Update README.md
Browse files
README.md
CHANGED
|
@@ -1,24 +1,93 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- translation
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
-
###
|
| 7 |
|
| 8 |
-
* source
|
| 9 |
-
* target
|
| 10 |
-
* OPUS readme: [
|
| 11 |
|
| 12 |
-
*
|
| 13 |
-
*
|
| 14 |
-
*
|
| 15 |
-
*
|
| 16 |
-
*
|
| 17 |
-
*
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Benchmarks
|
| 20 |
|
| 21 |
| testset | BLEU | chr-F |
|
| 22 |
|-----------------------|-------|-------|
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: fi
|
| 3 |
tags:
|
| 4 |
- translation
|
| 5 |
+
|
| 6 |
+
license: apache-2.0
|
| 7 |
---
|
| 8 |
|
| 9 |
+
### fin-eng
|
| 10 |
|
| 11 |
+
* source group: Finnish
|
| 12 |
+
* target group: English
|
| 13 |
+
* OPUS readme: [fin-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fin-eng/README.md)
|
| 14 |
|
| 15 |
+
* model: transformer-align
|
| 16 |
+
* source language(s): fin
|
| 17 |
+
* target language(s): eng
|
| 18 |
+
* model: transformer-align
|
| 19 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
| 20 |
+
* download original weights: [opus-2020-08-05.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.zip)
|
| 21 |
+
* test set translations: [opus-2020-08-05.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.test.txt)
|
| 22 |
+
* test set scores: [opus-2020-08-05.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.eval.txt)
|
| 23 |
|
| 24 |
## Benchmarks
|
| 25 |
|
| 26 |
| testset | BLEU | chr-F |
|
| 27 |
|-----------------------|-------|-------|
|
| 28 |
+
| newsdev2015-enfi-fineng.fin.eng | 25.3 | 0.536 |
|
| 29 |
+
| newstest2015-enfi-fineng.fin.eng | 26.9 | 0.547 |
|
| 30 |
+
| newstest2016-enfi-fineng.fin.eng | 29.0 | 0.571 |
|
| 31 |
+
| newstest2017-enfi-fineng.fin.eng | 32.3 | 0.594 |
|
| 32 |
+
| newstest2018-enfi-fineng.fin.eng | 23.8 | 0.517 |
|
| 33 |
+
| newstest2019-fien-fineng.fin.eng | 29.0 | 0.565 |
|
| 34 |
+
| newstestB2016-enfi-fineng.fin.eng | 24.5 | 0.527 |
|
| 35 |
+
| newstestB2017-enfi-fineng.fin.eng | 27.4 | 0.557 |
|
| 36 |
+
| newstestB2017-fien-fineng.fin.eng | 27.4 | 0.557 |
|
| 37 |
+
| Tatoeba-test.fin.eng | 53.4 | 0.697 |
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
### System Info:
|
| 41 |
+
- hf_name: fin-eng
|
| 42 |
+
|
| 43 |
+
- source_languages: fin
|
| 44 |
+
|
| 45 |
+
- target_languages: eng
|
| 46 |
+
|
| 47 |
+
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/fin-eng/README.md
|
| 48 |
+
|
| 49 |
+
- original_repo: Tatoeba-Challenge
|
| 50 |
+
|
| 51 |
+
- tags: ['translation']
|
| 52 |
+
|
| 53 |
+
- prepro: normalization + SentencePiece (spm32k,spm32k)
|
| 54 |
+
|
| 55 |
+
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.zip
|
| 56 |
+
|
| 57 |
+
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/fin-eng/opus-2020-08-05.test.txt
|
| 58 |
+
|
| 59 |
+
- src_alpha3: fin
|
| 60 |
+
|
| 61 |
+
- tgt_alpha3: eng
|
| 62 |
+
|
| 63 |
+
- short_pair: fi-en
|
| 64 |
+
|
| 65 |
+
- chrF2_score: 0.6970000000000001
|
| 66 |
+
|
| 67 |
+
- bleu: 53.4
|
| 68 |
+
|
| 69 |
+
- brevity_penalty: 0.99
|
| 70 |
+
|
| 71 |
+
- ref_len: 74651.0
|
| 72 |
+
|
| 73 |
+
- src_name: Finnish
|
| 74 |
+
|
| 75 |
+
- tgt_name: English
|
| 76 |
+
|
| 77 |
+
- train_date: 2020-08-05
|
| 78 |
+
|
| 79 |
+
- src_alpha2: fi
|
| 80 |
+
|
| 81 |
+
- tgt_alpha2: en
|
| 82 |
+
|
| 83 |
+
- prefer_old: False
|
| 84 |
+
|
| 85 |
+
- long_pair: fin-eng
|
| 86 |
+
|
| 87 |
+
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
|
| 88 |
+
|
| 89 |
+
- transformers_git_sha: 46e9f53347bbe9e989f0335f98465f30886d8173
|
| 90 |
+
|
| 91 |
+
- port_machine: brutasse
|
| 92 |
|
| 93 |
+
- port_time: 2020-08-18-01:48
|