F5-TTS repo and pinokio versions fail to synthesize cloned voice/ regular user-not a programmer

[mhouse777]

Checks

• This template is only for bug reports, usage problems go with 'Help Wanted'.
• I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
• I have searched for existing issues, including closed ones, and couldn't find a solution.
• I am using English to submit this issue to facilitate community communication.

Environment Details

windows 10 64 , python 310 , cuda 12.6 ,

Steps to Reproduce

1. start f5 TTs
2. . add 10 sec voice sample
3. cloned voice synthesis fails.
4. error message: F:\F5-TTS\venv\lib\site-packages\gradio\processing_utils.py:777: UserWarning: Trying to convert audio automatically from float32 to 16-bit int format.
   warnings.warn(warning.format(data.dtype))

✔️ Expected Behavior

synthesized cloned voice

❌ Actual Behavior

f5-tts fails to synthesize cloned voice in both repo and pinokio installment. Error message in terminal....F:\F5-TTS\venv\lib\site-packages\gradio\processing_utils.py:777: UserWarning: Trying to convert audio automatically from float32 to 16-bit int format.
warnings.warn(warning.format(data.dtype))

[SWivid]

UserWarning

[SWivid]

check torch version, input output stuff (see issue template)