Recent content by hobbies

Seems soo much more accurate. I have a favour to ask, is there anyway you can teach me to set it up or the commands?

I have a good GPU (6 gb vram) but im using whisper on my computer using cmd prompt. e.g. whisper --model large --language ja --task translate "C:\Users\user\Downloads\Video\1ha.mp3" I want to use the VAD system instead, do you have a script or a tutortial on that?

which colab uses this?

Any chance you can offer a tutorial on how to use that? I went to the site to where or how i can get the model t hey uploaded but i couldnt find it For now im just using cmd whisper command+ audacity method

Hmm interesting

as always, thank you for your help !

There arent anymore. I think all the crazy types of JAV hit their peak in 2013-2017. Now the stuff that comes out isnt as crazy or freaky.

I get the following error when im using whipser in CMD: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See...

Thanks! Also i had better luck with Audacity and its free. Have you or anyone here tried WHISPER LIVE transcribe?

Thanks Chuckie. Mine repeats the same phrases and missing dialog (old videos from 2012) so i figured it must cause of the wrong audio format im using.

I see, thanks!!

Whats the most accurate model of whisper? As per screenshot there are lots lol

@Chuckie100 I'm wondering what are your whisper settings? model_size? language? translation_mode? vad_threshold? chunk_threshold? max_attemps? And what audio code do you use? e.g. aac / mp3 Your translations are superior

Are there any JAV sites that break up the movie into smaller scenes? E.g. a 4 hr movie

Seems the issue from the error had nothing to do with that. I had to use an older version of PIL . A quick google search fixed the issue for me (forcing python to install an older version of PIL). Thanks for replying though :D