You can deploy this model and start earning money today!

toanle5124055/
vzdt-droroberta-pos

Name: vzdt-droroberta-pos
Availability: InStock

Views

No views yet

DRoBERTa POS Tagging for Vietnamese (No Diacritics)

This model is fine-tuned for Part-of-Speech tagging on Vietnamese text without diacritics using the Vietnamese Zero-Diacritic Treebank (VZDT).

Model Details

Base model: DRoBERTa
Task: Token Classification (POS)
Language: Vietnamese (no diacritics)
Data format: CoNLL-U

Usage

python

from transformers import pipeline

pipe = pipeline(
    "token-classification",
    model="toanle5124055/vzdt-droroberta-pos",
    tokenizer="toanle5124055/vzdt-droroberta-pos",
    aggregation_strategy="simple"
)

pipe("toi di hoc o truong dai hoc")