Praha-Labs/IndexTTS-nano-codec

该数据集包含文本数据以及与文本相关的四个整数列表层（nano_layer_1至nano_layer_4），和一个表示编码长度的整数字段(encoded_len)。数据集被划分为训练集，包含34473个示例。具体的应用场景和文本内容在README文件中未提供。The dataset includes text data along with four integer list layers associated with the text (nano_layer_1 to nano_layer_4), and an integer field representing the encoding length (encoded_len). The dataset is split into a training set containing 34,473 examples. The specific application scenario and the content of the text are not provided in the README file.