Update
Browse files- 123.png +0 -0
- README.md +2 -0
- predict.py +2 -1
123.png
ADDED
README.md
CHANGED
@@ -146,6 +146,8 @@ print(res)
|
|
146 |
|
147 |
Outputs:
|
148 |
|
|
|
|
|
149 |
```python
|
150 |
[{'word': '▁neuf', 'score': 0.9911066293716431, 'entity': 'B-time', 'index': 6, 'start': 15, 'end': 19},
|
151 |
{'word': '▁heures', 'score': 0.9200698733329773, 'entity': 'I-time', 'index': 7, 'start': 20, 'end': 26},
|
|
|
146 |
|
147 |
Outputs:
|
148 |
|
149 |
+
![English - Hebrew - Spanish](123.png)
|
150 |
+
|
151 |
```python
|
152 |
[{'word': '▁neuf', 'score': 0.9911066293716431, 'entity': 'B-time', 'index': 6, 'start': 15, 'end': 19},
|
153 |
{'word': '▁heures', 'score': 0.9200698733329773, 'entity': 'I-time', 'index': 7, 'start': 20, 'end': 26},
|
predict.py
CHANGED
@@ -3,7 +3,8 @@ from transformers import AutoTokenizer, AutoModelForTokenClassification, TokenCl
|
|
3 |
tokenizer = AutoTokenizer.from_pretrained('qanastek/XLMRoberta-Alexa-Intents-NER-NLU')
|
4 |
model = AutoModelForTokenClassification.from_pretrained('qanastek/XLMRoberta-Alexa-Intents-NER-NLU')
|
5 |
predict = TokenClassificationPipeline(model=model, tokenizer=tokenizer)
|
6 |
-
res = predict("
|
|
|
7 |
|
8 |
for r in res:
|
9 |
print(r)
|
|
|
3 |
tokenizer = AutoTokenizer.from_pretrained('qanastek/XLMRoberta-Alexa-Intents-NER-NLU')
|
4 |
model = AutoModelForTokenClassification.from_pretrained('qanastek/XLMRoberta-Alexa-Intents-NER-NLU')
|
5 |
predict = TokenClassificationPipeline(model=model, tokenizer=tokenizer)
|
6 |
+
res = predict("réveille-moi à neuf heures du matin le vendredi")
|
7 |
+
# res = predict("je veux écouter la chanson de jacques brel encore une fois")
|
8 |
|
9 |
for r in res:
|
10 |
print(r)
|