Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,33 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-sa-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- fi
|
6 |
+
pipeline_tag: translation
|
7 |
+
---
|
8 |
+
|
9 |
+
# Opus Tatoeba | English -> Finish
|
10 |
+
|
11 |
+
* dataset: opus
|
12 |
+
* model: transformer-align
|
13 |
+
* source language(s): eng
|
14 |
+
* target language(s): fin
|
15 |
+
* model: transformer-align
|
16 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
17 |
+
* download: [opus-2021-02-19.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opus-2021-02-19.zip)
|
18 |
+
* test set translations: [opus-2021-02-19.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opus-2021-02-19.test.txt)
|
19 |
+
* test set scores: [opus-2021-02-19.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opus-2021-02-19.eval.txt)
|
20 |
+
|
21 |
+
## Benchmarks
|
22 |
+
|
23 |
+
| testset | BLEU | chr-F | #sent | #words | BP |
|
24 |
+
|---------|-------|-------|-------|--------|----|
|
25 |
+
| newsdev2015-enfi.eng-fin | 21.6 | 0.556 | 1500 | 23375 | 1.000 |
|
26 |
+
| newstest2015-enfi.eng-fin | 23.2 | 0.567 | 1370 | 19968 | 1.000 |
|
27 |
+
| newstest2016-enfi.eng-fin | 24.9 | 0.578 | 3000 | 48116 | 0.986 |
|
28 |
+
| newstest2017-enfi.eng-fin | 27.5 | 0.605 | 3002 | 45718 | 0.996 |
|
29 |
+
| newstest2018-enfi.eng-fin | 18.4 | 0.532 | 3000 | 45475 | 1.000 |
|
30 |
+
| newstest2019-enfi.eng-fin | 23.3 | 0.551 | 1997 | 38369 | 0.966 |
|
31 |
+
| newstestB2016-enfi.eng-fin | 19.7 | 0.542 | 3000 | 45766 | 1.000 |
|
32 |
+
| newstestB2017-enfi.eng-fin | 22.7 | 0.565 | 3002 | 45506 | 1.000 |
|
33 |
+
| Tatoeba-test.eng-fin | 38.7 | 0.629 | 10000 | 60517 | 0.935 |
|