OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-05-06 11:39:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(format): run black on dev

Browse Source
This commit is contained in:
github-actions[bot] 2024-04-21 16:46:13 +00:00
parent b06cdcce32
commit 35bfdccfb2
3 changed files with 28 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gui_v1.py
View File

@ -356,7 +356,7 @@ if __name__ == "__main__":
enable_events=True,
),
],
[
[
sg.Text(i18n("共振偏移")),
sg.Slider(
range=(-5, 5),

23
infer/lib/infer_pack/models.py
View File

@ -249,12 +249,17 @@ class Generator(torch.nn.Module):
if gin_channels != 0:
self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
def forward(self, x: torch.Tensor, g: Optional[torch.Tensor] = None, n_res: Optional[torch.Tensor] = None):
def forward(
self,
x: torch.Tensor,
g: Optional[torch.Tensor] = None,
n_res: Optional[torch.Tensor] = None,
):
if n_res is not None:
assert isinstance(n_res, torch.Tensor)
n = int(n_res.item())
if n != x.shape[-1]:
x = F.interpolate(x, size=n, mode='linear')
x = F.interpolate(x, size=n, mode="linear")
x = self.conv_pre(x)
if g is not None:
x = x + self.cond(g)
@ -532,17 +537,23 @@ class GeneratorNSF(torch.nn.Module):
self.upp = math.prod(upsample_rates)
self.lrelu_slope = modules.LRELU_SLOPE
def forward(self, x, f0, g: Optional[torch.Tensor] = None, n_res: Optional[torch.Tensor] = None):
def forward(
self,
x,
f0,
g: Optional[torch.Tensor] = None,
n_res: Optional[torch.Tensor] = None,
):
har_source, noi_source, uv = self.m_source(f0, self.upp)
har_source = har_source.transpose(1, 2)
if n_res is not None:
assert isinstance(n_res, torch.Tensor)
n = int(n_res.item())
if n * self.upp != har_source.shape[-1]:
har_source = F.interpolate(har_source, size=n*self.upp, mode='linear')
har_source = F.interpolate(har_source, size=n * self.upp, mode="linear")
if n != x.shape[-1]:
x = F.interpolate(x, size=n, mode='linear')
x = F.interpolate(x, size=n, mode="linear")
x = self.conv_pre(x)
if g is not None:
x = x + self.cond(g)

18
infer/lib/rtrvc.py
View File

@ -78,7 +78,7 @@ class RVC:
self.n_cpu = n_cpu
self.use_jit = self.config.use_jit
self.is_half = config.is_half
if index_rate != 0:
self.index = faiss.read_index(index_path)
self.big_npy = self.index.reconstruct_n(0, self.index.ntotal)
@ -92,9 +92,9 @@ class RVC:
self.cache_pitchf = torch.zeros(
1024, device=self.device, dtype=torch.float32
)
self.resample_kernel = {}
if last_rvc is None:
models, _, _ = fairseq.checkpoint_utils.load_model_ensemble_and_task(
["assets/hubert/hubert_base.pt"],
@ -191,10 +191,10 @@ class RVC:
def change_key(self, new_key):
self.f0_up_key = new_key
def change_formant(self, new_formant):
self.formant_shift = new_formant
def change_index_rate(self, new_index_rate):
if new_index_rate != 0 and self.index_rate == 0:
self.index = faiss.read_index(self.index_path)
@ -442,11 +442,13 @@ class RVC:
if upp_res != self.tgt_sr // 100:
if upp_res not in self.resample_kernel:
self.resample_kernel[upp_res] = Resample(
orig_freq=upp_res,
new_freq=self.tgt_sr // 100,
orig_freq=upp_res,
new_freq=self.tgt_sr // 100,
dtype=torch.float32,
).to(self.device)
infered_audio = self.resample_kernel[upp_res](infered_audio[: ,: return_length * upp_res])
infered_audio = self.resample_kernel[upp_res](
infered_audio[:, : return_length * upp_res]
)
t5 = ttime()
printt(
"Spent time: fea = %.3fs, index = %.3fs, f0 = %.3fs, model = %.3fs",