This model is a float16 quantized version of gimmeursocks/opus-mt-tc-big-en-ar-distilled. It achieves the following results on the testing set:
| langpair | testset | chr-F | BLEU | TER | #sent | #words |
|---|---|---|---|---|---|---|
| eng-ara | tatoeba-test-v2021-08-07 | 0.496 | 22.4 | 0.629 | 10305 | 61356 |
| eng-ara | flores101-devtest | 0.566 | 25.6 | 0.581 | 1012 | 21357 |
| eng-ara | tico19-test | 0.545 | 24.8 | 0.609 | 2100 | 51339 |
- Downloads last month
- 59
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for gimmeursocks/opus-mt-tc-big-en-ar-distilled-f16
Base model
Helsinki-NLP/opus-mt-en-ar