Helsinki-NLP/opus-mt-cpp-cpp

1---2language: 3- id4- cpp5 6tags:7- translation8 9license: apache-2.010---11 12### cpp-cpp13 14* source group: Creoles and pidgins, Portuguese-based 15* target group: Creoles and pidgins, Portuguese-based 16*  OPUS readme: [cpp-cpp](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-cpp/README.md)17 18*  model: transformer19* source language(s): ind pap20* target language(s): ind pap21* model: transformer22* pre-processing: normalization + SentencePiece (spm32k,spm32k)23* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)24* download original weights: [opus-2020-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.zip)25* test set translations: [opus-2020-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.test.txt)26* test set scores: [opus-2020-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.eval.txt)27 28## Benchmarks29 30| testset               | BLEU  | chr-F |31|-----------------------|-------|-------|32| Tatoeba-test.msa-msa.msa.msa 	| 0.7 	| 0.149 |33| Tatoeba-test.msa-pap.msa.pap 	| 31.7 	| 0.577 |34| Tatoeba-test.multi.multi 	| 21.1 	| 0.369 |35| Tatoeba-test.pap-msa.pap.msa 	| 17.7 	| 0.197 |36 37 38### System Info: 39- hf_name: cpp-cpp40 41- source_languages: cpp42 43- target_languages: cpp44 45- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cpp-cpp/README.md46 47- original_repo: Tatoeba-Challenge48 49- tags: ['translation']50 51- languages: ['id', 'cpp']52 53- src_constituents: {'zsm_Latn', 'ind', 'pap', 'min', 'tmw_Latn', 'max_Latn', 'zlm_Latn'}54 55- tgt_constituents: {'zsm_Latn', 'ind', 'pap', 'min', 'tmw_Latn', 'max_Latn', 'zlm_Latn'}56 57- src_multilingual: True58 59- tgt_multilingual: True60 61- prepro:  normalization + SentencePiece (spm32k,spm32k)62 63- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.zip64 65- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/cpp-cpp/opus-2020-07-26.test.txt66 67- src_alpha3: cpp68 69- tgt_alpha3: cpp70 71- short_pair: cpp-cpp72 73- chrF2_score: 0.36974 75- bleu: 21.176 77- brevity_penalty: 0.88278 79- ref_len: 18.080 81- src_name: Creoles and pidgins, Portuguese-based82 83- tgt_name: Creoles and pidgins, Portuguese-based84 85- train_date: 2020-07-2686 87- src_alpha2: cpp88 89- tgt_alpha2: cpp90 91- prefer_old: False92 93- long_pair: cpp-cpp94 95- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c53596 97- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b98 99- port_machine: brutasse100 101- port_time: 2020-08-21-14:41