We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
大概看了下是通过bert提取char embedding,和音素拼接输入给模型,没有看到停顿是如何处理的。
The text was updated successfully, but these errors were encountered:
这个bert模型是用停顿训练的;bert的char embedding通过softmax可以得到停顿标注 #1 #2 ~~~;用显示的停顿标注训练TTS,需要将将停顿标注转换成embedding;有点多余的感觉,所以就直接用的char embedding。
Sorry, something went wrong.
所以说可以理解为这个bert embedding用来控制停顿+韵律,输入文本,bert会自动预测停顿,和文本中的标点符号没有直接关系呗?
所以说可以理解为这个bert embedding用来控制停顿+韵律,输入文本,bert会自动预测停顿 --是的 和文本中的标点符号没有直接关系呗? --bert支持标点吧,时间有点久了,记不太清了
No branches or pull requests
大概看了下是通过bert提取char embedding,和音素拼接输入给模型,没有看到停顿是如何处理的。
The text was updated successfully, but these errors were encountered: