fish-speech icon indicating copy to clipboard operation
fish-speech copied to clipboard

Error when clicking on generate in web ui page

Open kevin1121 opened this issue 2 months ago • 1 comments

Self Checks

  • [X] This template is only for bug reports. For questions, please visit Discussions.
  • [X] I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
  • [X] I have searched for existing issues, including closed ones. Search issues
  • [X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
  • [X] Please do not modify this template and fill in all required fields.

Cloud or Self Hosted

Self Hosted (Source)

Environment Details

macOS 15.2、Python 3.10、torch=2.4.1、Gradio 5.9.1

Steps to Reproduce

1.Run command: python -m tools.run_webui
--llama-checkpoint-path "checkpoints/fish-speech-1.5"
--decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"
--decoder-config-name firefly_gan_vq

image image

The page can be accessed as normal

image

When clicking Generate, the page reports an error: Expected elements.dtype() == test_elements.dtype() to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

image

No error message in the command line window

✔️ Expected Behavior

Ability to generate corresponding voice files according to the text.

❌ Actual Behavior

Page error: Expected elements.dtype() == test_elements.dtype() to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

kevin1121 avatar Dec 23 '24 08:12 kevin1121