t5-large-korean-P2G

이 모델은 lcw99 / t5-large-korean-text-summary을 국립 국어원 신문 말뭉치 50만개의 문장을 2021을 g2pK로 훈련시켜 G2P된 데이터를 원본으로 돌립니다.
git : https://github.com/taemin6697

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
model_dir = "kfkas/t5-large-korean-P2G"
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForSeq2SeqLM.from_pretrained(model_dir)

text = "서규왕국 싸우디 태양광·풍녁 빨쩐 중심지 될 껃"
inputs = tokenizer.encode(text,return_tensors="pt")
output = model.generate(inputs)
decoded_output = tokenizer.batch(output[0], skip_special_tokens=True)
print(decoded_output)#석유왕국 사우디 태양광·풍력 발전 중심지 될 것

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: None
• training_precision: float16

Training results

Framework versions

• Transformers 4.22.1
• TensorFlow 2.10.0
• Datasets 2.5.1
• Tokenizers 0.12.1