change model path

hardcoded some stuff don't mind me

the aranese code was wrong

improved UI, added rest of the availables languages (I think)

wip

wip

wip

add execution permission to tikal.sh

wip, fixed (hopefully) issue with the download button by lowering the gradio version (hopefully they will fix it at some point)

wip

wip

wip

wip

wip

wip

wip

wip

wip

wip

wip

remove dockerfile, we are using gradio apps now

add setup.sh

updated gradio app to support two different models of translator (with and without fastalign), refactored a bit of the code as well

added more comments

re-organised the code a bit, tried to use batch processing, didn't work

Working version using the non-quantized version of the model. Splits paragraphs and sentences, translates them and then reconstructs the paragraph.

fixed error, added appropiate prompt

wip

wip

remove fastalign from main.py since we are using the salamandraTA model that already aligns the tags

forgot to add this file in the previous commit

created classes for running the translation models either from a local model or a huggingface endpoint. for now main.py only supports local models

forgotten requirement

separated the translator that uses the HF endpoint

test

this folder does not exist anymore, we need to download it at build time

modified dockerfile and added script to setup environment, library building and asset downloading so when can run this script not only on docker

remove git lfs so I can push this stuff to github as well

looks like the previous version doesn't exist anymore

fixed a couple of bugs

wip

added textbox to use user token, remove text translation for now

fix token acquisition

Improved feedback to the user

fixed button issues

wip

wip

wip

wip

wip