chenming6615

Failed to trace C extension function in numpy

6

Hi, first thank you for making this awesome project ! I am trying to trace the execution of numpy with the following code: ``` python import numpy as np from...

The duration groud truth data shouldn't be used in synthesis in the validation step.

1

The `duration_target` is not None even when it is called in the validation step, which will cause the model to use the ground truth directly instead of the predicted data...

Why do we need `batch_size=batch_size * group_size`? What is the point of the `group_size` variable?

2

How can group_size larger than 1 will enable sorting in Dataset ? or Why do we need enable sorting in Dataset? https://github.com/ming024/FastSpeech2/blob/d4e79eb52e8b01d24703b2dfc0385544092958f3/train.py#L31 ``` python batch_size = train_config["optimizer"]["batch_size"] group_size = 4...