utils.py 文件源码

python
阅读 29 收藏 0 点赞 0 评论 0

项目:SynThai 作者: KenjiroAI 项目源码 文件源码
def _load(self):
        """Load text to memory"""

        corpus_directory = glob.escape(self.corpus_directory)
        file_list = sorted(glob.glob(os.path.join(corpus_directory, "*.txt")))

        for path in file_list:
            with open(path, "r", encoding="utf8") as text:
                # Read content from text file
                content = text.read()

                # Preprocessing
                content = self._preprocessing(content)

                # Create text instance
                text = Text(path, os.path.basename(path), content)

                # Add text to corpus
                self.__corpus.append(text)
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号