OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/aav-urj/opus4m+btTCv20210807-2021-09-30
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	0.8
1	khm-fin	flores200-devtest	show	0.8
2	khm-fin	ntrex128	show	1
3	khm-hun	flores101-devtest	show	0.8
4	khm-hun	flores200-devtest	show	0.9
5	khm-hun	ntrex128	show	0.9
6	vie-fin	flores101-devtest	show	10.8
7	vie-fin	flores200-devtest	show	10.7
8	vie-fin	ntrex128	show	9.8
9	vie-hun	flores101-devtest	show	13.8
10	vie-hun	flores200-devtest	show	13.8
11	vie-hun	ntrex128	show	10.3
			average	6.200