Add README.md for Helsinki-NLP-opus-mt-en-sal
Browse files
Helsinki-NLP-opus-mt-en-sal/README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- sal
|
| 5 |
+
|
| 6 |
+
tags:
|
| 7 |
+
- translation
|
| 8 |
+
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
### eng-sal
|
| 13 |
+
|
| 14 |
+
* source group: English
|
| 15 |
+
* target group: Salishan languages
|
| 16 |
+
* OPUS readme: [eng-sal](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sal/README.md)
|
| 17 |
+
|
| 18 |
+
* model: transformer
|
| 19 |
+
* source language(s): eng
|
| 20 |
+
* target language(s): shs_Latn
|
| 21 |
+
* model: transformer
|
| 22 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
| 23 |
+
* download original weights: [opus-2020-07-14.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sal/opus-2020-07-14.zip)
|
| 24 |
+
* test set translations: [opus-2020-07-14.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sal/opus-2020-07-14.test.txt)
|
| 25 |
+
* test set scores: [opus-2020-07-14.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sal/opus-2020-07-14.eval.txt)
|
| 26 |
+
|
| 27 |
+
## Benchmarks
|
| 28 |
+
|
| 29 |
+
| testset | BLEU | chr-F |
|
| 30 |
+
|-----------------------|-------|-------|
|
| 31 |
+
| Tatoeba-test.eng.multi | 32.6 | 0.585 |
|
| 32 |
+
| Tatoeba-test.eng.shs | 1.1 | 0.072 |
|
| 33 |
+
| Tatoeba-test.eng-shs.eng.shs | 1.2 | 0.065 |
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
### System Info:
|
| 37 |
+
- hf_name: eng-sal
|
| 38 |
+
|
| 39 |
+
- source_languages: eng
|
| 40 |
+
|
| 41 |
+
- target_languages: sal
|
| 42 |
+
|
| 43 |
+
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-sal/README.md
|
| 44 |
+
|
| 45 |
+
- original_repo: Tatoeba-Challenge
|
| 46 |
+
|
| 47 |
+
- tags: ['translation']
|
| 48 |
+
|
| 49 |
+
- languages: ['en', 'sal']
|
| 50 |
+
|
| 51 |
+
- src_constituents: {'eng'}
|
| 52 |
+
|
| 53 |
+
- tgt_constituents: {'shs_Latn'}
|
| 54 |
+
|
| 55 |
+
- src_multilingual: False
|
| 56 |
+
|
| 57 |
+
- tgt_multilingual: True
|
| 58 |
+
|
| 59 |
+
- prepro: normalization + SentencePiece (spm32k,spm32k)
|
| 60 |
+
|
| 61 |
+
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sal/opus-2020-07-14.zip
|
| 62 |
+
|
| 63 |
+
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-sal/opus-2020-07-14.test.txt
|
| 64 |
+
|
| 65 |
+
- src_alpha3: eng
|
| 66 |
+
|
| 67 |
+
- tgt_alpha3: sal
|
| 68 |
+
|
| 69 |
+
- short_pair: en-sal
|
| 70 |
+
|
| 71 |
+
- chrF2_score: 0.07200000000000001
|
| 72 |
+
|
| 73 |
+
- bleu: 1.1
|
| 74 |
+
|
| 75 |
+
- brevity_penalty: 1.0
|
| 76 |
+
|
| 77 |
+
- ref_len: 199.0
|
| 78 |
+
|
| 79 |
+
- src_name: English
|
| 80 |
+
|
| 81 |
+
- tgt_name: Salishan languages
|
| 82 |
+
|
| 83 |
+
- train_date: 2020-07-14
|
| 84 |
+
|
| 85 |
+
- src_alpha2: en
|
| 86 |
+
|
| 87 |
+
- tgt_alpha2: sal
|
| 88 |
+
|
| 89 |
+
- prefer_old: False
|
| 90 |
+
|
| 91 |
+
- long_pair: eng-sal
|
| 92 |
+
|
| 93 |
+
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
|
| 94 |
+
|
| 95 |
+
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
|
| 96 |
+
|
| 97 |
+
- port_machine: brutasse
|
| 98 |
+
|
| 99 |
+
- port_time: 2020-08-21-14:41
|