add_prenet=False？

[yangyyt]

Why should add_prenet be set to false? If it is not set to True, false is indeed better after the experiment, but I do not understand why, can you help to explain. thx. @lifeiteng

[yfyeung]

Text units can be directly embedded because they are discrete points that map to continuous vectors in an embedding space. In contrast, audio features are continuous and physically meaningful, requiring an extra network (a prenet) to transform them into more abstract representations for further processing.