Update README.md
Browse files
README.md
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
### opus-mt-en-INSULAR_CELTIC
|
2 |
+
|
3 |
+
* source languages: en
|
4 |
+
* target languages: ga,cy,br,gd,kw,gv
|
5 |
+
* OPUS readme: [en-ga+cy+br+gd+kw+gv](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-ga+cy+br+gd+kw+gv/README.md)
|
6 |
+
|
7 |
+
* dataset: opus+techiaith+bt
|
8 |
+
* model: transformer-align
|
9 |
+
* pre-processing: normalization + SentencePiece
|
10 |
+
* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
|
11 |
+
* download original weights: [opus+techiaith+bt-2020-04-24.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-ga+cy+br+gd+kw+gv/opus+techiaith+bt-2020-04-24.zip)
|
12 |
+
* test set translations: [opus+techiaith+bt-2020-04-24.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ga+cy+br+gd+kw+gv/opus+techiaith+bt-2020-04-24.test.txt)
|
13 |
+
* test set scores: [opus+techiaith+bt-2020-04-24.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-ga+cy+br+gd+kw+gv/opus+techiaith+bt-2020-04-24.eval.txt)
|
14 |
+
|
15 |
+
## Benchmarks
|
16 |
+
|
17 |
+
| testset | BLEU | chr-F |
|
18 |
+
|-----------------------|-------|-------|
|
19 |
+
| Tatoeba.en.ga | 22.8 | 0.404 |
|
20 |
+
|