A pytorch implementation of the GAN-TTS: HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS(https://arxiv.org/pdf/1909.11646.pdf)
- I did not use the loss function mentioned in the paper. I modified the loss function and learn from MelGAN(https://arxiv.org/pdf/1910.06711.pdf).
- This is not official implementation, some details are not necessarily correct.
- Work in progress.