Closed Shengqiang-Li closed 3 months ago
Support the wavlm discriminator, which leverages large speech language model representations to enhance the naturalness of the synthesized speech. (see this paper https://arxiv.org/pdf/2306.07691.pdf)
Support the wavlm discriminator, which leverages large speech language model representations to enhance the naturalness of the synthesized speech. (see this paper https://arxiv.org/pdf/2306.07691.pdf)
![img_v3_029e_d2073880-71da-47fd-9145-ac7e576a80dg](https://github.com/wenet-e2e/wetts/assets/49022799/5b99eab9-7512-485c-b60f-a1dba16f7f28)