OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: OPUS-MT-models/et+hu+fi-et+hu+fi/opus-2019-12-04
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	est-fin	flores101-devtest	show	14.9
1	est-hun	flores101-devtest	show	16.2
2	fin-est	flores101-devtest	show	15.8
3	fin-hun	flores101-devtest	show	14.9
4	fin-hun	tatoeba-test-v2021-08-07	show	47.7
5	hun-est	flores101-devtest	show	14.1
6	hun-fin	flores101-devtest	show	11.9
7	hun-fin	tatoeba-test-v2021-08-07	show	48.8
			average	23.038