Xlm Roberta Base Language Detection Onnx

🚀 ONNX version of papluca/xlm-roberta-base-language-detection

This model is a conversion of the original language - detection model to ONNX format, offering efficient language - detection capabilities.

🚀 Quick Start

This model is a converted version of papluca/xlm-roberta-base-language-detection to ONNX format using the 🤗 Optimum library.

✨ Features

• Multilingual Support: Supports 20 languages including Arabic, Bulgarian, German, etc.
• Fine - tuned Model: Based on [xlm - roberta - base](https://huggingface.co/xlm - roberta - base) and fine - tuned on the [Language Identification](https://huggingface.co/datasets/papluca/language - identification#additional - information) dataset.
• Sequence Classification: Can be directly used for language detection in sequence classification tasks.

📦 Installation

Loading the model requires the 🤗 Optimum library installed.

💻 Usage Examples

Basic Usage

from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("laiyer/xlm-roberta-base-language-detection-onnx")
model = ORTModelForSequenceClassification.from_pretrained("laiyer/xlm-roberta-base-language-detection-onnx")
classifier = pipeline(
    task="text-classification",
    model=model,
    tokenizer=tokenizer,
    top_k=None,
)

classifier_output = classifier("It's not toxic comment")
print(classifier_output)

Advanced Usage

This model can also be used in the [Language scanner](https://llm - guard.com/input_scanners/language/).

📚 Documentation

Model description

This model is a fine - tuned version of [xlm - roberta - base](https://huggingface.co/xlm - roberta - base) on the [Language Identification](https://huggingface.co/datasets/papluca/language - identification#additional - information) dataset. It is an XLM - RoBERTa transformer model with a classification head on top (i.e. a linear layer on top of the pooled output). For additional information please refer to the [xlm - roberta - base](https://huggingface.co/xlm - roberta - base) model card or to the paper Unsupervised Cross - lingual Representation Learning at Scale by Conneau et al.

Intended uses & limitations

You can directly use this model as a language detector, i.e. for sequence classification tasks. Currently, it supports the following 20 languages:

arabic (ar), bulgarian (bg), german (de), modern greek (el), english (en), spanish (es), french (fr), hindi (hi), italian (it), japanese (ja), dutch (nl), polish (pl), portuguese (pt), russian (ru), swahili (sw), thai (th), turkish (tr), urdu (ur), vietnamese (vi), and chinese (zh)

🔧 Technical Details

• Model Type: XLM - RoBERTa transformer model with a classification head.
• Base Model: [papluca/xlm - roberta - base - language - detection](https://huggingface.co/papluca/xlm - roberta - base - language - detection)
• Training Data: [Language Identification](https://huggingface.co/datasets/papluca/language - identification#additional - information) dataset
• Metrics: Accuracy, F1

📄 License

This model is released under the MIT license.

👥 Community

Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions, or engage in discussions about LLM security!