README.md

metadata

language:
  - yue
tags:
  - bart
  - cantonese
  - fill-mask
license: other

bart-base-cantonese

This is the Cantonese model of BART base. It is based on another model created by: https://huggingface.co/Ayaka/bart-base-cantonese

Usage

from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained('jed351/bart-zh-hk-wiki')
model = BartForConditionalGeneration.from_pretrained('jed351/bart-zh-hk-wiki')
text2text_generator = Text2TextGenerationPipeline(model, tokenizer)  
output = text2text_generator('聽日就要返香港，我激動到[MASK]唔着', max_length=50, do_sample=False)
print(output[0]['generated_text'].replace(' ', ''))

Note: Please use the BertTokenizer for the model vocabulary. DO NOT use the original BartTokenizer.