OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/gmq-ukr/opusTCv20210807+bt+pbt+pft-sepvoc_transformer-tiny11-align_2022-03-23
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	dan-ukr	flores101-devtest	show	22.7
1	dan-ukr	flores200-devtest	show	22.7
2	dan-ukr	ntrex128	show	17.8
3	nno-ukr	flores200-devtest	show	14.8
4	nno-ukr	ntrex128	show	13
5	nob-ukr	flores101-devtest	show	18.7
6	nob-ukr	flores200-devtest	show	18.7
7	nob-ukr	ntrex128	show	18.1
8	nor-ukr	tatoeba-test-v2021-03-30	show	42.7
9	nor-ukr	tatoeba-test-v2021-08-07	show	42.8
10	swe-ukr	flores101-devtest	show	21.9
11	swe-ukr	flores200-devtest	show	21.9
12	swe-ukr	ntrex128	show	19.1
			average	22.685