OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: HPLT-MT-models/en-hi/translate-en-hi-v1.0-hplt
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 (logfile)	33
1	eng-hin	flores200-devtest	show (logfile)	33
2	eng-hin	newstest2014	show (logfile)	23
3	eng-hin	ntrex128	show (logfile)	26.6
4	eng-hin	tatoeba-test-v2021-08-07	show (logfile)	26.4
5	eng-hin	tico19-test	show (logfile)	42.1
			average	30.683