语言: 中文

标签:

• 句子修正

• 文本生成

许可协议: cc-by-nc-sa-4.0

数据集:

• jfleg

模型

该模型基于T5-base预训练模型，使用改进版JFLEG数据集和Happy Transformer框架进行微调。专为加勒比英语克里奥尔语的标准英语翻译和位置性英语翻译的句子修正而优化。随着数据集的持续扩充，本模型将定期更新。关于加勒比英语克里奥尔语的更多信息，请访问Caribe库。

重新训练/微调

微调后的最终准确率达到92%

使用方法

from happytransformer import HappyTextToText, TTSettings

pre_trained_model="T5"
model = HappyTextToText(pre_trained_model, "KES/T5-KES")

arguments = TTSettings(num_beams=4, min_length=1)
sentence = "Wat iz your nam"

correction = model.generate_text("grammar: "+sentence, args=arguments)
if(correction.text.find(" .")):
    correction.text=correction.text.replace(" .", ".")

print(correction.text) # 修正结果: "What is your name?".

使用Transformers库

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("KES/T5-KES")
model = AutoModelForSeq2SeqLM.from_pretrained("KES/T5-KES")

text = "I am lived with my parenmts "
inputs = tokenizer("grammar:"+text, truncation=True, return_tensors='pt')

output = model.generate(inputs['input_ids'], num_beams=4, max_length=512, early_stopping=True)
correction=tokenizer.batch_decode(output, skip_special_tokens=True)
print("".join(correction)) #修正结果: I am living with my parents.