https://github.com/ayaka14732/bart-base-cantonese
The pre-trained Cantonese BART model
https://github.com/ayaka14732/bart-base-cantonese
bart cantonese huggingface nlp pre-trained-model transformer
Last synced: about 1 year ago
JSON representation
The pre-trained Cantonese BART model
- Host: GitHub
- URL: https://github.com/ayaka14732/bart-base-cantonese
- Owner: ayaka14732
- Created: 2022-11-06T15:32:47.000Z (over 3 years ago)
- Default Branch: 2nd-stage-pre-train
- Last Pushed: 2022-11-06T15:37:42.000Z (over 3 years ago)
- Last Synced: 2025-03-25T15:50:13.996Z (about 1 year ago)
- Topics: bart, cantonese, huggingface, nlp, pre-trained-model, transformer
- Language: Python
- Homepage: https://huggingface.co/Ayaka/bart-base-cantonese
- Size: 262 KB
- Stars: 8
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# BART Base Cantonese
This is the Cantonese model of BART base. It is obtained by a second-stage pre-training on the [LIHKG dataset](https://github.com/ayaka14732/lihkg-scraper) based on the [fnlp/bart-base-chinese](https://huggingface.co/fnlp/bart-base-chinese) model.
This project is supported by Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC).
## Usage
```python
from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained('Ayaka/bart-base-cantonese')
model = BartForConditionalGeneration.from_pretrained('Ayaka/bart-base-cantonese')
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(' ', ''))
# output: 聽日就要返香港，我激動到瞓唔着
```