OPUS-MT Dashboard

Language pair: bul-tur [all languages]
Models: [all models] [OPUS-MT] [external] [compare]
Selected: huggingface/facebook/nllb-200-distilled-1.3B
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	bul-tur	flores101-devtest	show (logfile)	16.2
1	bul-tur	flores200-devtest	show (logfile)	16.2
2	bul-tur	ntrex128	show (logfile)	12.6
3	bul-tur	tatoeba-test-v2020-07-28	show (logfile)	41.1
4	bul-tur	tatoeba-test-v2021-03-30	show (logfile)	41.1
5	bul-tur	tatoeba-test-v2021-08-07	show (logfile)	41.1
	show all		average	28.050