thenlpresearcher/test_data_human_validated_eng_mar download history
thenlpresearcher/test_data_human_validated_eng_mar is a translation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 33 times (12 in the last 7 days), and 268 times in total. It ranks #361,752 among datasets by monthly downloads.
Virām: Diagnostic Benchmark for Punctuation-Robust English-to-Marathi Machine Translation Paper | GitHub | Demo Virām (also referred to as PEM or Punct-Eng-Mar) is the first diagnostic benchmark for assessing punctuation robustness in English-to-Marathi machine translation. It consist
Models trained on test_data_human_validated_eng_mar
1 models list it as training data.
- thenlpresearcher/shalaka_indictrans2-en-indic-dist-200M_finetuned_eng_Latn_to_mar_Deva 30 downloads in 30 days
Open thenlpresearcher/test_data_human_validated_eng_mar on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.