oliverguhr commited on
Commit
11a1eff
1 Parent(s): cc816c5

added library sample

Browse files
Files changed (1) hide show
  1. README.md +35 -3
README.md CHANGED
@@ -28,14 +28,46 @@ This multilanguage model was trained on the [Europarl Dataset](https://huggingfa
28
 
29
  The model restores the following punctuation markers: **"." "," "?" "-" ":"**
30
  ## Sample Code
 
31
 
 
 
 
 
 
 
 
 
32
  ```python
33
- from transformers import pipeline
34
 
35
- pipe = pipeline("token-classification", "oliverguhr/fullstop-punctuation-multilang-large")
36
- pipe(["My name is Clara and I live in Berkeley California"])
 
 
37
  ```
38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
 
40
  ## Results
41
 
 
28
 
29
  The model restores the following punctuation markers: **"." "," "?" "-" ":"**
30
  ## Sample Code
31
+ We provide a simple python package that allows you to process text of any length.
32
 
33
+ ## Install
34
+
35
+ To get started install the package from [pypi](https://pypi.org/project/deepmultilingualpunctuation/):
36
+
37
+ ```bash
38
+ pip install deepmultilingualpunctuation
39
+ ```
40
+ ### Restore Punctuation
41
  ```python
42
+ from deepmultilingualpunctuation import PunctuationModel
43
 
44
+ model = PunctuationModel()
45
+ text = "My name is Clara and I live in Berkeley California Ist das eine Frage Frau Müller"
46
+ result = model.restore_punctuation(text)
47
+ print(result)
48
  ```
49
 
50
+ **output**
51
+ > My name is Clara and I live in Berkeley, California. Ist das eine Frage, Frau Müller?
52
+
53
+
54
+ ### Predict Labels
55
+ ```python
56
+ from deepmultilingualpunctuation import PunctuationModel
57
+
58
+ model = PunctuationModel()
59
+ text = "My name is Clara and I live in Berkeley California Ist das eine Frage Frau Müller"
60
+ clean_text = model.preprocess(text)
61
+ labled_words = model.predict(clean_text)
62
+ print(labled_words)
63
+ ```
64
+
65
+ **output**
66
+
67
+ > [['My', '0', 0.9999887], ['name', '0', 0.99998665], ['is', '0', 0.9998579], ['Clara', '0', 0.6752215], ['and', '0', 0.99990904], ['I', '0', 0.9999877], ['live', '0', 0.9999839], ['in', '0', 0.9999515], ['Berkeley', ',', 0.99800044], ['California', '.', 0.99534047], ['Ist', '0', 0.99998784], ['das', '0', 0.99999154], ['eine', '0', 0.9999918], ['Frage', ',', 0.99622655], ['Frau', '0', 0.9999889], ['Müller', '?', 0.99863917]]
68
+
69
+
70
+
71
 
72
  ## Results
73