The speaker of the first line is always [S1], regardless of whether I have already marked it as [S2]. S1 is female, S2 is male. <img width="925" height="272" alt="Image" src="https://github.com/user-attachments/assets/bf66a397-2a1c-419f-9064-b43c3f3233fa" /> [audio (2).wav](https://github.com/user-attachments/files/22860272/audio.2.wav)