Open JohnHerry opened 4 months ago
Hi, all I see no benefit from the CLVP module, the best score AR generated mel code may not so good, even with some timbre mixture, Should we put the speaker cond into the text tokens during training CLVP?
You can remove CLVP module, it's useless in my test. RLHF is somewhat more useful.
Thank you, and is there any more detailed information about the RLHF you are taking for this GPT generation?
Hi, all I see no benefit from the CLVP module, the best score AR generated mel code may not so good, even with some timbre mixture, Should we put the speaker cond into the text tokens during training CLVP?