This paper describes a dataset of flute sounds with appropriate and inappropriate blowing styles. The flute is known as a difficult instrument to learn. We, therefore, have been developing a support system that automatically identifies the appropriateness of blowing in flute performances. To develop such a system, we need a dataset that consists of various sounds with various blowing styles, including both appropriate and inappropriate ways, but there are no such datasets. In this paper, we present the dataset that we have been developing. This dataset consists of sounds played by various players with various blowing styles, and also it has annotations of each sound's subjective evaluation.