opus-2020-07-27.zip dataset: opus model: transformer source language(s): asm hin mar urd zza target language(s): asm hin mar urd zza model: transformer pre-processing: normalization + SentencePiece (spm32k,spm32k) a sentence initial language token is required in the form of >>id<< (id = valid target language ID) download: opus-2020-07-27.zip test set translations: opus-2020-07-27.test.txt test set scores: opus-2020-07-27.eval.txt Benchmarks testset BLEU chr-F Tatoeba-test.asm-hin.asm.hin 3.5 0.202 Tatoeba-test.asm-zza.asm.zza 12.4 0.014 Tatoeba-test.hin-asm.hin.asm 6.2 0.238 Tatoeba-test.hin-mar.hin.mar 27.0 0.560 Tatoeba-test.hin-urd.hin.urd 21.4 0.507 Tatoeba-test.mar-hin.mar.hin 13.4 0.463 Tatoeba-test.multi.multi 17.7 0.460 Tatoeba-test.urd-hin.urd.hin 13.4 0.363 Tatoeba-test.zza-asm.zza.asm 5.3 0.000