slprl/StressTest

这是一个用于评估模型在句子重音推理和句子重音检测任务上的数据集，包含了218个语音样本及其相关特征，如转录文本、描述、语调、音频数据、元数据等。元数据中提供了说话人性别、语言代码、采样率和声音名称等信息。每个样本都有其对应的重音模式标注，包括二进制标记、重音词位置和实际重音词。

This is a dataset for evaluating models on Sentence Stress Reasoning (SSR) and Sentence Stress Detection (SSD) tasks, containing 218 speech samples with features such as transcription text, description, intonation, audio data, metadata, etc. The metadata provides information such as speaker gender, language code, sampling rate, and voice name. Each sample has its corresponding stress pattern annotation, including binary labels, stress word positions, and actual stress words.