OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2024-12-29 19:15:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(sync): merge dev into main (#1408)

Browse Source 
* Update mdxnet.py

* Update modules.py

* Rename preprocess.py to vr.py

* Add files via upload

* deps: add av lib (#1391)

* Add files via upload

* chore(format): run black on dev (#1398)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* chore: sync dev to mian (#1404)

* Add files via upload

* Update rvc_for_realtime.py

* Add files via upload

* Add files via upload

* chore(format): run black on dev (#1407)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

---------

Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Co-authored-by: Hiroto N <hironow365@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: 源文雨 <41315874+fumiama@users.noreply.github.com>
This commit is contained in:
github-actions[bot] 2023-10-10 10:57:55 +08:00 committed by GitHub
parent 1696c5356b
commit c08426ac51
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 8 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
infer-web.py
View File

@ -16,16 +16,6 @@ from configs.config import Config
from sklearn.cluster import MiniBatchKMeans
from dotenv import load_dotenv
import torch
try:
import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
if torch.xpu.is_available():
from infer.modules.ipex import ipex_init
ipex_init()
except Exception: # pylint: disable=broad-exception-caught
pass
import numpy as np
import gradio as gr
import faiss
@ -449,7 +439,8 @@ def change_f0(if_f0_3, sr2, version19): # f0method8,pretrained_G14,pretrained_D
path_str = "" if version19 == "v1" else "_v2"
return (
{"visible": if_f0_3, "__type__": "update"},
*get_pretrained_models(path_str, "f0", sr2),
{"visible": if_f0_3, "__type__": "update"},
*get_pretrained_models(path_str, "f0" if if_f0_3 == True else "", sr2),
)
@ -1291,7 +1282,7 @@ with gr.Blocks(title="RVC WebUI") as app:
if_f0_3.change(
change_f0,
[if_f0_3, sr2, version19],
[f0method8, pretrained_G14, pretrained_D15],
[f0method8, gpus_rmvpe, pretrained_G14, pretrained_D15],
)
gpus16 = gr.Textbox(
label=i18n("以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2"),

2
infer/lib/infer_pack/models.py
View File

@ -1125,7 +1125,7 @@ class SynthesizerTrnMs768NSFsid_nono(nn.Module):
sr=None,
**kwargs
):
super(self, SynthesizerTrnMs768NSFsid_nono).__init__()
super(SynthesizerTrnMs768NSFsid_nono, self).__init__()
self.spec_channels = spec_channels
self.inter_channels = inter_channels
self.hidden_channels = hidden_channels

6
infer/modules/vc/pipeline.py
View File

@ -321,14 +321,14 @@ class Pipeline(object):
if audio_pad.shape[0] > self.t_max:
audio_sum = np.zeros_like(audio)
for i in range(self.window):
audio_sum += audio_pad[i : i - self.window]
audio_sum += np.abs(audio_pad[i : i - self.window])
for t in range(self.t_center, audio.shape[0], self.t_center):
opt_ts.append(
t
- self.t_query
+ np.where(
np.abs(audio_sum[t - self.t_query : t + self.t_query])
== np.abs(audio_sum[t - self.t_query : t + self.t_query]).min()
audio_sum[t - self.t_query : t + self.t_query]
== audio_sum[t - self.t_query : t + self.t_query].min()
)[0][0]
)
s = 0

2
tools/rvc_for_realtime.py
View File

@ -373,7 +373,7 @@ class RVC:
else:
printt("Index search FAILED or disabled")
except:
traceback.printt_exc()
traceback.print_exc()
printt("Index search FAILED")
feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
t3 = ttime()