tuanh123789 / AdaSpeech

An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"
96 stars 27 forks source link

How does the speakerembedding part work when finetune #13

Open tuntun990606 opened 1 year ago

tuntun990606 commented 1 year ago

I would like to ask that the speaker used in finetune is unknown, so what should be done with the speakerembedding section?

tuntun990606 commented 1 year ago

I found that when I finetune with a new speaker , the speaker_id will be set to 0 by default, isn't it?

tuanh123789 commented 1 year ago

I found that when I finetune with a new speaker , the speaker_id will be set to 0 by default, isn't it? Yes, that's right.