fumiama/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-06-10 13:00:36 +08:00
Code Activity

Support mps generate (#263)

Browse Source
This commit is contained in:
Ftps
2023-05-10 22:17:13 +09:00
committed by GitHub
parent 5b0ff12163
commit 6cc2279fb9
2 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vc_infer_pipeline.py
View File

@@ -246,6 +246,8 @@ class VC(object):
pitch, pitchf = self.get_f0(audio_pad, p_len, f0_up_key, f0_method, inp_f0)
pitch = pitch[:p_len]
pitchf = pitchf[:p_len]
if self.device == "mps":
pitchf = pitchf.astype(np.float32)
pitch = torch.tensor(pitch, device=self.device).unsqueeze(0).long()
pitchf = torch.tensor(pitchf, device=self.device).unsqueeze(0).float()
t2 = ttime()