PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-02-02 16:23:58 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

DDSP-SVC: silent-front, auto_adaptive_key

Browse Source
This commit is contained in:
wataru 2023-04-19 04:30:56 +09:00
parent 513a85e6c7
commit 3ad903fad6
5 changed files with 1622 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
client/demo/dist/index.html vendored
View File

@ -1 +1,10 @@
<!doctype html><html style="width:100%;height:100%;overflow:hidden"><head><meta charset="utf-8"/><title>Voice Changer Client Demo</title><script defer="defer" src="index.js"></script></head><body style="width:100%;height:100%;margin:0"><div id="app" style="width:100%;height:100%"></div></body></html>
<!DOCTYPE html>
<html style="width: 100%; height: 100%; overflow: hidden">
<head>
<meta charset="utf-8" />
<title>Voice Changer Client Demo</title>
<script defer src="index.js"></script></head>
<body style="width: 100%; height: 100%; margin: 0px">
<div id="app" style="width: 100%; height: 100%"></div>
</body>
</html>

1607
client/demo/dist/index.js vendored
View File

File diff suppressed because one or more lines are too long

31
client/demo/dist/index.js.LICENSE.txt vendored
View File

@ -1,31 +0,0 @@
/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
/**
* @license React
* react-dom.production.min.js
*
* Copyright (c) Facebook, Inc. and its affiliates.
*
* This source code is licensed under the MIT license found in the
* LICENSE file in the root directory of this source tree.
*/
/**
* @license React
* react.production.min.js
*
* Copyright (c) Facebook, Inc. and its affiliates.
*
* This source code is licensed under the MIT license found in the
* LICENSE file in the root directory of this source tree.
*/
/**
* @license React
* scheduler.production.min.js
*
* Copyright (c) Facebook, Inc. and its affiliates.
*
* This source code is licensed under the MIT license found in the
* LICENSE file in the root directory of this source tree.
*/

4
client/demo/src/components/demo/components/610_EnableEnhancerRow.tsx
View File

@ -21,7 +21,7 @@ export const EnableEnhancerRow = (_props: EnableEnhancerRowProps) => {
</select>
</div>
</div>
<div className="body-row split-3-3-4 left-padding-1 guided">
{/* <div className="body-row split-3-3-4 left-padding-1 guided">
<div className="body-item-title left-padding-1 ">Enhancer Tune</div>
<div>
<input type="range" className="body-item-input-slider" min="0" max="10" step="1" value={appState.serverSetting.serverSetting.enhancerTune || 0} onChange={(e) => {
@ -31,7 +31,7 @@ export const EnableEnhancerRow = (_props: EnableEnhancerRowProps) => {
</div>
<div className="body-button-container">
</div>
</div>
</div> */}
</>
)
}, [

7
server/voice_changer/DDSP_SVC/DDSP_SVC.py
View File

@ -199,7 +199,8 @@ class DDSP_SVC:
self.audio_buffer = self.audio_buffer[-1 * convertSize:] # 変換対象の部分だけ抽出
# f0
f0 = self.f0_detector.extract(self.audio_buffer * 32768.0, uv_interp=True)
f0 = self.f0_detector.extract(self.audio_buffer * 32768.0, uv_interp=True,
silence_front=self.settings.extraConvertSize / self.sampling_rate)
f0 = torch.from_numpy(f0).float().unsqueeze(-1).unsqueeze(0)
f0 = f0 * 2 ** (float(self.settings.tran) / 12)
@ -285,7 +286,9 @@ class DDSP_SVC:
self.args.data.sampling_rate,
f0,
self.args.data.block_size,
adaptive_key=float(self.settings.enhancerTune))
# adaptive_key=float(self.settings.enhancerTune),
adaptive_key='auto',
silence_front=self.settings.extraConvertSize / self.sampling_rate)
result = seg_output.squeeze().cpu().numpy() * 32768.0
return np.array(result).astype(np.int16)