FFAStrans forum

Hi emcodem! Thanks for reply. I've tested a little bit more. And as far as I can see it is related to those urls where a playlist exists. But: in my case in FFAStrans playlist is not allowed and regardless of that it won't download those which are part of a playlist. If there is no playlist then dow...

Hi Admin Team, Hope you are fine. I have a problem. When using Youtube decoder the step "Extracting media information" takes forever. File will not be downloaded. It worked until it didnt. That makes me very sad. As far as I can see YT-DLP within ffastrans folder is the latest release. Whe...

emcodem wrote: ↑Fri Jan 26, 2024 10:56 am In a few days, steinar should release ffastrans 1.4

Aha!

Heyho Emcodem, Thanks for your detailed reply. To be clear: I didn‘t want to push you in any kind/direction of enhancing those stuff. I know that you are a prodigy among programmers and I‘m a great fan of you. Really are! Really like your enthusiasm and professional help! My wishes were rather aimed...

Thanks a lot for your suggestions and the insight Frances!!!

And you know what would be great? If the system could detect all supported spoken languages within the file and transcibe those respective to it. I mean...sometimes they speak in more than 1 language. And: its analyzing the first 30 seconds which in some cases leads either way to a wrong transcripti...

hehehe yeah I'm not a big fan of the gan models too. But it really depends what the expectations are. For myself I want a slight enhancement of medium distorted images. No artificial crap outcome where faces and objects have no texture anymore and identity changes of faces. And I think with some com...

Thanks for the detailed information! Great that you have a workaround for repeated sentences! I will look into it. And yes, in the long term it is defnitely better using faster-whisper where the development follows the original. Concerning the quantized models I haven't tested so far faster-whisper ...

Hi Admin Team, Look at this: https://github.com/chaiNNer-org/chaiNNer Node based image manipulation gui. I'm currently using it to compare different super resolution models against each other so I can implement my favorites in FFAStrans in the end. Because there are trillions of models and I was loo...

i hate pytorch. and i learned in the last months that i hate every application that start with: py apart from that. @emcodem: thanks for link! this week i switched over to faster-whisper. much faster than original whisper, less vram requirements. great. good to know that there is already a windows e...