OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/fin-zls/opusTCv20210807_transformer-big_2022-07-23
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

ID	Language	Benchmark	Output	bleu
0	fin-bul	flores101-devtest	show	26.2
1	fin-bul	flores200-devtest	show	26.2
2	fin-bul	ntrex128	show	20.3
3	fin-hrv	flores101-devtest	show	21.3
4	fin-hrv	flores200-devtest	show	21.2
5	fin-hrv	ntrex128	show	19
6	fin-slv	flores101-devtest	show	22.3
7	fin-slv	flores200-devtest	show	22.3
8	fin-slv	ntrex128	show	19.6
9	fin-srp_Cyrl	flores101-devtest	show	21.8
10	fin-srp_Cyrl	flores200-devtest	show	21.8
11	fin-srp_Cyrl	ntrex128	show	12.6
12	fin-srp_Latn	ntrex128	show	15.9
			average	20.808