zhouyong64

Results 4 comments of zhouyong64
trafficstars

On what kind of datasets does the model trained on?

> Actually, `daanzu_multi_en` is a partial and unfinished training pipeline. I have ended up working with a heavily modified version of the Zamia pipeline. The datasets are: > > *...

Does it will work on unseen data also? will it be able to convert voice of unseen speaker with different content than that of data in training, will we obtain the disentanglement?

I have the same question.

Extremely weird DDP issue for train_second.py

Did you try other versions of PyTorch?

After 100 epochs training, the model can synthesize natural speech on LibriTTS

@dohe0342 Could you share this file "unique_text_tokens.k2symbols"? It's need for inference.