search

SWivid / F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
https://arxiv.org/abs/2410.06885
MIT License
4.53k stars 424 forks source link

using cpu only #176

Open d3r4j opened 9 hours ago

d3r4j commented 9 hours ago

python gradio_app.py Using cpu device Starting app... Running on local URL: http://127.0.0.1:7878 Traceback (most recent call last): File "D:\tech\F5-TTS\gradio_app.py", line 792, in main() File "C:\Users\dhira.conda\envs\f5\lib\site-packages\click\core.py", line 1157, in call return self.main(args, kwargs) File "C:\Users\dhira.conda\envs\f5\lib\site-packages\click\core.py", line 1078, in main rv = self.invoke(ctx) File "C:\Users\dhira.conda\envs\f5\lib\site-packages\click\core.py", line 1434, in invoke return ctx.invoke(self.callback, ctx.params) File "C:\Users\dhira.conda\envs\f5\lib\site-packages\click\core.py", line 783, in invoke return __callback(args, **kwargs) File "D:\tech\F5-TTS\gradio_app.py", line 785, in main app.queue(api_open=api).launch( File "C:\Users\dhira.conda\envs\f5\lib\site-packages\gradio\blocks.py", line 2465, in launch raise ValueError( ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

SWivid commented 7 hours ago

Running on cpu would be much slower. It is recommended to try with online space demos if the device at hand does not have a GPU.

Makkarob commented 7 hours ago

Owner

I'm using an i3 9100f with 32GB DDR4 and have no complaints. Unless you're voicing full Romeo and Juliet, you should be fine.