fumiama/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-06-08 20:10:44 +08:00
Code Activity

optimize(infer.synthesizer): all modules inherit from one

Browse Source
This commit is contained in:
源文雨
2024-06-10 21:34:35 +09:00
parent b67050b2f7
commit e33ef19200
5 changed files with 127 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
infer/lib/rtrvc.py
View File

@@ -399,6 +399,7 @@ class RVC:
p_len = input_wav.shape[0] // 160
factor = pow(2, self.formant_shift / 12)
return_length2 = int(np.ceil(return_length * factor))
cache_pitch = cache_pitchf = None
if self.if_f0 == 1:
f0_extractor_frame = block_frame_16k + 800
if f0method == "rmvpe":
@@ -424,25 +425,18 @@ class RVC:
p_len = torch.LongTensor([p_len]).to(self.device)
sid = torch.LongTensor([0]).to(self.device)
skip_head = torch.LongTensor([skip_head])
return_length2 = torch.LongTensor([return_length2])
# return_length2 = torch.LongTensor([return_length2])
return_length = torch.LongTensor([return_length])
with torch.no_grad():
if self.if_f0 == 1:
infered_audio, _, _ = self.net_g.infer(
feats,
p_len,
cache_pitch,
cache_pitchf,
sid,
skip_head,
return_length,
return_length2,
)
else:
infered_audio, _, _ = self.net_g.infer(
feats, p_len, sid, skip_head, return_length, return_length2
)
infered_audio = infered_audio.squeeze(1).float()
infered_audio = self.net_g.infer(
feats,
p_len,
sid,
pitch=cache_pitch,
pitchf=cache_pitchf,
skip_head=skip_head,
return_length=return_length,
).squeeze(1).float()
upp_res = int(np.floor(factor * self.tgt_sr // 100))
if upp_res != self.tgt_sr // 100:
if upp_res not in self.resample_kernel: