[hts-users:00764] Questions on training and flat pitch pattern

["Lee Sillon" <sillon.lee@xxxxxxxxx>]

Dear all,

 

I have some problems about model training,

 

1. If the training corpus is larger (for example,10,000 sentences), the training process will crash because of memory consuming(about 2GB). Could it be solved?

2. How many sentences are enough for training a good model? 1000 sentences are enough or not?

3. In some papers, POS is considered because it influence pitch pattern a lot. But in the demo, it is ignored. Is it one of reasons that cause flat pitch pattern?

 

Thanks in advance!

 
--
Have a nice day!
Sillon Lee