Dmitry Chaplinsky
commited on
Commit
·
2b4230d
1
Parent(s):
1888ae1
Trying to unfuck the pipeline
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- token-classification
|
| 6 |
- punctuation prediction
|
| 7 |
- punctuation
|
|
|
|
| 8 |
license: mit
|
| 9 |
metrics:
|
| 10 |
- f1
|
|
@@ -12,6 +13,10 @@ metrics:
|
|
| 12 |
|
| 13 |
# Ukrainian model to restore punctuation and capitalization
|
| 14 |
|
| 15 |
-
This is the NeMo model to restore punctuation and capitalization in sentences, trained on 10m+ sentences from UberText 2.0 corpus (yet unreleased)
|
| 16 |
|
| 17 |
-
Model restores the following punctuations -- [? . ,]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
- token-classification
|
| 6 |
- punctuation prediction
|
| 7 |
- punctuation
|
| 8 |
+
library_name: nemo
|
| 9 |
license: mit
|
| 10 |
metrics:
|
| 11 |
- f1
|
|
|
|
| 13 |
|
| 14 |
# Ukrainian model to restore punctuation and capitalization
|
| 15 |
|
| 16 |
+
This is the NeMo model to restore punctuation and capitalization in sentences, trained on 10m+ sentences from UberText 2.0 corpus (yet unreleased). Basic transformer under the hood is `bert-base-multilingual-cased`.
|
| 17 |
|
| 18 |
+
Model restores the following punctuations -- [? . ,].
|
| 19 |
+
|
| 20 |
+
It also restores capitalization of words.
|
| 21 |
+
|
| 22 |
+
Copyright: Dmytro Chaplynskyi, [lang-uk](https://lang.org.ua) project, 2022
|