OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/mkh-fiu/opus-2021-02-18
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	khm-fin	flores101-devtest	show	0.4
1	khm-fin	flores200-devtest	show	0.4
2	khm-fin	ntrex128	show	0.6
3	khm-hun	flores101-devtest	show	1.3
4	khm-hun	flores200-devtest	show	1.2
5	khm-hun	ntrex128	show	1.1
6	vie-fin	flores101-devtest	show	4
7	vie-fin	flores200-devtest	show	4
8	vie-fin	ntrex128	show	4.3
9	vie-hun	flores101-devtest	show	6.2
10	vie-hun	flores200-devtest	show	6.2
11	vie-hun	ntrex128	show	4.9
			average	2.883