相同参数,语速相差非常大 #381
GwsinTracy
started this conversation in
General
Replies: 1 comment 1 reply
-
找到问题所在了,忽略。 |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
相同的length_scale参数,不同的启动后,生成的音频语速相差非常大。看了下这个是StochasticDurationPredictor模型生成的logw -> w -> y_lengths -> y_mask导致每次合成的长度不一样。
同一次启动的情况下,y_lengths相差不会很大,但是不同的启动下,y_lengths相差会非常大。
请问这个有人遇到过吗?可能会是什么原因导致的?
Beta Was this translation helpful? Give feedback.
All reactions