Update README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: urj
|
| 3 |
+
tags:
|
| 4 |
+
- translation
|
| 5 |
+
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
### urj-urj
|
| 10 |
+
|
| 11 |
+
* source languages: urj
|
| 12 |
+
* target languages: urj
|
| 13 |
+
* OPUS readme: [urj-urj](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urj-urj/README.md)
|
| 14 |
+
|
| 15 |
+
* dataset: opus
|
| 16 |
+
* model: transformer
|
| 17 |
+
* source language(s): est fin fkv_Latn hun izh krl liv_Latn vep vro
|
| 18 |
+
* target language(s): est fin fkv_Latn hun izh krl liv_Latn vep vro
|
| 19 |
+
* model: transformer
|
| 20 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
| 21 |
+
* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
|
| 22 |
+
* download original weights: [opus-2020-07-27.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-urj/opus-2020-07-27.zip)
|
| 23 |
+
* test set translations: [opus-2020-07-27.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-urj/opus-2020-07-27.test.txt)
|
| 24 |
+
* test set scores: [opus-2020-07-27.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/urj-urj/opus-2020-07-27.eval.txt)
|
| 25 |
+
|
| 26 |
+
## Benchmarks
|
| 27 |
+
|
| 28 |
+
| testset | BLEU | chr-F |
|
| 29 |
+
|-----------------------|-------|-------|
|
| 30 |
+
| Tatoeba-test.est-est.est.est | 5.1 | 0.288 |
|
| 31 |
+
| Tatoeba-test.est-fin.est.fin | 50.9 | 0.709 |
|
| 32 |
+
| Tatoeba-test.est-fkv.est.fkv | 0.7 | 0.215 |
|
| 33 |
+
| Tatoeba-test.est-vep.est.vep | 1.0 | 0.154 |
|
| 34 |
+
| Tatoeba-test.fin-est.fin.est | 55.5 | 0.718 |
|
| 35 |
+
| Tatoeba-test.fin-fkv.fin.fkv | 1.8 | 0.254 |
|
| 36 |
+
| Tatoeba-test.fin-hun.fin.hun | 45.0 | 0.672 |
|
| 37 |
+
| Tatoeba-test.fin-izh.fin.izh | 7.1 | 0.492 |
|
| 38 |
+
| Tatoeba-test.fin-krl.fin.krl | 2.6 | 0.278 |
|
| 39 |
+
| Tatoeba-test.fkv-est.fkv.est | 0.6 | 0.099 |
|
| 40 |
+
| Tatoeba-test.fkv-fin.fkv.fin | 15.5 | 0.444 |
|
| 41 |
+
| Tatoeba-test.fkv-liv.fkv.liv | 0.6 | 0.101 |
|
| 42 |
+
| Tatoeba-test.fkv-vep.fkv.vep | 0.6 | 0.113 |
|
| 43 |
+
| Tatoeba-test.hun-fin.hun.fin | 46.3 | 0.675 |
|
| 44 |
+
| Tatoeba-test.izh-fin.izh.fin | 13.4 | 0.431 |
|
| 45 |
+
| Tatoeba-test.izh-krl.izh.krl | 2.9 | 0.078 |
|
| 46 |
+
| Tatoeba-test.krl-fin.krl.fin | 14.1 | 0.439 |
|
| 47 |
+
| Tatoeba-test.krl-izh.krl.izh | 1.0 | 0.125 |
|
| 48 |
+
| Tatoeba-test.liv-fkv.liv.fkv | 0.9 | 0.170 |
|
| 49 |
+
| Tatoeba-test.liv-vep.liv.vep | 2.6 | 0.176 |
|
| 50 |
+
| Tatoeba-test.multi.multi | 32.9 | 0.580 |
|
| 51 |
+
| Tatoeba-test.vep-est.vep.est | 3.4 | 0.265 |
|
| 52 |
+
| Tatoeba-test.vep-fkv.vep.fkv | 0.9 | 0.239 |
|
| 53 |
+
| Tatoeba-test.vep-liv.vep.liv | 2.6 | 0.190 |
|
| 54 |
+
|