Commit
•
b26fd1c
1
Parent(s):
d720825
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,9 @@ This model accepts as input lower-cased, unpunctuated English text and performs
|
|
| 20 |
|
| 21 |
In contast to many similar models, this model can predict punctuated acronyms (e.g., "U.S.") via a special "acronym" class, as well as arbitarily-capitalized words (NATO, McDonald's, etc.) via multi-label true-casing predictions.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
| 23 |
# Usage
|
| 24 |
The easy way to use this model is to install [punctuators](https://github.com/1-800-BAD-CODE/punctuators):
|
| 25 |
|
|
|
|
| 20 |
|
| 21 |
In contast to many similar models, this model can predict punctuated acronyms (e.g., "U.S.") via a special "acronym" class, as well as arbitarily-capitalized words (NATO, McDonald's, etc.) via multi-label true-casing predictions.
|
| 22 |
|
| 23 |
+
**Widget note**: The text generation widget doesn't seem to respect line breaks.
|
| 24 |
+
Instead, the pipeline inserts a new line token `\n` in the text where the model has predicted sentence boundaries (line breaks).
|
| 25 |
+
|
| 26 |
# Usage
|
| 27 |
The easy way to use this model is to install [punctuators](https://github.com/1-800-BAD-CODE/punctuators):
|
| 28 |
|