my changes
Browse files
README.md
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
---
|
| 2 |
language: no
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
widget:
|
| 6 |
-
- text: "
|
|
|
|
| 7 |
license: cc-by-4.0
|
| 8 |
---
|
| 9 |
|
|
@@ -14,11 +15,3 @@ The DeUnCaser is a sequence-to-sequence byT5 model that is reversing this proces
|
|
| 14 |
|
| 15 |
It is using based on the multi-lingual base model. However the current finetuning is only done on Norwegian. For other languages this will be mainly experimental. I will update it with support for other languages if there is any demand.
|
| 16 |
|
| 17 |
-
## Example input - output
|
| 18 |
-
````
|
| 19 |
-
this is a test of a program developed in norway it is actually strange that it is able to do stuff like this even on sequences that are tricky to read by humans
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
````
|
|
|
|
| 1 |
---
|
| 2 |
language: no
|
| 3 |
tags:
|
| 4 |
+
- translation
|
| 5 |
widget:
|
| 6 |
+
- text: "dette er en liten test som er laget av per egil kummervold han er en forsker som tidligere jobbet ved nasjonalbiblioteket"
|
| 7 |
+
- text: "what do you think is the problem with boris is he just tired of being prime minister"
|
| 8 |
license: cc-by-4.0
|
| 9 |
---
|
| 10 |
|
|
|
|
| 15 |
|
| 16 |
It is using based on the multi-lingual base model. However the current finetuning is only done on Norwegian. For other languages this will be mainly experimental. I will update it with support for other languages if there is any demand.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|