Update README.md

README.md

@@ -1,7 +1,8 @@
 ---
 license: apache-2.0
+language: ca
 tags:
-- generated_from_trainer
+- "catalan"
 datasets:
 - catalonia_independence
 metrics:
@@ -20,29 +21,26 @@ model-index:
     - name: Accuracy
       type: accuracy
       value: 0.7611940298507462
+widget:
+ - text: "Puigdemont, a l'estat espanyol: Quatre anys després, ens hem guanyat el dret a dir prou"
+ - text: "Llarena demana la detenció de Comín i Ponsatí aprofitant que són a Itàlia amb Puigdemont"
+ - text: "Assegura l'expert que en un 46% els catalans s'inclouen dins del que es denomina com el doble sentiment identitari. És a dir, se senten tant catalans com espanyols. 1 de cada cinc, en canvi, té un sentiment excloent, només se senten catalans, i un 4% sol espanyol."
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# roberta-base-ca-finetuned-mnli
+# roberta-base-ca-finetuned-catalonia-independence-detector
 
 This model is a fine-tuned version of [BSC-TeMU/roberta-base-ca](https://huggingface.co/BSC-TeMU/roberta-base-ca) on the catalonia_independence dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6065
 - Accuracy: 0.7612
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
+<details>
 
 ## Training and evaluation data
 
-More information needed
+This dataset contains two corpora in Spanish and Catalan that consist of annotated Twitter messages for automatic stance detection. The data was collected over 12 days during February and March of 2019 from tweets posted in Barcelona, and during September of 2018 from tweets posted in the town of Terrassa, Catalonia.
+
+Each corpus is annotated with three classes: AGAINST, FAVOR and NEUTRAL, which express the stance towards the target - independence of Catalonia.
 
 ## Training procedure
 
@@ -68,9 +66,51 @@ The following hyperparameters were used during training:
 | 0.3837        | 5.0   | 1885 | 0.7232          | 0.7582   |
 
 
+</details>
+
+### Model in action 🚀
+
+Fast usage with **pipelines**:
+
+```python
+
+from transformers import pipeline
+
+model_path = "JonatanGk/roberta-base-ca-finetuned-catalonia-independence-detector"
+independence_analysis = pipeline("text-classification", model=model_path, tokenizer=model_path)
+
+independence_analysis(
+    "Assegura l'expert que en un 46% els catalans s'inclouen dins del que es denomina com el doble sentiment identitari. És a dir, se senten tant catalans com espanyols. 1 de cada cinc, en canvi, té un sentiment excloent, només se senten catalans, i un 4% sol espanyol."
+    )
+# Output:
+[{'label': 'AGAINST', 'score': 0.7457581758499146}]
+
+independence_analysis(
+    "Llarena demana la detenció de Comín i Ponsatí aprofitant que són a Itàlia amb Puigdemont"
+    )
+# Output:
+[{'label': 'NEUTRAL', 'score': 0.7436802983283997}] 
+    
+independence_analysis(
+    "Puigdemont, a l'estat espanyol: Quatre anys després, ens hem guanyat el dret a dir prou"
+    )
+# Output:
+[{'label': 'FAVOR', 'score': 0.9040119647979736}]
+
+
+```
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JonatanGk/Shared-Colab/blob/master/Catalonia_independence_Detector_(CATALAN).ipynb#scrollTo=j29NHJtOyAVU)
+
+
 ### Framework versions
 
 - Transformers 4.11.3
 - Pytorch 1.9.0+cu111
 - Datasets 1.12.1
 - Tokenizers 0.10.3
+
+
+## Citation
+
+Thx to HF.co & [@lewtun](https://github.com/lewtun) for Dataset ;)