[VITS] Fix speaker_embed device mismatch (#26115)
* [VITS] Fix speaker_embed device mismatch
- pass device arg to speaker_id tensor
* [VITS] put speaker_embed on device when int
* [VITS] device=self.device
instead of self.embed_speaker.weight.device
* [VITS] make tensor directly on device
using torch.full()
