Benchmark Almanac

Amrith Krishna

We track 2 benchmarks that Amrith Krishna made or helped make.

0 in use 1 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Post-OCR Text Correction in Sanskrit Models correct machine transcriptions of printed Sanskrit books in Devanagari. The benchmark reports character and word error rates. Reading in many languages Jun 2022 Not in cards
SIGHUM Sanskrit Word Segmentation Models recover individual Sanskrit words from continuous text. Evaluators measure word precision, recall, F1, and the percentage of sentences whose entire segmentation matches. Reading in many languages Jun 2017 Not in cards