Update README.md

README.md

@@ -1,3 +1,62 @@
 ---
 license: cc-by-nc-4.0
+datasets:
+- Babelscape/wikineural
+language:
+- de
+- fr
+- it
+- rm
+- multilingual
+widget:
+- text: Mein Name sei Gantenbein.
+  example_title: "German example"
+  inference:
+    parameters:
+      default_language: "de_CH"
+tags:
+  - named-entity-recognition
 ---
+
+The [SwissBERT](https://huggingface.co/ZurichNLP/swissbert) model fine-tuned on the [WikiNEuRal](https://huggingface.co/datasets/Babelscape/wikineural) dataset for multilingual NER.
+
+Supports German, French and Italian as supervised languages and Romansh Grischun as a zero-shot language.
+
+## Usage
+
+```python
+from transformers import pipeline
+
+token_classifier = pipeline(
+  model="ZurichNLP/swissbert-ner",
+  aggregation_strategy="simple",
+)
+```
+
+### German example
+```python
+token_classifier.model.set_default_language("de_CH")
+token_classifier("Mein Name sei Gantenbein.")
+```
+Output:
+```
+[{'entity_group': 'PER',
+  'score': 0.5002625,
+  'word': 'Gantenbein',
+  'start': 13,
+  'end': 24}]
+```
+
+### French example
+```python
+token_classifier.model.set_default_language("fr_CH")
+token_classifier("J'habite à Lausanne.")
+```
+Output:
+```
+[{'entity_group': 'LOC',
+  'score': 0.99955386,
+  'word': 'Lausanne',
+  'start': 10,
+  'end': 19}]
+```