djopin/asr_compare
收藏Hugging Face2025-11-09 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/djopin/asr_compare
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含音频数据和对应参考文本的数据集，用于测试自动语音识别模型。数据集中的音频数据可能已经被多个版本的模型处理过，包括QuartzNet和Soloba模型的不同版本。数据集分为测试集，共有45个示例，总大小为20,690,456字节。
This dataset includes audio data and corresponding reference text for testing automatic speech recognition models. The audio data in the dataset may have been processed by multiple versions of models, including different versions of QuartzNet and Soloba models. The dataset is split into a test set with a total of 45 examples, totaling 20,690,456 bytes in size.
提供机构：
djopin
