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

I'm curious, how different was the faster whisper from the colab version? Were they similar quality or was one notably better than the other?
The Faster Whisper was a bit faster... mainly, I think, due to the time it took to upload the audio file to Colab. Quality seems to vary... sometimes Whisper Colab is better, sometimes Faster Whisper is better. Probably not the definitive answers you were looking for but this is what I've experienced.
 
Last edited:

[Reducing Mosaic]DASS-442 After A Month Of Showering My Mother With Love And Affection Every Day, I Had Sex With Her Again And Again, Making A Baby. Reina Kuroki​

1737846978872.png

I downloaded this recently released, reduced mosaic JAV starring a Milf with huge boobs and had to Sub it. I used Purview Faster Whisper XXL to create this Sub and I also 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

The Faster Whisper was a bit faster... mainly, I think, due to the time it took to upload the audio file to Colab. Quality seems to vary... sometimes Whisper Colab is better, sometimes Faster Whisper is better. Probably not the definitive answers you were looking for but this is what I've experienced.
I have not used Collab. Within SE there are options to usee use CPP or Faster Whisper etc. I found Faster Whisper to be faster than CPP. For me what speeded up the transcription was getting a good GPU after I installed RTX3060 with 12gb it goes much faster but thats an expensive upgrade. Some people said *gb is enough. But you need a card that uses CUDA. Also recently I discovered a parameter for Faster Whisper called -batched which became available from r239.1, it does batched inference and reduced the subtitle creation by 50%. Of course that may introduce more hallucinations.
The Faster Whisper was a bit faster... mainly, I think, due to the time it took to upload the audio file to Colab. Quality seems to vary... sometimes Whisper Colab is better, sometimes Faster Whisper is better. Probably not the definitive answers you were looking for but this is what I've experienced.
 
I have not used Collab. Within SE there are options to use CPP or Faster Whisper etc. I found Faster Whisper to be faster than CPP. For me what speeded up the transcription was getting a good GPU after I installed RTX3060 with 12gb it goes much faster but that's an expensive upgrade. Some people said 8gb is enough. But you need a card that uses CUDA. Also recently I discovered a parameter for Faster Whisper called -batched which became available from r239.1, it does batched inference and reduced the subtitle creation by 50%. Of course that may introduce more hallucinations.
 
  • Like
Reactions: Chuckie100
I have not used Collab. Within SE there are options to use CPP or Faster Whisper etc. I found Faster Whisper to be faster than CPP. For me what speeded up the transcription was getting a good GPU after I installed RTX3060 with 12gb it goes much faster but that's an expensive upgrade. Some people said 8gb is enough. But you need a card that uses CUDA. Also recently I discovered a parameter for Faster Whisper called -batched which became available from r239.1, it does batched inference and reduced the subtitle creation by 50%. Of course that may introduce more hallucinations.
Yea, I'm running an old Intel i7 cpu and recently got a NVDIA1060 type GPU. It has 6gb but it was in the price range what I was willing to pay. I haven't really timed it but it probably takes ~30+ mins for a 2 hour movie. Most of my time is then spent editing the Whisper crap...although I shouldn't bad mouth Whisper (in any form) because it's the best we have for now.