hardcoded some stuff don't mind me

wip

wip

wip

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

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

separated the translator that uses the HF endpoint

fixed a couple of bugs

wip

Improved feedback to the user

Fixed some bugs, added dockerfile

Fixed a lot of error, now the script should crash much less often.

changed nltk tokenizer to multilingual tokenizers

Fixed bug when processing docx files

added language dropdown menus to document translation tab

enforce the usage of the hf token

turns out odts work a bit differently and runs could have more than one tag id, which complicates things quite a lot

Updated readme and added salamandraTA7b translator class

integrated any-doc into the gradle app, separated the translation side to make it easier to implement other translation models

forgot to remove placeholder text

moved scripts to src folder, created new create that hopefully should be able to work with any type of document