OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/eng-hin/opus+bt-2021-04-10
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	eng-hin	flores101-devtest	show	23.5
1	eng-hin	flores200-devtest	show	23.4
2	eng-hin	newstest2014	show	17.3
3	eng-hin	ntrex128	show	19.6
4	eng-hin	tatoeba-test-v2020-07-28	show	22.4
5	eng-hin	tatoeba-test-v2021-03-30	show	22.4
6	eng-hin	tatoeba-test-v2021-08-07	show	22.4
7	eng-hin	tico19-test	show	30.1
			average	22.638