OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: huggingface/facebook/nllb-200-distilled-1.3B
Benchmark: [all benchmarks] multi30k_test_2017_mscoco [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	chrf
0	deu-eng	multi30k_test_2017_mscoco	show (logfile)	0.5973
1	deu-fra	multi30k_test_2017_mscoco	show (logfile)	0.58197
2	eng-deu	multi30k_test_2017_mscoco	show (logfile)	0.59542
3	eng-fra	multi30k_test_2017_mscoco	show (logfile)	0.71615
4	fra-deu	multi30k_test_2017_mscoco	show (logfile)	0.54638
5	fra-eng	multi30k_test_2017_mscoco	show	0.6987
		show all	average	0.623