w-okada / voice-changer

リアルタイムボイスチェンジャー Realtime Voice Changer
Other
16.65k stars 1.81k forks source link

Exception during loading hubert/contentvec model stat #222

Closed buildcore closed 1 year ago

buildcore commented 1 year ago

Tried: loaded two models so-vits-svc and rvc independently (.json, .pt, .pth), loaded correctly Device: MacOS M1

Something looks wrong in SoVitsSvc40.py, in loadModel():

content_vec_path = self.params.content_vec_500
        content_vec_onnx_path = self.params.content_vec_500_onnx
        content_vec_onnx_on = self.params.content_vec_500_onnx_on
        hubert_base_path = self.params.hubert_base

Moreover, got an exception on "voice_changer/VoiceChanger.py":

VC PROCESSING!!!! EXCEPTION!!! ufunc 'resample_f_s' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule "'safe'
Traceback (most recent call last):
File "voice_changer/VoiceChanger py", line 231, in on_request_sola
File "resampy/core.py", line 168, in resample File "numba/np/ufunc/gufunc.py", line 192, in _call.
lypetrror: ufunc 'resample_f_s' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule lisafpli
w-okada commented 1 year ago

I cannot reproduce it. please tell me how to reproduce.

w-okada commented 1 year ago

no res. close