OPUS-MT Dashboard

Language pair: eng-fra [all languages]
Models: [all models] [OPUS-MT] [external] [compare]
Benchmark: [all benchmarks] [average score] multi30k_test_2018_flickr
Evaluation metric: [bleu][spbleu][chrf] chrf++ [comet]
Chart Type: [barchart][scatterplot] [size] [type]

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]
include scores of user-contributed translations

Model Scores (chrf++ scores on the "multi30k_test_2018_flickr" testset)

ID	chrf++	Output	Model	Size	Link
6	0.645	show	facebook/nll...illed-1.3B	1331.2M	URL
5	0.645	show	facebook/nllb-200-3.3B	3379.2M	URL
4	0.637	show	facebook/nllb-200-1.3B	1331.2M	URL
3	0.614	show	facebook/nll...illed-600M	600M	URL
2	0.600	show	facebook/m2m100_1.2B	1331.2M	URL
1	0.539	show	facebook/m2m100_418M	418M	URL
0	0.135	show	JamesH/Trans...fr_project	?	URL