Fiber-terahertz communication is regarded as one of the best candidates for future 6G mobile communication systems. Using fiber optic-assisted terahertz communication can solve the problem of large-capacity terahertz coverage. Still, it also leads to more complex and variable channel environments. This makes channel estimation for fiber terahertz communication challenging. In this paper, we use the conditional generative adversarial networks (CGAN) to solve channel estimation problems with their excellent mapping ability to complex relationships. Meanwhile, we further improved the performance of the network by using a residual structure and an unrolled structure. Compared with the traditional recurrent neural networks (RNN) and convolutional neural networks (CNN), the normalized mean squared error (NMSE) of CGAN-based fiber terahertz channel estimation is reduced by up to 1.93 dB and 1.02 dB, respectively.