Error when clicking on generate in web ui page

[kevin1121]

Self Checks

• This template is only for bug reports. For questions, please visit Discussions.
• 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)
• I have searched for existing issues, including closed ones. Search issues
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• 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

The page can be accessed as normal

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.)

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.)

[LeafYeeXYZ]

I encountered the same error when using MPS on my Mac (both in webui and http api)

here is a temporary solution (using CPU):

        # if torch.backends.mps.is_available():
        if False:
            self.device = "mps"
            logger.info("mps is available, running on mps.")
        elif not torch.cuda.is_available():
            self.device = "cpu"
            logger.info("CUDA is not available, running on CPU.")