---
library_name: transformers
license: apache-2.0
language:
- en
- bg
- es
- tr
- ar
- nl
metrics:
- accuracy
- f1
- recall
- precision
pipeline_tag: text-classification
---

# Model Card for Model ID

The model detect claim-worthiness of a given text. This model is a part of an automatic fact-checking pipeline. 

The model is trained on data for Task 1 from [CLEF2021-CheckThat](https://sites.google.com/view/clef2021-checkthat/tasks/task-1-check-worthiness-estimation) and [CLEF2024-CheckThat](https://gitlab.com/checkthat_lab/clef2024-checkthat-lab/-/tree/main/task1/data)

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

- **Developed by:** [More Information Needed]
- **Model type:** transformer
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** FacebookAI/xlm-roberta-base

## Uses

The model is fine-tuned on a multilingual dataset, combining english, spanish, arabic, bulgarian, turkish, and dutch. It is meant to be used as zero-shot model for multilingual text data.

```
tokenizer = XLMRobertaTokenizer.from_pretrained("FacebookAI/xlm-roberta-base")
model = XLMRobertaForSequenceClassification.from_pretrained("SophieTr/xlm-roberta-base-claim-detection-clef21-24")

inputs = tokenizer(
    sentence_array, 
    return_tensors="pt", 
    padding=True, 
    truncation=True
)

with torch.no_grad():
    logits = model(**inputs).logits
    
predictions = [logits[i].argmax().item() for i,t in enumerate(logits)]
```