Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-nc-sa-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
language:
|
| 4 |
+
- tr
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: translation
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Opus Tatoeba | Turkish -> English
|
| 10 |
+
|
| 11 |
+
* dataset: opus
|
| 12 |
+
* model: transformer
|
| 13 |
+
* source language(s): tur
|
| 14 |
+
* target language(s): eng
|
| 15 |
+
* model: transformer
|
| 16 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
| 17 |
+
* download: [opus-2021-02-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-eng/opus-2021-02-18.zip)
|
| 18 |
+
* test set translations: [opus-2021-02-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-eng/opus-2021-02-18.test.txt)
|
| 19 |
+
* test set scores: [opus-2021-02-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/tur-eng/opus-2021-02-18.eval.txt)
|
| 20 |
+
|
| 21 |
+
## Benchmarks
|
| 22 |
+
|
| 23 |
+
| testset | BLEU | chr-F | #sent | #words | BP |
|
| 24 |
+
|---------|-------|-------|-------|--------|----|
|
| 25 |
+
| newsdev2016-entr.tur-eng | 27.9 | 0.546 | 1001 | 22011 | 0.927 |
|
| 26 |
+
| newstest2016-entr.tur-eng | 24.2 | 0.526 | 3000 | 66175 | 0.942 |
|
| 27 |
+
| newstest2017-entr.tur-eng | 24.9 | 0.533 | 3007 | 67703 | 0.943 |
|
| 28 |
+
| newstest2018-entr.tur-eng | 27.0 | 0.548 | 3000 | 68725 | 0.957 |
|
| 29 |
+
| Tatoeba-test.tur-eng | 58.4 | 0.725 | 10000 | 77701 | 0.966 |
|