1berry/wokada-voice-changer
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

WIP: support rvc-webui, export onnxs is not support yet

Browse Source
This commit is contained in:
wataru 2023-04-24 16:43:51 +09:00
parent 11a536b03f
commit cdceae9cf1
33 changed files with 819 additions and 122 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
client/demo/dist/assets/gui_settings/DDSP-SVC.json vendored
View File

@ -43,6 +43,7 @@
"showFeature": false,
"showIndex": false,
"showHalfPrecision": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true,
"showOnnxExportButton": false

1
client/demo/dist/assets/gui_settings/MMVCv13.json vendored
View File

@ -40,6 +40,7 @@
"showCorrespondence": false,
"showPyTorchCluster": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": false
}
},

2
client/demo/dist/assets/gui_settings/MMVCv15.json vendored
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": true,
"showPyTorchCluster": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": false
}
},

22
client/demo/dist/assets/gui_settings/RVC.json vendored
View File

@ -36,6 +36,10 @@
{
"name": "onnxExport",
"options": {}
},
{
"name": "onnxExecutor",
"options": {}
}
],
"modelSetting": [
@ -43,29 +47,23 @@
"name": "modelUploader",
"options": {
"showModelSlot": true,
"showFrameworkSelector": false,
"showConfig": false,
"showOnnx": true,
"showPyTorch": true,
"oneModelFileType": true,
"showOnnx": false,
"showPyTorch": false,
"showCorrespondence": false,
"showPyTorchCluster": false,
"showFeature": true,
"showIndex": true,
"showHalfPrecision": true,
"showPyTorchEnableCheckBox": false,
"defaultEnablePyTorch": true,
"onlySelectedFramework": true,
"showDefaultTune": true
}
},
{
"name": "framework",
"options": {
"showFramework": true
}
},
{
"name": "modelSamplingRate",
"options": {}
}
],
"deviceSetting": [

183
client/demo/dist/assets/gui_settings/RVC_CLASSIC.json vendored Normal file
View File

@ -0,0 +1,183 @@
{
"type": "demo",
"id": "RVC",
"front": {
"title": [
{
"name": "title",
"options": {
"mainTitle": "Realtime Voice Changer Client",
"subTitle": "for RVC",
"lineNum": 1
}
},
{
"name": "clearSetting",
"options": {}
}
],
"serverControl": [
{
"name": "startButton",
"options": {}
},
{
"name": "performance",
"options": {}
},
{
"name": "serverInfo",
"options": {}
},
{
"name": "modelSwitch",
"options": {}
},
{
"name": "onnxExport",
"options": {}
}
],
"modelSetting": [
{
"name": "modelUploader",
"options": {
"showModelSlot": true,
"showConfig": false,
"showOnnx": true,
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": false,
"showFeature": true,
"showIndex": true,
"showHalfPrecision": true,
"defaultEnablePyTorch": true,
"showDefaultTune": true
}
},
{
"name": "framework",
"options": {
"showFramework": true
}
},
{
"name": "modelSamplingRate",
"options": {}
}
],
"deviceSetting": [
{
"name": "audioInput",
"options": {}
},
{
"name": "audioOutput",
"options": {}
}
],
"qualityControl": [
{
"name": "noiseControl",
"options": {}
},
{
"name": "gainControl",
"options": {}
},
{
"name": "f0Detector",
"options": {
"detectors": ["pm", "harvest"]
}
},
{
"name": "divider",
"options": {}
},
{
"name": "analyzer",
"options": {}
}
],
"speakerSetting": [
{
"name": "dstId",
"options": {
"showF0": true,
"useServerInfo": false
}
},
{
"name": "tune",
"options": {}
},
{
"name": "indexRatio",
"options": {}
},
{
"name": "silentThreshold",
"options": {}
}
],
"converterSetting": [
{
"name": "inputChunkNum",
"options": {}
},
{
"name": "extraDataLength",
"options": {}
},
{
"name": "gpu",
"options": {}
}
],
"advancedSetting": [
{
"name": "protocol",
"options": {}
},
{
"name": "crossFadeOverlapSize",
"options": {}
},
{
"name": "crossFadeOffsetRate",
"options": {}
},
{
"name": "crossFadeEndRate",
"options": {}
},
{
"name": "trancateNumThreshold",
"options": {}
},
{
"name": "rvcQuality",
"options": {}
},
{
"name": "silenceFront",
"options": {}
}
]
},
"dialogs": {
"license": [
{
"title": "Retrieval-based-Voice-Conversion-WebUI",
"auther": "liujing04",
"contact": "",
"url": "https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI",
"license": "MIT"
}
]
}
}

2
client/demo/dist/assets/gui_settings/so-vits-svc-40.json vendored
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": true,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true
}
},

2
client/demo/dist/assets/gui_settings/so-vits-svc-40v2.json vendored
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": true,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true
}
},

57
client/demo/dist/index.js vendored
View File

File diff suppressed because one or more lines are too long

1
client/demo/public/assets/gui_settings/DDSP-SVC.json
View File

@ -43,6 +43,7 @@
"showFeature": false,
"showIndex": false,
"showHalfPrecision": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true,
"showOnnxExportButton": false

1
client/demo/public/assets/gui_settings/MMVCv13.json
View File

@ -40,6 +40,7 @@
"showCorrespondence": false,
"showPyTorchCluster": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": false
}
},

2
client/demo/public/assets/gui_settings/MMVCv15.json
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": true,
"showPyTorchCluster": false,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": false
}
},

22
client/demo/public/assets/gui_settings/RVC.json
View File

@ -36,6 +36,10 @@
{
"name": "onnxExport",
"options": {}
},
{
"name": "onnxExecutor",
"options": {}
}
],
"modelSetting": [
@ -43,29 +47,23 @@
"name": "modelUploader",
"options": {
"showModelSlot": true,
"showFrameworkSelector": false,
"showConfig": false,
"showOnnx": true,
"showPyTorch": true,
"oneModelFileType": true,
"showOnnx": false,
"showPyTorch": false,
"showCorrespondence": false,
"showPyTorchCluster": false,
"showFeature": true,
"showIndex": true,
"showHalfPrecision": true,
"showPyTorchEnableCheckBox": false,
"defaultEnablePyTorch": true,
"onlySelectedFramework": true,
"showDefaultTune": true
}
},
{
"name": "framework",
"options": {
"showFramework": true
}
},
{
"name": "modelSamplingRate",
"options": {}
}
],
"deviceSetting": [

183
client/demo/public/assets/gui_settings/RVC_CLASSIC.json Normal file
View File

@ -0,0 +1,183 @@
{
"type": "demo",
"id": "RVC",
"front": {
"title": [
{
"name": "title",
"options": {
"mainTitle": "Realtime Voice Changer Client",
"subTitle": "for RVC",
"lineNum": 1
}
},
{
"name": "clearSetting",
"options": {}
}
],
"serverControl": [
{
"name": "startButton",
"options": {}
},
{
"name": "performance",
"options": {}
},
{
"name": "serverInfo",
"options": {}
},
{
"name": "modelSwitch",
"options": {}
},
{
"name": "onnxExport",
"options": {}
}
],
"modelSetting": [
{
"name": "modelUploader",
"options": {
"showModelSlot": true,
"showConfig": false,
"showOnnx": true,
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": false,
"showFeature": true,
"showIndex": true,
"showHalfPrecision": true,
"defaultEnablePyTorch": true,
"showDefaultTune": true
}
},
{
"name": "framework",
"options": {
"showFramework": true
}
},
{
"name": "modelSamplingRate",
"options": {}
}
],
"deviceSetting": [
{
"name": "audioInput",
"options": {}
},
{
"name": "audioOutput",
"options": {}
}
],
"qualityControl": [
{
"name": "noiseControl",
"options": {}
},
{
"name": "gainControl",
"options": {}
},
{
"name": "f0Detector",
"options": {
"detectors": ["pm", "harvest"]
}
},
{
"name": "divider",
"options": {}
},
{
"name": "analyzer",
"options": {}
}
],
"speakerSetting": [
{
"name": "dstId",
"options": {
"showF0": true,
"useServerInfo": false
}
},
{
"name": "tune",
"options": {}
},
{
"name": "indexRatio",
"options": {}
},
{
"name": "silentThreshold",
"options": {}
}
],
"converterSetting": [
{
"name": "inputChunkNum",
"options": {}
},
{
"name": "extraDataLength",
"options": {}
},
{
"name": "gpu",
"options": {}
}
],
"advancedSetting": [
{
"name": "protocol",
"options": {}
},
{
"name": "crossFadeOverlapSize",
"options": {}
},
{
"name": "crossFadeOffsetRate",
"options": {}
},
{
"name": "crossFadeEndRate",
"options": {}
},
{
"name": "trancateNumThreshold",
"options": {}
},
{
"name": "rvcQuality",
"options": {}
},
{
"name": "silenceFront",
"options": {}
}
]
},
"dialogs": {
"license": [
{
"title": "Retrieval-based-Voice-Conversion-WebUI",
"auther": "liujing04",
"contact": "",
"url": "https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI",
"license": "MIT"
}
]
}
}

2
client/demo/public/assets/gui_settings/so-vits-svc-40.json
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": true,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true
}
},

2
client/demo/public/assets/gui_settings/so-vits-svc-40v2.json
View File

@ -39,7 +39,7 @@
"showPyTorch": true,
"showCorrespondence": false,
"showPyTorchCluster": true,
"showPyTorchEnableCheckBox": true,
"defaultEnablePyTorch": true
}
},

2
client/demo/src/001_ClientSelector.tsx
View File

@ -19,7 +19,7 @@ export const ClientSelector = () => {
if (ua.indexOf("mac os x") !== -1) {
return ["MMVCv13", "MMVCv15", "so-vits-svc-40", "RVC"] as ClientType[]
} else {
return ["MMVCv13", "MMVCv15", "so-vits-svc-40", "so-vits-svc-40v2", "RVC", "DDSP-SVC"] as ClientType[]
return ["MMVCv13", "MMVCv15", "so-vits-svc-40", "so-vits-svc-40v2", "RVC", "DDSP-SVC", "RVC_CLASSIC_GUI"] as ClientType[]
}
}, [])

2
client/demo/src/components/demo/002_ComponentGenerator.tsx
View File

@ -42,6 +42,7 @@ import { DstIdRow2, DstIdRow2Props } from "./components/602v2_DstIdRow2"
import { SilenceFrontRow, SilenceFrontRowProps } from "./components/812_SilenceFrontRow"
import { ModelSwitchRow, ModelSwitchRowProps } from "./components/204_ModelSwitchRow"
import { ONNXExportRow, ONNXExportRowProps } from "./components/205_ONNXExportRow"
import { ONNXExecutorRow, ONNXExecutorRowProps } from "./components/206_ONNXExecutorRow"
export const catalog: { [key: string]: (props: any) => JSX.Element } = {}
@ -68,6 +69,7 @@ const initialize = () => {
addToCatalog("serverInfo", (props: ServerInfoRowProps) => { return <ServerInfoRow {...props} /> })
addToCatalog("modelSwitch", (props: ModelSwitchRowProps) => { return <ModelSwitchRow {...props} /> })
addToCatalog("onnxExport", (props: ONNXExportRowProps) => { return <ONNXExportRow {...props} /> })
addToCatalog("onnxExecutor", (props: ONNXExecutorRowProps) => { return <ONNXExecutorRow {...props} /> })

16
client/demo/src/components/demo/components/204_ModelSwitchRow.tsx
View File

@ -1,3 +1,4 @@
import { Framework } from "@dannadori/voice-changer-client-js"
import React, { useMemo } from "react"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
@ -9,20 +10,23 @@ export const ModelSwitchRow = (_props: ModelSwitchRowProps) => {
const appState = useAppState()
const modelSwitchRow = useMemo(() => {
const slot = appState.serverSetting.serverSetting.modelSlotIndex
const onSwitchModelClicked = (index: number) => {
appState.serverSetting.updateServerSettings({ ...appState.serverSetting.serverSetting, modelSlotIndex: index })
const onSwitchModelClicked = (index: number, filename: string) => {
const framework: Framework = filename.endsWith(".onnx") ? "ONNX" : "PyTorch"
console.log("Framework:::", filename, framework)
appState.serverSetting.updateServerSettings({ ...appState.serverSetting.serverSetting, modelSlotIndex: index, framework: framework })
}
let filename = ""
const modelOptions = appState.serverSetting.serverSetting.modelSlots.map((x, index) => {
const className = index == slot ? "body-button-active left-margin-1" : "body-button left-margin-1"
let filename = ""
if (x.pyTorchModelFile && x.pyTorchModelFile.length > 0) {
filename = x.pyTorchModelFile.replace(/^.*[\\\/]/, '')
return <div key={index} className="body-button left-margin-1" onClick={() => { onSwitchModelClicked(index) }}>{filename}</div>
return <div key={index} className={className} onClick={() => { onSwitchModelClicked(index, filename) }}>{filename}</div>
} else if (x.onnxModelFile && x.onnxModelFile.length > 0) {
filename = x.onnxModelFile.replace(/^.*[\\\/]/, '')
return <div key={index} className="body-button left-margin-1" onClick={() => { onSwitchModelClicked(index) }}>{filename}</div>
return <div key={index} className={className} onClick={() => { onSwitchModelClicked(index, filename) }}>{filename}</div>
} else {
return <div key={index} ></div>
}

4
client/demo/src/components/demo/components/205_ONNXExportRow.tsx
View File

@ -12,6 +12,10 @@ export const ONNXExportRow = (_props: ONNXExportRowProps) => {
const guiState = useGuiState()
const onnxExporthRow = useMemo(() => {
if (appState.serverSetting.serverSetting.framework != "PyTorch") {
return <></>
}
const onnxExportButtonAction = async () => {
if (guiState.isConverting) {

43
client/demo/src/components/demo/components/206_ONNXExecutorRow.tsx Normal file
View File

@ -0,0 +1,43 @@
import { OnnxExecutionProvider, OnnxExporterInfo } from "@dannadori/voice-changer-client-js"
import React, { useMemo } from "react"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
import { useGuiState } from "../001_GuiStateProvider"
export type ONNXExecutorRowProps = {
}
export const ONNXExecutorRow = (_props: ONNXExecutorRowProps) => {
const appState = useAppState()
const onnxExecutorRow = useMemo(() => {
if (appState.serverSetting.serverSetting.framework != "ONNX") {
return <></>
}
const onOnnxExecutionProviderChanged = async (val: OnnxExecutionProvider) => {
appState.serverSetting.updateServerSettings({ ...appState.serverSetting.serverSetting, onnxExecutionProvider: val })
}
return (
<div className="body-row split-3-7 left-padding-1">
<div className="body-item-title left-padding-2">OnnxExecutionProvider</div>
<div className="body-select-container">
<select className="body-select" value={appState.serverSetting.serverSetting.onnxExecutionProvider} onChange={(e) => {
onOnnxExecutionProviderChanged(e.target.value as
OnnxExecutionProvider)
}}>
{
Object.values(OnnxExecutionProvider).map(x => {
return <option key={x} value={x}>{x}</option>
})
}
</select>
</div>
</div>
)
}, [appState.getInfo, appState.serverSetting.serverSetting])
return onnxExecutorRow
}

73
client/demo/src/components/demo/components/301-2-5_ModelSelectRow copy.tsx Normal file
View File

@ -0,0 +1,73 @@
import React, { useMemo } from "react"
import { fileSelector } from "@dannadori/voice-changer-client-js"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
import { useGuiState } from "../001_GuiStateProvider"
export const ModelSelectRow = () => {
const appState = useAppState()
const guiState = useGuiState()
const onnxSelectRow = useMemo(() => {
const slot = guiState.modelSlotNum
const fileUploadSetting = appState.serverSetting.fileUploadSettings[slot]
if (!fileUploadSetting) {
return <></>
}
const onnxModelFilenameText = fileUploadSetting.onnxModel?.filename || fileUploadSetting.onnxModel?.file?.name || ""
const pyTorchFilenameText = fileUploadSetting.pyTorchModel?.filename || fileUploadSetting.pyTorchModel?.file?.name || ""
const modelFilenameText = onnxModelFilenameText + pyTorchFilenameText
const onModelFileLoadClicked = async () => {
const file = await fileSelector("")
if (file.name.endsWith(".onnx") == false && file.name.endsWith(".pth") == false) {
alert("モデルファイルの拡張子は.onnxか.pthである必要があります。(Extension of the model file should be .onnx or .pth.)")
return
}
if (file.name.endsWith(".onnx") == true) {
appState.serverSetting.setFileUploadSetting(slot, {
...appState.serverSetting.fileUploadSettings[slot],
onnxModel: {
file: file
},
pyTorchModel: null
})
return
}
if (file.name.endsWith(".pth") == true) {
appState.serverSetting.setFileUploadSetting(slot, {
...appState.serverSetting.fileUploadSettings[slot],
pyTorchModel: {
file: file
},
onnxModel: null
})
return
}
}
const onModelFileClearClicked = () => {
appState.serverSetting.setFileUploadSetting(slot, {
...appState.serverSetting.fileUploadSettings[slot],
onnxModel: null,
pyTorchModel: null
})
}
return (
<div className="body-row split-3-3-4 left-padding-1 guided">
<div className="body-item-title left-padding-2">Model(.onnx or .pth)</div>
<div className="body-item-text">
<div>{modelFilenameText}</div>
</div>
<div className="body-button-container">
<div className="body-button" onClick={onModelFileLoadClicked}>select</div>
<div className="body-button left-margin-1" onClick={onModelFileClearClicked}>clear</div>
</div>
</div>
)
}, [appState.serverSetting.fileUploadSettings, appState.serverSetting.setFileUploadSetting, guiState.modelSlotNum])
return onnxSelectRow
}

10
client/demo/src/components/demo/components/301-2_ONNXSelectRow.tsx
View File

@ -3,13 +3,21 @@ import { fileSelector } from "@dannadori/voice-changer-client-js"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
import { useGuiState } from "../001_GuiStateProvider"
export const ONNXSelectRow = () => {
type ONNXSelectRowProps = {
onlyWhenSelected: boolean
}
export const ONNXSelectRow = (props: ONNXSelectRowProps) => {
const appState = useAppState()
const guiState = useGuiState()
const onnxSelectRow = useMemo(() => {
const slot = guiState.modelSlotNum
if (props.onlyWhenSelected && appState.serverSetting.fileUploadSettings[slot]?.framework != "ONNX") {
return <></>
}
const onnxModelFilenameText = appState.serverSetting.fileUploadSettings[slot]?.onnxModel?.filename || appState.serverSetting.fileUploadSettings[slot]?.onnxModel?.file?.name || ""
const onOnnxFileLoadClicked = async () => {
const file = await fileSelector("")

13
client/demo/src/components/demo/components/301-3_PyTorchSelectRow.tsx
View File

@ -3,15 +3,24 @@ import { fileSelector } from "@dannadori/voice-changer-client-js"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
import { useGuiState } from "../001_GuiStateProvider"
export type PyTorchSelectRow = {
export type PyTorchSelectRowProps = {
onlyWhenSelected: boolean
}
export const PyTorchSelectRow = (_props: PyTorchSelectRow) => {
export const PyTorchSelectRow = (props: PyTorchSelectRowProps) => {
const appState = useAppState()
const guiState = useGuiState()
const pyTorchSelectRow = useMemo(() => {
if (guiState.showPyTorchModelUpload == false) {
return <></>
}
const slot = guiState.modelSlotNum
if (props.onlyWhenSelected && appState.serverSetting.fileUploadSettings[slot]?.framework != "PyTorch") {
return <></>
}
const pyTorchFilenameText = appState.serverSetting.fileUploadSettings[slot]?.pyTorchModel?.filename || appState.serverSetting.fileUploadSettings[slot]?.pyTorchModel?.file?.name || ""
const onPyTorchFileLoadClicked = async () => {
const file = await fileSelector("")

10
client/demo/src/components/demo/components/301-8_HalfPrescisionRow.tsx
View File

@ -9,6 +9,11 @@ export const HalfPrecisionRow = () => {
const halfPrecisionSelectRow = useMemo(() => {
const slot = guiState.modelSlotNum
const fileUploadSetting = appState.serverSetting.fileUploadSettings[slot]
if (!fileUploadSetting) {
return <></>
}
const currentValue = fileUploadSetting ? fileUploadSetting.isHalf : true
const onHalfPrecisionChanged = () => {
appState.serverSetting.setFileUploadSetting(slot, {
...appState.serverSetting.fileUploadSettings[slot],
@ -16,16 +21,13 @@ export const HalfPrecisionRow = () => {
})
}
const currentVal = appState.serverSetting.fileUploadSettings[slot] ? appState.serverSetting.fileUploadSettings[slot].isHalf : true
return (
<div className="body-row split-3-3-4 left-padding-1 guided">
<div className="body-item-title left-padding-2">-</div>
<div className="body-item-text">
<div></div>
<input type="checkbox" checked={currentValue} onChange={() => onHalfPrecisionChanged()} /> half-precision
</div>
<div className="body-button-container">
<input type="checkbox" checked={currentVal} onChange={() => onHalfPrecisionChanged()} /> half-precision
</div>
</div>
)

2
client/demo/src/components/demo/components/301-9_ModelUploadButtonRow.tsx
View File

@ -27,7 +27,7 @@ export const ModelUploadButtonRow = () => {
</div>
<div className="body-button-container">
<div className={uploadButtonClassName} onClick={uploadButtonAction}>{uploadButtonLabel}</div>
<div>{uploadedText}</div>
<div className="body-item-text-em" >{uploadedText}</div>
</div>
</div>

8
client/demo/src/components/demo/components/301-c_DefaultTuneRow.tsx
View File

@ -8,6 +8,10 @@ export const DefaultTuneRow = () => {
const defaultTuneRow = useMemo(() => {
const slot = guiState.modelSlotNum
const fileUploadSetting = appState.serverSetting.fileUploadSettings[slot]
if (!fileUploadSetting) {
return <></>
}
const currentValue = fileUploadSetting.defaultTune
const onDefaultTuneChanged = (val: number) => {
appState.serverSetting.setFileUploadSetting(slot, {
@ -20,10 +24,10 @@ export const DefaultTuneRow = () => {
<div className="body-row split-3-2-1-4 left-padding-1 guided">
<div className="body-item-title left-padding-2 ">Default Tune</div>
<div>
<input type="range" className="body-item-input-slider" min="-50" max="50" step="1" value={fileUploadSetting?.defaultTune || 0} onChange={(e) => {
<input type="range" className="body-item-input-slider" min="-50" max="50" step="1" value={currentValue} onChange={(e) => {
onDefaultTuneChanged(Number(e.target.value))
}}></input>
<span className="body-item-input-slider-val">{fileUploadSetting?.defaultTune || 0}</span>
<span className="body-item-input-slider-val">{currentValue}</span>
</div>
<div>
</div>

42
client/demo/src/components/demo/components/301-d_FrameworkSelector.tsx Normal file
View File

@ -0,0 +1,42 @@
import { Framework } from "@dannadori/voice-changer-client-js"
import React, { useMemo } from "react"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
import { useGuiState } from "../001_GuiStateProvider"
export const FrameworkSelectorRow = () => {
const appState = useAppState()
const guiState = useGuiState()
const frameworkSelectorRow = useMemo(() => {
const slot = guiState.modelSlotNum
const fileUploadSetting = appState.serverSetting.fileUploadSettings[slot]
const currentValue = fileUploadSetting?.framework || Framework.PyTorch
const onFrameworkChanged = (val: Framework) => {
appState.serverSetting.setFileUploadSetting(slot, {
...appState.serverSetting.fileUploadSettings[slot],
framework: val
})
}
return (
<div className="body-row split-3-7 left-padding-1 guided">
<div className="body-item-title left-padding-2">Framework</div>
<div className="body-input-container">
<div className="body-select-container">
<select className="body-select" value={currentValue} onChange={(e) => {
onFrameworkChanged(e.target.value as Framework)
}}>
{
Object.values(Framework).map(x => {
return <option key={x} value={x}>{x}</option>
})
}
</select>
</div>
</div>
</div>
)
}, [appState.serverSetting.fileUploadSettings, appState.serverSetting.setFileUploadSetting, guiState.modelSlotNum])
return frameworkSelectorRow
}

29
client/demo/src/components/demo/components/301_ModelUploaderRow.tsx
View File

@ -1,6 +1,7 @@
import React, { useMemo, useEffect } from "react"
import { useGuiState } from "../001_GuiStateProvider"
import { ConfigSelectRow } from "./301-1_ConfigSelectRow"
import { ModelSelectRow } from "./301-2-5_ModelSelectRow copy"
import { ONNXSelectRow } from "./301-2_ONNXSelectRow"
import { PyTorchSelectRow } from "./301-3_PyTorchSelectRow"
import { CorrespondenceSelectRow } from "./301-4_CorrespondenceSelectRow"
@ -11,9 +12,11 @@ import { HalfPrecisionRow } from "./301-8_HalfPrescisionRow"
import { ModelUploadButtonRow } from "./301-9_ModelUploadButtonRow"
import { ModelSlotRow } from "./301-a_ModelSlotRow"
import { DefaultTuneRow } from "./301-c_DefaultTuneRow"
import { FrameworkSelectorRow } from "./301-d_FrameworkSelector"
export type ModelUploaderRowProps = {
showModelSlot: boolean
showFrameworkSelector: boolean
showConfig: boolean
showOnnx: boolean
showPyTorch: boolean
@ -26,7 +29,10 @@ export type ModelUploaderRowProps = {
showDescription: boolean
showDefaultTune: boolean
showPyTorchEnableCheckBox: boolean
defaultEnablePyTorch: boolean
onlySelectedFramework: boolean
oneModelFileType: boolean
showOnnxExportButton: boolean
}
@ -38,6 +44,15 @@ export const ModelUploaderRow = (props: ModelUploaderRowProps) => {
}, [])
const modelUploaderRow = useMemo(() => {
const pytorchEnableCheckBox = props.showPyTorchEnableCheckBox ?
<div>
<input type="checkbox" checked={guiState.showPyTorchModelUpload} onChange={(e) => {
guiState.setShowPyTorchModelUpload(e.target.checked)
}} /> enable PyTorch
</div>
:
<></>
return (
<>
<div className="body-row split-3-3-4 left-padding-1 guided">
@ -46,17 +61,17 @@ export const ModelUploaderRow = (props: ModelUploaderRowProps) => {
<div></div>
</div>
<div className="body-item-text">
<div>
<input type="checkbox" checked={guiState.showPyTorchModelUpload} onChange={(e) => {
guiState.setShowPyTorchModelUpload(e.target.checked)
}} /> enable PyTorch
</div>
{pytorchEnableCheckBox}
</div>
</div>
{props.showModelSlot ? <ModelSlotRow /> : <></>}
{props.showFrameworkSelector ? <FrameworkSelectorRow /> : <></>}
{props.showConfig ? <ConfigSelectRow /> : <></>}
{props.showOnnx ? <ONNXSelectRow /> : <></>}
{props.showPyTorch && guiState.showPyTorchModelUpload ? <PyTorchSelectRow /> : <></>}
{props.oneModelFileType ? <ModelSelectRow /> : <></>}
{props.showOnnx ? <ONNXSelectRow onlyWhenSelected={props.onlySelectedFramework} /> : <></>}
{props.showPyTorch ? <PyTorchSelectRow onlyWhenSelected={props.onlySelectedFramework} /> : <></>}
{props.showCorrespondence ? <CorrespondenceSelectRow /> : <></>}
{props.showPyTorchCluster ? <PyTorchClusterSelectRow /> : <></>}
{props.showFeature ? <FeatureSelectRow /> : <></>}

2
client/demo/src/components/demo/components/303_ModelSamplingRateRow.tsx
View File

@ -1,5 +1,5 @@
import React, { useMemo } from "react"
import { fileSelector, ModelSamplingRate } from "@dannadori/voice-changer-client-js"
import { ModelSamplingRate } from "@dannadori/voice-changer-client-js"
import { useAppState } from "../../../001_provider/001_AppStateProvider"
export type ModelSamplingRateRowProps = {

8
client/demo/src/css/App.css
View File

@ -535,6 +535,14 @@ body {
color: rgb(30, 30, 30);
font-size: 0.7rem;
}
.body-item-text-em {
color: rgb(250, 30, 30);
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
font-weight: 700;
}
.body-input-container {
display: flex;
}

5
client/lib/src/hooks/useServerSetting.ts
View File

@ -1,5 +1,5 @@
import { useState, useMemo, useEffect } from "react"
import { VoiceChangerServerSetting, ServerInfo, ServerSettingKey, INDEXEDDB_KEY_SERVER, INDEXEDDB_KEY_MODEL_DATA, ClientType, DefaultServerSetting_MMVCv13, DefaultServerSetting_MMVCv15, DefaultServerSetting_so_vits_svc_40v2, DefaultServerSetting_so_vits_svc_40, DefaultServerSetting_so_vits_svc_40_c, DefaultServerSetting_RVC, OnnxExporterInfo, DefaultServerSetting_DDSP_SVC, MAX_MODEL_SLOT_NUM } from "../const"
import { VoiceChangerServerSetting, ServerInfo, ServerSettingKey, INDEXEDDB_KEY_SERVER, INDEXEDDB_KEY_MODEL_DATA, ClientType, DefaultServerSetting_MMVCv13, DefaultServerSetting_MMVCv15, DefaultServerSetting_so_vits_svc_40v2, DefaultServerSetting_so_vits_svc_40, DefaultServerSetting_so_vits_svc_40_c, DefaultServerSetting_RVC, OnnxExporterInfo, DefaultServerSetting_DDSP_SVC, MAX_MODEL_SLOT_NUM, Framework } from "../const"
import { VoiceChangerClient } from "../VoiceChangerClient"
import { useIndexedDB } from "./useIndexedDB"
@ -22,6 +22,7 @@ export type FileUploadSetting = {
isHalf: boolean
uploaded: boolean
defaultTune: number
framework: Framework
params: string
}
@ -38,6 +39,7 @@ const InitialFileUploadSetting: FileUploadSetting = {
isHalf: true,
uploaded: false,
defaultTune: 0,
framework: Framework.PyTorch,
params: "{}"
}
@ -322,6 +324,7 @@ export const useServerSetting = (props: UseServerSettingProps): ServerSettingSta
isHalf: fileUploadSetting.isHalf, // キャッシュとしては不使用。guiで上書きされる。
uploaded: false, // キャッシュから読み込まれるときには、まだuploadされていないから。
defaultTune: fileUploadSetting.defaultTune,
framework: fileUploadSetting.framework,
params: fileUploadSetting.params
}
setItem(`${INDEXEDDB_KEY_MODEL_DATA}_${slot}`, saveData)

81
server/voice_changer/RVC/RVC.py
View File

@ -31,8 +31,9 @@ import pyworld as pw
from voice_changer.RVC.custom_vc_infer_pipeline import VC
from infer_pack.models import SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFsid_nono
from .models import SynthesizerTrnMsNSFsid as SynthesizerTrnMs768NSFsid
# from .const import RVC_MODEL_TYPE_NORMAL, RVC_MODEL_TYPE_PITCHLESS, RVC_MODEL_TYPE_WEBUI_256_NORMAL, RVC_MODEL_TYPE_WEBUI_768_NORMAL, RVC_MODEL_TYPE_WEBUI_256_PITCHLESS, RVC_MODEL_TYPE_WEBUI_768_PITCHLESS, RVC_MODEL_TYPE_UNKNOWN
from .models import SynthesizerTrnMsNSFsid as SynthesizerTrnMsNSFsid_webui
from .models import SynthesizerTrnMsNSFsidNono as SynthesizerTrnMsNSFsidNono_webui
from .const import RVC_MODEL_TYPE_RVC, RVC_MODEL_TYPE_WEBUI
from fairseq import checkpoint_utils
providers = ['OpenVINOExecutionProvider', "CUDAExecutionProvider", "DmlExecutionProvider", "CPUExecutionProvider"]
@ -101,14 +102,10 @@ class RVC:
self.feature_file = None
self.index_file = None
# self.net_g2 = None
# self.onnx_session2 = None
# self.feature_file2 = None
# self.index_file2 = None
self.gpu_num = torch.cuda.device_count()
self.prevVol = 0
self.params = params
self.mps_enabled: bool = getattr(torch.backends, "mps", None) is not None and torch.backends.mps.is_available()
self.currentSlot = -1
print("RVC initialization: ", params)
@ -142,11 +139,10 @@ class RVC:
except Exception as e:
print("EXCEPTION during loading hubert/contentvec model", e)
# self.switchModel(self.slot)
if self.initialLoad:
self.prepareModel(self.tmp_slot)
self.slot = self.tmp_slot
self.currentSlot = self.slot
self.settings.modelSlotIndex = self.tmp_slot
self.currentSlot = self.settings.modelSlotIndex
self.switchModel()
self.initialLoad = False
@ -158,6 +154,7 @@ class RVC:
onnxModelFile = self.settings.modelSlots[slot].onnxModelFile
# PyTorchモデル生成
if pyTorchModelFile != None and pyTorchModelFile != "":
print("[Voice Changer] Loading Pytorch Model...")
cpt = torch.load(pyTorchModelFile, map_location="cpu")
'''
(1) オリジナルとrvc-webuiのモデル判定 ⇒ config全体の形状
@ -176,7 +173,6 @@ class RVC:
# print("config shape:1::::", cpt["config"], cpt["f0"])
# print("config shape:2::::", (cpt).keys)
config_len = len(cpt["config"])
upsamplingRateDims = len(cpt["config"][12])
if config_len == 18:
self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_RVC
self.settings.modelSlots[slot].embChannels = 256
@ -188,43 +184,19 @@ class RVC:
self.settings.modelSamplingRate = cpt["config"][-1]
# if config_len == 18 and cpt["f0"] == 0:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_PITCHLESS")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_PITCHLESS
# elif config_len == 18 and cpt["f0"] == 1:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_NORMAL")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_NORMAL
# elif config_len == 19:
# print("PARAMS:::::::::", cpt["params"])
# embedding = cpt["config"][17]
# if embedding == 256 and cpt["f0"] == 0:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_WEBUI_256_PITCHLESS")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_WEBUI_256_PITCHLESS
# elif embedding == 256 and cpt["f0"] == 1:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_WEBUI_256_NORMAL")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_WEBUI_256_NORMAL
# elif embedding == 768 and cpt["f0"] == 0:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_WEBUI_768_PITCHLESS")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_WEBUI_768_PITCHLESS
# else:
# print("[Voice Changer] RVC Model Type: RVC_MODEL_TYPE_WEBUI_768_NORMAL")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_WEBUI_768_NORMAL
# else:
# print("[Voice Changer] RVC Model Type: UNKNOWN")
# self.settings.modelSlots[slot].modelType = RVC_MODEL_TYPE_UNKNOWN
if self.settings.modelSlots[slot].modelType == RVC_MODEL_TYPE_RVC and self.settings.modelSlots[slot].f0 == True:
net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=self.is_half)
elif self.settings.modelSlots[slot].modelType == RVC_MODEL_TYPE_RVC and self.settings.modelSlots[slot].f0 == False:
net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
elif self.settings.modelSlots[slot].modelType == RVC_MODEL_TYPE_WEBUI and self.settings.modelSlots[slot].f0 == True:
net_g = SynthesizerTrnMs768NSFsid(**cpt["params"], is_half=self.is_half)
net_g = SynthesizerTrnMsNSFsid_webui(**cpt["params"], is_half=self.is_half)
elif self.settings.modelSlots[slot].modelType == RVC_MODEL_TYPE_WEBUI and self.settings.modelSlots[slot].f0 == False:
######################
# TBD
######################
print("webui non-f0 is not supported yet")
net_g = SynthesizerTrnMs768NSFsid(**cpt["params"], is_half=self.is_half)
net_g = SynthesizerTrnMsNSFsidNono_webui(**cpt["params"], is_half=self.is_half)
else:
print("unknwon")
@ -234,10 +206,12 @@ class RVC:
net_g = net_g.half()
self.next_net_g = net_g
else:
print("[Voice Changer] Skip Loading Pytorch Model...")
self.next_net_g = None
# ONNXモデル生成
if onnxModelFile != None and onnxModelFile != "":
print("[Voice Changer] Loading ONNX Model...")
self.next_onnx_session = ModelWrapper(onnxModelFile)
self.settings.modelSlots[slot].samplingRateOnnx = self.next_onnx_session.getSamplingRate()
self.settings.modelSlots[slot].f0Onnx = self.next_onnx_session.getF0()
@ -249,15 +223,17 @@ class RVC:
self.settings.modelSlots[slot].f0 = self.settings.modelSlots[slot].f0Onnx
else:
print("[Voice Changer] Skip Loading ONNX Model...")
self.next_onnx_session = None
self.next_feature_file = self.settings.modelSlots[slot].featureFile
self.next_index_file = self.settings.modelSlots[slot].indexFile
self.next_trans = self.settings.modelSlots[slot].defaultTrans
print("[Voice Changer] Prepare done.",)
return self.get_info()
def switchModel(self):
print("[Voice Changer] Switching model..",)
# del self.net_g
# del self.onnx_session
self.net_g = self.next_net_g
@ -267,6 +243,7 @@ class RVC:
self.settings.tran = self.next_trans
self.next_net_g = None
self.next_onnx_session = None
print("[Voice Changer] Switching model..done",)
def update_settings(self, key: str, val: any):
if key == "onnxExecutionProvider" and self.onnx_session != None:
@ -285,7 +262,6 @@ class RVC:
print("Onnx is not enabled. Please load model.")
return False
elif key in self.settings.intData:
setattr(self.settings, key, int(val))
if key == "gpu" and val >= 0 and val < self.gpu_num and self.onnx_session != None:
providers = self.onnx_session.get_providers()
print("Providers:", providers)
@ -296,7 +272,7 @@ class RVC:
# self.switchModel(int(val))
self.tmp_slot = int(val)
self.prepareModel(self.tmp_slot)
self.slot = self.tmp_slot
setattr(self.settings, key, int(val))
elif key in self.settings.floatData:
setattr(self.settings, key, float(val))
elif key in self.settings.strData:
@ -389,7 +365,7 @@ class RVC:
def _pyTorch_inference(self, data):
if hasattr(self, "net_g") == False or self.net_g == None:
print("[Voice Changer] No pyTorch session.")
print("[Voice Changer] No pyTorch session.", hasattr(self, "net_g"), self.net_g)
raise NoModeLoadedException("pytorch")
if self.settings.gpu < 0 or (self.gpu_num == 0 and self.mps_enabled == False):
@ -437,12 +413,13 @@ class RVC:
return result
def inference(self, data):
if hasattr(self, "slot") == False:
print("[Voice Changer] No model uploaded.")
raise NoModeLoadedException("model_common")
# if self.settings.modelSlotIndex < -1:
# print("[Voice Changer] No model uploaded.")
# raise NoModeLoadedException("model_common")
if self.currentSlot != self.slot:
self.currentSlot = self.slot
if self.currentSlot != self.settings.modelSlotIndex:
print(f"Switch model {self.currentSlot} -> {self.settings.modelSlotIndex}")
self.currentSlot = self.settings.modelSlotIndex
self.switchModel()
if self.settings.framework == "ONNX":
@ -474,7 +451,7 @@ class RVC:
print("[Voice Changer] export2onnx, No pyTorch session.")
return {"status": "ng", "path": f""}
pyTorchModelFile = self.settings.modelSlots[self.slot].pyTorchModelFile # inference前にexportできるようにcurrentSlotではなくslot
pyTorchModelFile = self.settings.modelSlots[self.settings.modelSlotIndex].pyTorchModelFile # inference前にexportできるようにcurrentSlotではなくslot
if pyTorchModelFile == None:
print("[Voice Changer] export2onnx, No pyTorch filepath.")
@ -488,10 +465,10 @@ class RVC:
metadata = {
"application": "VC_CLIENT",
"version": "1",
"ModelType": self.settings.modelSlots[self.slot].modelType,
"samplingRate": self.settings.modelSlots[self.slot].samplingRate,
"f0": self.settings.modelSlots[self.slot].f0,
"embChannels": self.settings.modelSlots[self.slot].embChannels,
"ModelType": self.settings.modelSlots[self.settings.modelSlotIndex].modelType,
"samplingRate": self.settings.modelSlots[self.settings.modelSlotIndex].samplingRate,
"f0": self.settings.modelSlots[self.settings.modelSlotIndex].f0,
"embChannels": self.settings.modelSlots[self.settings.modelSlotIndex].embChannels,
}
if torch.cuda.device_count() > 0:

108
server/voice_changer/RVC/models.py
View File

@ -3,7 +3,7 @@ import torch
from torch import nn
import numpy as np
from infer_pack.models import sr2sr, GeneratorNSF, PosteriorEncoder, ResidualCouplingBlock
from infer_pack.models import sr2sr, GeneratorNSF, PosteriorEncoder, ResidualCouplingBlock, Generator
from infer_pack import commons, attentions
@ -111,7 +111,6 @@ class SynthesizerTrnMsNSFsid(nn.Module):
n_layers,
kernel_size,
p_dropout,
# f0=False,
)
self.dec = GeneratorNSF(
inter_channels,
@ -169,3 +168,108 @@ class SynthesizerTrnMsNSFsid(nn.Module):
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
class SynthesizerTrnMsNSFsidNono(nn.Module):
def __init__(
self,
spec_channels,
segment_size,
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
spk_embed_dim,
gin_channels,
emb_channels,
sr=None,
**kwargs
):
super().__init__()
self.spec_channels = spec_channels
self.inter_channels = inter_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
self.resblock = resblock
self.resblock_kernel_sizes = resblock_kernel_sizes
self.resblock_dilation_sizes = resblock_dilation_sizes
self.upsample_rates = upsample_rates
self.upsample_initial_channel = upsample_initial_channel
self.upsample_kernel_sizes = upsample_kernel_sizes
self.segment_size = segment_size
self.gin_channels = gin_channels
self.emb_channels = emb_channels
# self.hop_length = hop_length#
self.spk_embed_dim = spk_embed_dim
self.enc_p = TextEncoder(
inter_channels,
hidden_channels,
filter_channels,
emb_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
f0=False,
)
self.dec = Generator(
inter_channels,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=gin_channels,
)
self.enc_q = PosteriorEncoder(
spec_channels,
inter_channels,
hidden_channels,
5,
1,
16,
gin_channels=gin_channels,
)
self.flow = ResidualCouplingBlock(
inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
)
self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
print("gin_channels:", gin_channels, "self.spk_embed_dim:", self.spk_embed_dim)
def remove_weight_norm(self):
self.dec.remove_weight_norm()
self.flow.remove_weight_norm()
self.enc_q.remove_weight_norm()
def forward(self, phone, phone_lengths, y, y_lengths, ds): # 这里ds是id，[bs,1]
g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
z_p = self.flow(z, y_mask, g=g)
z_slice, ids_slice = commons.rand_slice_segments(
z, y_lengths, self.segment_size
)
o = self.dec(z_slice, g=g)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, sid, max_len=None):
g = self.emb_g(sid).unsqueeze(-1)
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], g=g)
return o, x_mask, (z, z_p, m_p, logs_p)