPU and Window 10 Pro operating system should handle faster-Whisper-XXL I probably am missing something in the download/install but too brain dead to explore anymore tonight! Any other thoughts out there?

Good Morning! I think I may have messed up on the installation after installation I moved Faster-Whisper to my "C" drive may have lost something in the move. Am retrying the install. Will keep this saga alive until I get it or give up!

UPDATE:
Reinstalling Faster-Whisper-XXL and CUDA seemed to help...at least I didn't get the error message that the Program could not run on my computer; however, there seems to be some files missing; eg, Whisper reported that it could mot find the "models" file. I did a little more Google searching and found this ad: https://apps.microsoft.com/detail/9nmms8xgx8vn?hl=en-US&gl=US . Decided to give it a try to save what little hair I have left! Once purchased the MS Store will download it and install it on your computur (~4GB). It looks promising it ran for 10-12 mins and produced a srt file similar to what WhisperColab produces. Excited to try varing some of the advanced setting to see what effect they might have.. It's kinda neat...it even has a GUI interface for software dummies like me!
Click to expand...
that is great, you can use SubtitleEdit to run faster-whisper-xxl and that also provide gui interface to download models v1,v2,v3, distil etc.
 
  • Like
Reactions: freshmilk69
Chuckie100 said:

MIMK-054 My Aunt's Body Is Too Pleasant "Late Part" ~ My Aunt Was Super Superstar ~ Haruna Hanana​

mimk054pl.jpg

I really liked this series (MIMK-052, 054 and 084) starring Hana Haruna and her big boobs! I recently found "reduced mosaic" downloads of all three videos and decided to revisit my older copies of the censored videos. I had previously commissioned EroJapanese to Sub MIMK-052 and I had previously downloaded MIMK-054 from JavGuru's hard coded version of MIMK-054. Although the hard-coded version was passible, I never was satisfied with it. After downloading the 'reduced mosaic" version of the video, I found a Sub on SubtitleCat that seemed to match the Subs in JavGuru's video. I used it, plus I created a Whisper version to provide additional clarity in several places. I attempted 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.
Click to expand...
Hi Chuckie! Just wanted to drop by and say thanks for the subs you and others have posted here in this thread! Love it! I've been on a huge Hana Haruna binge lately and this series with her nephew is gold! She has so many delicious mom titles out there as well. Again thanks a bunch!
 
  • Love
Reactions: Chuckie100 and Imscully
Thanks to bestbuy for his info on SubtitleEdit and the inclusion of FasterWhisperXXL capabilities. I ran WhisperColab, The SubtitleEdit FasterWhisperXXL and the FasterWhisperXXL from the Microsoft Store (that I had purchased), using RCT-746 as a test case. My initial assessment is that WhisperColab might be a little better. Both of the FasterWhisperXXL produced Subs appear to be pretty similar and could be used to fill in missing dialog and provide clarification. I realize this is a single data point and may not represent all cases but I think I will continue my subscription to WhisperColab and use the SubtitleEdit FasterWhisperXXLto help in the editing (while also continuing evaluation of FasterWhisper. Anyway I'd love to hear about other's experiences with FasterWhisperXX and what your assessment of FasterWhisperXXL is.

One last thing: FasterWhisperXXL is indeed faster than using WhisperColab, mainly I think because one does not have to upload an audio file.
 

Attachments

  • Like
Reactions: xsf27, DapDunlap and Imscully
DapDunlap said:
Hi Chuckie! Just wanted to drop by and say thanks for the subs you and others have posted here in this thread! Love it! I've been on a huge Hana Haruna binge lately and this series with her nephew is gold! She has so many delicious mom titles out there as well. Again thanks a bunch!
Click to expand...
Yea, I'd love to "binge" on Hana's body too! ;)
 
  • Like
Reactions: DapDunlap

[Reducing Mosaic]RCT-746 Target Wary Mom Chibikko Sexual Harassment Molester Corps Bathing Hen Request SP​

1rct746pl.jpg

I recently downloaded this reduced mosaic of an oldie Mother-Son themed JAV movie. I used Whisper Colab to create this Sub and I also used a Sub created with FasterWhisperXXL that I used to fill in missing dialog and provide better clarification in several places...and oh yea, I enhanced it a tad! Finally, I attempted to clean it up a bit and re-interpreted some of the meaningless/ "lewd-less" dialog. Again, I don't understand Japanese so my re-interpretations might not be totally accurate but I try to match what's happening in the scene. Anyway, enjoy and let me know what you think​

 

Attachments

  • Like
  • Love
Reactions: xsf27, DapDunlap, JAVinsight and 1 other person
krack said:
edited: On the latest version, the standalone .7z file comes with a One Click Transcribe.bat file. Now you can drag and drop file or files or folder onto this shortcut to do automatic one click transcriptions. So you can skip steps 3,4,5 below.

If you're on Windows, here is a standalone version:
  1. Go to Faster Whisper XXL Releases and download the latest Windows version.
  2. Extract the .7z file and navigate to the folder: Faster-Whisper-XXL.
  3. Place your movie file inside this folder.
  4. In the folder, type cmd in the address bar and press Enter.
  5. In the command prompt, type the following command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt​
6. This will start the process using your CPU.​

For NVIDIA GPU Acceleration:​

  1. Download the required CUDA files from CUDA Dependencies for Faster Whisper and extract all contents into the same Faster-Whisper-XXL folder.
    The files are:
    • cublas64_11
    • cublasLt64_11
    • cudnn_cnn_infer64_8
    • cudnn_ops_infer64_8
    • zlibwapi
  2. Run the same command as above and the process will start with CUDA, If it doesn't, add --device cuda to the command:

    faster-whisper-xxl.exe "C:\yourmediafileslocation\abc-123.mp4" --language ja --model tiny --task translate --output_format srt --device cuda

Additional Information:​

For more details about arguments and options, type the following in the command prompt:

Faster-Whisper-XXL -h​
​
This should get you started. For more accurate results, you might want to try the medium or large model with a capable GPU.
Click to expand...
Thanks, it works nicely on my i7 with 4060t ti GPU. I ended going with large-V2. Takes anywhere bt 4 to 8 mins, Here's any example:

1733455132394.png
 
  • Like
  • Love
Reactions: mei2, krack and Chuckie100
I have noticed that FasterWhisperXXL seems to produce more "hallucinations" than WhisperColab. I think I remember that WhisperColab had an update to try and limit hallucinations but I couldn't find the reference.
 
  • Like
Reactions: ericf
The colab uses a separate VAD system to handle the speech detection better than whisper alone and it also splits the audio in many small parts so that helps with hallucination.
 
  • Like
  • Love
Reactions: ericf and Chuckie100
Most if not all linked in this thread do, that's why all the ones linked in my tutorial(see signature) are called something like whisper with silero VAD.
 
  • Like
Reactions: Imscully
You must log in or register to reply here.
Top Bottom