Skip to content
New issue

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

PNNX转换fastspeech2的onnx模型报错 #5758

Open
qweasdzxcvde opened this issue Oct 24, 2024 · 2 comments
Open

PNNX转换fastspeech2的onnx模型报错 #5758

qweasdzxcvde opened this issue Oct 24, 2024 · 2 comments

Comments

@qweasdzxcvde
Copy link

大佬们,第一次使用ncnn,在转换模型的时候报错
阅读源码发现部分环节会直接随机初始化输入到模型,但是模型的输入是有范围的,请问这个有什么方法可以解决吗?

error log | 日志或报错信息 | ログ

image

model | 模型 | モデル

  1. original model
    转换的是tts的fastspeech2模型,输入是音素的id和说话人的id,音素id取值范围是0-254,说话人id的取值范围是0-5

how to reproduce | 复现步骤 | 再現方法

  1. 解压模型文件
  2. 运行 pnnx fastspeech2_aishell3.onnx inputshape=[1]i32,[1]i32
    fastspeech2_aishell3.zip
@wzyforgit
Copy link
Contributor

感觉像是把前处理给搞进去了,得把这部分挖出来作为你的外部输入,然后再转

@qweasdzxcvde
Copy link
Author

好的,我试下,谢谢大佬

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants