OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: HPLT-MT-models/mt-en/translate-mt-en-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	mlt-eng	flores101-devtest	show (logfile)	41.1
1	mlt-eng	flores200-devtest	show (logfile)	41.1
2	mlt-eng	ntrex128	show (logfile)	34
3	mlt-eng	tatoeba-test-v2021-03-30	show (logfile)	41.7
4	mlt-eng	tatoeba-test-v2021-08-07	show (logfile)	41.9
			average	39.960