work

@syang1993 Thanks for reply, Does it mean that the training data requires sentences of the same person's different rhythms? What is the data in Blizzard Challenge 2013? I am still...

@bfs18 Hi,I use your model(wavenet_mol without pwn) to test synthesized speech, the mute part will become a murmur, and the non-mute part is normal. Do you know why? Is it...

What dataset do you use in this model?

> @switchzts , It is our owner mandarin corpus. Hi~I just want to know how long audio do you use in this model,and is it multi-speaker-dataset?

> @switchzts , Its average length is about 4s~5s. It is a single speaker database. hi,I mean the total time of the data set you used.BTW, what number of loss...

> @switchzts ， num_layers=10 in the model. The total time is about 12h. The train loss is about 11.0. "use_mu_law": true, Do you set it to true?

Why is my output a meaningless vocal? Instead of a sentence？Do you have any idea about it?

> What is your input? Do you give model conditional input? I use build_data to turn some .wav to TFRECORD file, and I think I have give model conditional input....