OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/fin-sem/opus4m+btTCv20210807-2022-01-19
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

orange = OPUS-MT, blue = Tatoeba-MT models, red = HPLT-MT models
green = student models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]

Model Scores (selected model)

ID	Language	Benchmark	Output	bleu
0	fin-ara	flores101-devtest	show	12.5
1	fin-ara	flores200-devtest	show	12.6
2	fin-arz	flores200-devtest	show	5
3	fin-heb	flores101-devtest	show	14.3
4	fin-heb	flores200-devtest	show	14.2
5	fin-heb	ntrex128	show	10.7
6	fin-heb	tatoeba-test-v2020-07-28	show	35.2
7	fin-heb	tatoeba-test-v2021-03-30	show	35.1
8	fin-heb	tatoeba-test-v2021-08-07	show	35.2
			average	19.422