microbert-tamil-mx / README.md
lgessler's picture
Create README.md
f51a7b6
metadata
language: tam
widget:
  - text: தொழிலாளர்களுடன் பேச்சுவார்த்தை நடத்தி, சுமூக தீர்வு காணப்படவில்லை.

This is a MicroBERT model for Tamil.

  • Its suffix is -mx, which means that it was pretrained using supervision from masked language modeling and XPOS tagging.
  • The unlabeled Tamil data was taken from a June 2022 dump of Tamil Wikipedia, downsampled to 1,429,735 tokens.
  • The UD treebank UD_Tamil-TTB, v2.9, totaling 9,581 tokens, was used for labeled data.

Please see the repository and the paper for more details.