Closed xiangmy21 closed 7 months ago
Oh I get it, not a problem. Just download from the demo page https://speechresearch.github.io/naturalspeech2/ or use own voice. But better provide a default example. Thanks~
Thanks for your attention and support towards our work. I will close this issue. If you have any further questions about prompt_examples
, please feel free to re-open this issue. We are glad to follow up!
Describe the bug
when use NaturalSpeech2 inference, it report RuntimeError: not found
NaturalSpeech2/prompt_example/ref_audio.wav
. same as https://github.com/open-mmlab/Amphion/issues/114, but in NaturalSpeech2, not VALLE. I think the problem comes from the .gitignore as well, it ignores all *.wav expect prompt_examples in VALLE now.How To Reproduce
follow https://huggingface.co/amphion/naturalspeech2_libritts .
Expected behavior
such as: