README.md

metadata

language:
  - en
  - multilingual
widget:
  - text: 'translate English to Darija:  what are you doing'
    example_title: 'Translation English to Darija #1'
  - text: 'translate English to Darija:  are you doing good'
    example_title: 'Translation English to Darija #2'
  - text: 'translate English to Darija:  can you help me please'
    example_title: 'Translation English to Darija #3'
license: apache-2.0
pipeline_tag: translation
tags:
  - translation
  - darija
  - moroccan
  - t5-large

Model T5-Large

I have made an initial attempt to fine-tune the t5-large model for use in Darija. However, it should be noted that this was only a first-time project for me and the available dataset was limited in terms of both size and diversity.

Note: Using only lowercase sentences without any special characters or punctuation is crucial for getting better output results, this is due to some mistakes on my part, my apologies, this was a side project and not meant to be taken seriously. I am currently working on a better/improved models with a larger dataset, more complex and with a diverse vocabulary.