README.md
| 1 | --- |
| 2 | language: |
| 3 | - ko |
| 4 | - en |
| 5 | |
| 6 | tags: |
| 7 | - translation |
| 8 | |
| 9 | license: apache-2.0 |
| 10 | --- |
| 11 | |
| 12 | ### kor-eng |
| 13 | |
| 14 | * source group: Korean |
| 15 | * target group: English |
| 16 | * OPUS readme: [kor-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md) |
| 17 | |
| 18 | * model: transformer-align |
| 19 | * source language(s): kor kor_Hang kor_Latn |
| 20 | * target language(s): eng |
| 21 | * model: transformer-align |
| 22 | * pre-processing: normalization + SentencePiece (spm32k,spm32k) |
| 23 | * download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip) |
| 24 | * test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt) |
| 25 | * test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.eval.txt) |
| 26 | |
| 27 | ## Benchmarks |
| 28 | |
| 29 | | testset | BLEU | chr-F | |
| 30 | |-----------------------|-------|-------| |
| 31 | | Tatoeba-test.kor.eng | 41.3 | 0.588 | |
| 32 | |
| 33 | |
| 34 | ### System Info: |
| 35 | - hf_name: kor-eng |
| 36 | |
| 37 | - source_languages: kor |
| 38 | |
| 39 | - target_languages: eng |
| 40 | |
| 41 | - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md |
| 42 | |
| 43 | - original_repo: Tatoeba-Challenge |
| 44 | |
| 45 | - tags: ['translation'] |
| 46 | |
| 47 | - languages: ['ko', 'en'] |
| 48 | |
| 49 | - src_constituents: {'kor_Hani', 'kor_Hang', 'kor_Latn', 'kor'} |
| 50 | |
| 51 | - tgt_constituents: {'eng'} |
| 52 | |
| 53 | - src_multilingual: False |
| 54 | |
| 55 | - tgt_multilingual: False |
| 56 | |
| 57 | - prepro: normalization + SentencePiece (spm32k,spm32k) |
| 58 | |
| 59 | - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip |
| 60 | |
| 61 | - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt |
| 62 | |
| 63 | - src_alpha3: kor |
| 64 | |
| 65 | - tgt_alpha3: eng |
| 66 | |
| 67 | - short_pair: ko-en |
| 68 | |
| 69 | - chrF2_score: 0.588 |
| 70 | |
| 71 | - bleu: 41.3 |
| 72 | |
| 73 | - brevity_penalty: 0.9590000000000001 |
| 74 | |
| 75 | - ref_len: 17711.0 |
| 76 | |
| 77 | - src_name: Korean |
| 78 | |
| 79 | - tgt_name: English |
| 80 | |
| 81 | - train_date: 2020-06-17 |
| 82 | |
| 83 | - src_alpha2: ko |
| 84 | |
| 85 | - tgt_alpha2: en |
| 86 | |
| 87 | - prefer_old: False |
| 88 | |
| 89 | - long_pair: kor-eng |
| 90 | |
| 91 | - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535 |
| 92 | |
| 93 | - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b |
| 94 | |
| 95 | - port_machine: brutasse |
| 96 | |
| 97 | - port_time: 2020-08-21-14:41 |