OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: huggingface/sshleifer/opus-mt-en-he
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	spbleu
0	eng-heb	flores101-devtest	show	40.2
1	eng-heb	flores200-devtest	show	40.5
2	eng-heb	tatoeba-test-v2020-07-28	show	45
3	eng-heb	tatoeba-test-v2021-03-30	show	45.5
4	eng-heb	tatoeba-test-v2021-08-07	show	45.6
			average	43.360