# Model description

- Morphosyntactic analyzer: Trankit
- Tagset: UD
- Embedding vectors: XLM-RoBERTa-Large
- Dataset: PDB (http://git.nlp.ipipan.waw.pl/alina/PDBUD/tree/master/PDB-UD/PDB-UD)

# How to use

## Clone

```
git clone git@hf.co:ipipan/nlpre_trankit_ud_xlm-roberta-large_pdb
```

## Load model

```
import trankit

model_path = './nlpre_trankit_ud_xlm-roberta-large_pdb'

trankit.verify_customized_pipeline(
    category='customized-mwt', # pipeline category
    save_dir=model_path, # directory used for saving models in previous steps
    embedding_name='xlm-roberta-large' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base`
)

model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-large')
```