Code-Inc/supertonic
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add ios and web

Browse Source
This commit is contained in:
ANLGBOY
2025-11-23 15:54:59 +09:00
parent 5d2e263401
commit 375fad69c2
17 changed files with 1986 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ios/ExampleiOSApp/App.swift Normal file
View File

@@ -0,0 +1,10 @@
import SwiftUI
@main
struct ExampleiOSApp: App {
var body: some Scene {
WindowGroup {
ContentView()
}
}
}

30
ios/ExampleiOSApp/AudioPlayer.swift Normal file
View File

@@ -0,0 +1,30 @@
import Foundation
import AVFoundation
final class AudioPlayer: NSObject, AVAudioPlayerDelegate {
private var player: AVAudioPlayer?
private var onFinish: (() -> Void)?
func play(url: URL, onFinish: (() -> Void)? = nil) {
self.onFinish = onFinish
do {
let data = try Data(contentsOf: url)
let player = try AVAudioPlayer(data: data)
player.delegate = self
player.prepareToPlay()
player.play()
self.player = player
} catch {
print("Audio play error: \(error)")
}
}
func stop() {
player?.stop()
player = nil
}
func audioPlayerDidFinishPlaying(_ player: AVAudioPlayer, successfully flag: Bool) {
onFinish?()
}
}

98
ios/ExampleiOSApp/ContentView.swift Normal file
View File

@@ -0,0 +1,98 @@
import SwiftUI
struct ContentView: View {
@StateObject private var vm = TTSViewModel()
var body: some View {
ZStack {
LinearGradient(gradient: Gradient(colors: [Color(.systemBackground), Color(.secondarySystemBackground)]), startPoint: .topLeading, endPoint: .bottomTrailing)
.ignoresSafeArea()
VStack(spacing: 20) {
Spacer()
VStack(spacing: 12) {
Text("SupertonicTTS iOS Demo")
.font(.title2.weight(.semibold))
.foregroundColor(.primary)
ZStack(alignment: .topLeading) {
if vm.text.isEmpty {
Text("Type text to synthesize")
.foregroundColor(.secondary)
.padding(.horizontal, 14)
.padding(.vertical, 12)
}
TextEditor(text: $vm.text)
.frame(minHeight: 120, maxHeight: 180)
.padding(8)
.background(Color(.secondarySystemBackground))
.cornerRadius(12)
.overlay(
RoundedRectangle(cornerRadius: 12)
.stroke(Color.secondary.opacity(0.3), lineWidth: 1)
)
}
.padding(.horizontal)
HStack(spacing: 12) {
Text("NFE")
.font(.subheadline)
.foregroundColor(.secondary)
Slider(value: $vm.nfe, in: 2...15, step: 1)
Text("\(Int(vm.nfe))")
.font(.subheadline.monospacedDigit())
.frame(width: 36)
}
.padding(.horizontal)
Picker("Voice", selection: $vm.voice) {
Text("M").tag(TTSService.Voice.male)
Text("F").tag(TTSService.Voice.female)
}
.pickerStyle(SegmentedPickerStyle())
.padding(.horizontal)
}
HStack(spacing: 16) {
Button(action: { vm.generate() }) {
Label(vm.isGenerating ? "Generating..." : "Generate", systemImage: vm.isGenerating ? "hourglass" : "wand.and.stars"
)
.labelStyle(.titleAndIcon)
}
.buttonStyle(.borderedProminent)
.tint(.accentColor)
.disabled(vm.isGenerating)
Button(action: { vm.togglePlay() }) {
Label(vm.isPlaying ? "Stop" : "Play", systemImage: vm.isPlaying ? "stop.fill" : "play.fill")
}
.buttonStyle(.bordered)
.disabled(vm.audioURL == nil)
}
if let rtf = vm.rtfText {
Text(rtf)
.font(.footnote.monospacedDigit())
.foregroundColor(.secondary)
.padding(.top, 2)
}
if let error = vm.errorMessage {
Text(error)
.foregroundColor(.red)
.font(.footnote)
.multilineTextAlignment(.center)
.padding(.horizontal)
}
Spacer()
}
}
.onAppear { vm.startup() }
}
}
#Preview {
ContentView()
}

29
ios/ExampleiOSApp/Info.plist Normal file
View File

@@ -0,0 +1,29 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDevelopmentRegion</key>
<string>en</string>
<key>CFBundleExecutable</key>
<string>$(EXECUTABLE_NAME)</string>
<key>CFBundleIdentifier</key>
<string>$(PRODUCT_BUNDLE_IDENTIFIER)</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>ExampleiOSApp</string>
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>1</string>
<key>UILaunchScreen</key>
<dict/>
<key>UIApplicationSceneManifest</key>
<dict>
<key>UIApplicationSupportsMultipleScenes</key>
<false/>
</dict>
</dict>
</plist>

140
ios/ExampleiOSApp/TTSService.swift Normal file
View File

@@ -0,0 +1,140 @@
import Foundation
import OnnxRuntimeBindings
final class TTSService {
enum Voice { case male, female }
struct Settings {
var nTest: Int = 1
}
struct SynthesisResult {
let url: URL
let elapsedSeconds: Double
let audioSeconds: Double
var rtf: Double { elapsedSeconds / max(audioSeconds, 1e-6) }
}
private let env: ORTEnv
private let textToSpeech: TextToSpeech
private let bundleOnnxDir: String
private let sampleRate: Int
// Cached style per voice (precomputed at startup or on first use)
private var cachedStyle: [Voice: Style] = [:]
init() throws {
bundleOnnxDir = try Self.locateOnnxDirInBundle()
env = try ORTEnv(loggingLevel: .warning)
textToSpeech = try loadTextToSpeech(bundleOnnxDir, false, env)
sampleRate = textToSpeech.sampleRate
}
// Public warmup: precompute styles and run a quick generation to warm models
func warmup(nfe: Int = 1) async {
do { try precomputeStyle(for: .male) } catch { print("Warmup style (M) error: \(error)") }
do { try precomputeStyle(for: .female) } catch { print("Warmup style (F) error: \(error)") }
// Run a tiny synthesis to JIT/warm up kernels; discard file
do {
let res = try await synthesize(text: "Warm up", nfe: max(1, nfe), voice: .male)
try? FileManager.default.removeItem(at: res.url)
} catch {
print("Warmup synth error: \(error)")
}
}
func synthesize(text: String, nfe: Int, voice: Voice, settings: Settings = Settings()) async throws -> SynthesisResult {
let tic = Date()
// 1) Get or compute style for the selected voice
let style = try getStyle(voice: voice)
// 2) Synthesize via packed TextToSpeech component
let (wav, duration) = try textToSpeech.call([text], style, nfe)
let audioSeconds = Double(duration[0])
let wavLenSample = min(Int(Double(sampleRate) * audioSeconds), wav.count)
let wavOut = Array(wav[0..<wavLenSample])
let tmpURL = FileManager.default.temporaryDirectory.appendingPathComponent("supertonic_tts_\(UUID().uuidString).wav")
try writeWavFile(tmpURL.path, wavOut, sampleRate)
let elapsed = Date().timeIntervalSince(tic)
return SynthesisResult(url: tmpURL, elapsedSeconds: elapsed, audioSeconds: audioSeconds)
}
// MARK: - Style helpers
private func precomputeStyle(for voice: Voice) throws {
if cachedStyle[voice] != nil { return }
let styleURL = try Self.locateVoiceStyleURL(voice: voice)
let style = try loadVoiceStyle([styleURL.path], verbose: false)
cachedStyle[voice] = style
}
private func getStyle(voice: Voice) throws -> Style {
if let style = cachedStyle[voice] { return style }
try precomputeStyle(for: voice)
return cachedStyle[voice]!
}
// MARK: - Resource location helpers
private static func locateOnnxDirInBundle() throws -> String {
let bundle = Bundle.main
let fm = FileManager.default
func dirHasRequiredFiles(_ dir: URL) -> Bool {
let required = [
"tts.json",
"duration_predictor.onnx",
"text_encoder.onnx",
"vector_estimator.onnx",
"vocoder.onnx"
]
return required.allSatisfy { fm.fileExists(atPath: dir.appendingPathComponent($0).path) }
}
var candidates: [URL] = []
if let dir = bundle.resourceURL?.appendingPathComponent("onnx", isDirectory: true) { candidates.append(dir) }
if let dir = bundle.resourceURL?.appendingPathComponent("assets/onnx", isDirectory: true) { candidates.append(dir) }
if let url = bundle.url(forResource: "tts", withExtension: "json", subdirectory: "onnx") { candidates.append(url.deletingLastPathComponent()) }
if let url = bundle.url(forResource: "tts", withExtension: "json", subdirectory: "assets/onnx") { candidates.append(url.deletingLastPathComponent()) }
if let url = bundle.url(forResource: "tts", withExtension: "json", subdirectory: nil) { candidates.append(url.deletingLastPathComponent()) }
if let root = bundle.resourceURL { candidates.append(root) }
for dir in candidates {
if dirHasRequiredFiles(dir) { return dir.path }
}
throw NSError(
domain: "TTS",
code: -100,
userInfo: [NSLocalizedDescriptionKey: "Could not find the onnx directory in the bundle. Please make sure the onnx folder (as a folder reference) is included in Copy Bundle Resources in Xcode."]
)
}
private static func locateVoiceStyleURL(voice: Voice) throws -> URL {
// Prefer M1/F1 defaults; search common subdirectories
let fileName = (voice == .male) ? "M1" : "F1"
let bundle = Bundle.main
let candidates: [URL?] = [
bundle.url(forResource: fileName, withExtension: "json", subdirectory: "voice_styles"),
bundle.url(forResource: fileName, withExtension: "json", subdirectory: "assets/voice_styles"),
bundle.url(forResource: fileName, withExtension: "json", subdirectory: nil)
]
for url in candidates {
if let url = url { return url }
}
// Fallback: scan folders if needed
if let folder1 = bundle.resourceURL?.appendingPathComponent("voice_styles", isDirectory: true) {
let file = folder1.appendingPathComponent("\(fileName).json")
if FileManager.default.fileExists(atPath: file.path) { return file }
}
if let folder2 = bundle.resourceURL?.appendingPathComponent("assets/voice_styles", isDirectory: true) {
let file = folder2.appendingPathComponent("\(fileName).json")
if FileManager.default.fileExists(atPath: file.path) { return file }
}
throw NSError(
domain: "TTS",
code: -102,
userInfo: [NSLocalizedDescriptionKey: "Could not find the voice style JSON (\(fileName).json) in the bundle. Ensure voice_styles folder is included in Copy Bundle Resources."]
)
}
}

76
ios/ExampleiOSApp/TTSViewModel.swift Normal file
View File

@@ -0,0 +1,76 @@
import Foundation
import AVFoundation
@MainActor
final class TTSViewModel: ObservableObject {
@Published var text: String = "This morning, I took a walk in the park, and the sound of the birds and the breeze was so pleasant that I stopped for a long time just to listen."
@Published var nfe: Double = 5
@Published var voice: TTSService.Voice = .male
@Published var isGenerating: Bool = false
@Published var isPlaying: Bool = false
@Published var errorMessage: String?
@Published var audioURL: URL?
@Published var elapsedSeconds: Double?
@Published var audioSeconds: Double?
private var service: TTSService?
private var player = AudioPlayer()
var rtfText: String? {
guard let e = elapsedSeconds, let a = audioSeconds, a > 0 else { return nil }
let rtf = e / a
return String(format: "RTF %.2fx · %.2fs / %.2fs", rtf, e, a)
}
func startup() {
do {
service = try TTSService()
Task { await self.service?.warmup(nfe: 5) }
} catch {
errorMessage = "Failed to init TTS: \(error.localizedDescription)"
}
}
func generate() {
guard let service = service else { return }
isGenerating = true
errorMessage = nil
audioURL = nil
elapsedSeconds = nil
audioSeconds = nil
Task {
do {
let result = try await service.synthesize(text: text, nfe: Int(nfe), voice: voice)
await MainActor.run {
self.audioURL = result.url
self.elapsedSeconds = result.elapsedSeconds
self.audioSeconds = result.audioSeconds
self.isGenerating = false
}
self.play(url: result.url)
} catch {
await MainActor.run {
self.errorMessage = error.localizedDescription
self.isGenerating = false
}
}
}
}
func togglePlay() {
if isPlaying {
player.stop()
isPlaying = false
} else if let url = audioURL {
play(url: url)
}
}
private func play(url: URL) {
player.play(url: url) { [weak self] in
DispatchQueue.main.async { self?.isPlaying = false }
}
isPlaying = true
}
}

29
ios/ExampleiOSApp/project.yml Normal file
View File

@@ -0,0 +1,29 @@
name: ExampleiOSApp
options:
minimumXcodeGenVersion: 2.37.0
packages:
onnxruntime:
url: https://github.com/microsoft/onnxruntime-swift-package-manager.git
from: 1.16.0
targets:
ExampleiOSApp:
type: application
platform: iOS
deploymentTarget: "15.0"
sources:
- path: .
- path: ../../swift/Sources/Helper.swift <<- 여기
type: file
resources:
- path: onnx
type: folder
- path: audio
type: folder
settings:
base:
PRODUCT_BUNDLE_IDENTIFIER: com.supertonic.ExampleiOSApp
SWIFT_VERSION: 5.9
INFOPLIST_FILE: Info.plist
dependencies:
- package: onnxruntime
product: onnxruntime

59
ios/README.md Normal file
View File

@@ -0,0 +1,59 @@
# Supertonic iOS Example App
A minimal iOS demo that runs Supertonic (ONNX Runtime) on-device. The app shows:
- Multiline text input
- NFE (denoising steps) slider
- Voice toggle (M/F)
- Generate & Play buttons
- RTF display (Elapsed / Audio seconds)
All ONNX models/configs are reused from `Supertonic/assets/onnx`, and voice style JSON files from `Supertonic/assets/voice_styles`.
## Prerequisites
- macOS 13+, Xcode 15+
- Swift 5.9+
- iOS 15+ device (recommended)
- Homebrew, XcodeGen
Install tools (if needed):
```bash
brew install xcodegen
```
## Quick Start (zero-click in Xcode)
0) Prepare assets next to the iOS target (one-time)
```bash
cd ios/ExampleiOSApp
mkdir -p onnx voice_styles
rsync -a ../../assets/onnx/ onnx/
rsync -a ../../assets/voice_styles/ voice_styles/
```
1) Generate the Xcode project with XcodeGen
```bash
xcodegen generate
open ExampleiOSApp.xcodeproj
```
2) Open in Xcode and select your iPhone as the run destination
- Targets → ExampleiOSApp → Signing & Capabilities: Select your Team
- iOS Deployment Target: 15.0+
3) Build & Run on device
- Type text → adjust NFE/Voice → Tap Generate → Audio plays automatically
- An RTF line shows like: `RTF 0.30x · 3.04s / 10.11s`
## What's included (generated project)
- SwiftUI app files: `App.swift`, `ContentView.swift`, `TTSViewModel.swift`, `AudioPlayer.swift`
- Runtime wrapper: `TTSService.swift` (includes TTS inference logic)
- Resources (local, vendored in `ios/ExampleiOSApp/onnx` and `ios/ExampleiOSApp/voice_styles` after step 0)
These references are defined in `project.yml` and added to the app bundle by XcodeGen.
## App Controls
- **Text**: Multiline `TextEditor`
- **NFE**: Denoising steps (default 5)
- **Voice**: M1/M2/F1/F2 voice style selector (4 pre-extracted styles)
- **Generate**: Runs end-to-end synthesis
- **Play/Stop**: Controls playback of the last output
- **RTF**: Shows Elapsed / Audio seconds for quick performance intuition

4
web/.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
node_modules/
dist/
.DS_Store
*.log

106
web/README.md Normal file
View File

@@ -0,0 +1,106 @@
# Supertonic Web Example
This example demonstrates how to use Supertonic in a web browser using ONNX Runtime Web.
## 📰 Update News
**2025.11.23** - Enhanced text preprocessing with comprehensive normalization, emoji removal, symbol replacement, and punctuation handling for improved synthesis quality.
**2025.11.19** - Added speed control slider to adjust speech synthesis speed (default: 1.05, recommended range: 0.9-1.5).
**2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
## Features
- 🌐 Runs entirely in the browser (no server required for inference)
- 🚀 WebGPU support with automatic fallback to WebAssembly
- ⚡ Pre-extracted voice styles for instant generation
- 🎨 Modern, responsive UI
- 🎭 Multiple voice style presets (2 Male, 2 Female)
- 💾 Download generated audio as WAV files
- 📊 Detailed generation statistics (audio length, generation time)
- ⏱️ Real-time progress tracking
## Requirements
- Node.js (for development server)
- Modern web browser (Chrome, Edge, Firefox, Safari)
## Installation
1. Install dependencies:
```bash
npm install
```
## Running the Demo
Start the development server:
```bash
npm run dev
```
This will start a local development server (usually at http://localhost:3000) and open the demo in your browser.
## Usage
1. **Wait for Models to Load**: The app will automatically load models and the default voice style (M1)
2. **Select Voice Style**: Choose from available voice presets
- **Male 1 (M1)**: Default male voice
- **Male 2 (M2)**: Alternative male voice
- **Female 1 (F1)**: Default female voice
- **Female 2 (F2)**: Alternative female voice
3. **Enter Text**: Type or paste the text you want to convert to speech
4. **Adjust Settings** (optional):
- **Total Steps**: More steps = better quality but slower (default: 5)
5. **Generate Speech**: Click the "Generate Speech" button
6. **View Results**:
- See the full input text
- View audio length and generation time statistics
- Play the generated audio in the browser
- Download as WAV file
## Technical Details
### Browser Compatibility
This demo uses:
- **ONNX Runtime Web**: For running models in the browser
- **Web Audio API**: For playing generated audio
- **Vite**: For development and bundling
## Notes
- The ONNX models must be accessible at `assets/onnx/` relative to the web root
- Voice style JSON files must be accessible at `assets/voice_styles/` relative to the web root
- Pre-extracted voice styles enable instant generation without audio processing
- Four voice style presets are provided (M1, M2, F1, F2)
## Troubleshooting
### Models not loading
- Check browser console for errors
- Ensure `assets/onnx/` path is correct and models are accessible
- Check CORS settings if serving from a different domain
### WebGPU not available
- WebGPU is only available in recent Chrome/Edge browsers (version 113+)
- The app will automatically fall back to WebAssembly if WebGPU is not available
- Check the backend badge to see which execution provider is being used
### Out of memory errors
- Try shorter text inputs
- Reduce denoising steps
- Use a browser with more available memory
- Close other tabs to free up memory
### Audio quality issues
- Try different voice style presets
- Increase denoising steps for better quality
### Slow generation
- If using WebAssembly, try a browser that supports WebGPU
- Ensure no other heavy processes are running
- Consider using fewer denoising steps for faster (but lower quality) results

1
web/assets Symbolic link
View File

@@ -0,0 +1 @@
../assets

550
web/helper.js Normal file
View File

@@ -0,0 +1,550 @@
import * as ort from 'onnxruntime-web';
/**
* Unicode Text Processor
*/
export class UnicodeProcessor {
constructor(indexer) {
this.indexer = indexer;
}
call(textList) {
const processedTexts = textList.map(text => this.preprocessText(text));
const textIdsLengths = processedTexts.map(text => text.length);
const maxLen = Math.max(...textIdsLengths);
const textIds = processedTexts.map(text => {
const row = new Array(maxLen).fill(0);
for (let j = 0; j < text.length; j++) {
const codePoint = text.codePointAt(j);
row[j] = (codePoint < this.indexer.length) ? this.indexer[codePoint] : -1;
}
return row;
});
const textMask = this.getTextMask(textIdsLengths);
return { textIds, textMask };
}
preprocessText(text) {
// TODO: Need advanced normalizer for better performance
text = text.normalize('NFKD');
// FIXME: this should be fixed for non-English languages
// Remove emojis (wide Unicode range)
const emojiPattern = /[\u{1F600}-\u{1F64F}\u{1F300}-\u{1F5FF}\u{1F680}-\u{1F6FF}\u{1F700}-\u{1F77F}\u{1F780}-\u{1F7FF}\u{1F800}-\u{1F8FF}\u{1F900}-\u{1F9FF}\u{1FA00}-\u{1FA6F}\u{1FA70}-\u{1FAFF}\u{2600}-\u{26FF}\u{2700}-\u{27BF}\u{1F1E6}-\u{1F1FF}]+/gu;
text = text.replace(emojiPattern, '');
// Replace various dashes and symbols
const replacements = {
'–': '-',
'‑': '-',
'—': '-',
'¯': ' ',
'_': ' ',
'"': '"',
'"': '"',
'\u2018': "'", // left single quote
'\u2019': "'", // right single quote
'´': "'",
'`': "'",
'[': ' ',
']': ' ',
'|': ' ',
'/': ' ',
'#': ' ',
'→': ' ',
'←': ' ',
};
for (const [k, v] of Object.entries(replacements)) {
text = text.replaceAll(k, v);
}
// Remove combining diacritics // FIXME: this should be fixed for non-English languages
text = text.replace(/[\u0302\u0303\u0304\u0305\u0306\u0307\u0308\u030A\u030B\u030C\u0327\u0328\u0329\u032A\u032B\u032C\u032D\u032E\u032F]/g, '');
// Remove special symbols
text = text.replace(/[♥☆♡©\\]/g, '');
// Replace known expressions
const exprReplacements = {
'@': ' at ',
'e.g.,': 'for example, ',
'i.e.,': 'that is, ',
};
for (const [k, v] of Object.entries(exprReplacements)) {
text = text.replaceAll(k, v);
}
// Fix spacing around punctuation
text = text.replace(/ ,/g, ',');
text = text.replace(/ \./g, '.');
text = text.replace(/ !/g, '!');
text = text.replace(/ \?/g, '?');
text = text.replace(/ ;/g, ';');
text = text.replace(/ :/g, ':');
text = text.replace(/ '/g, "'");
// Remove duplicate quotes
while (text.includes('""')) {
text = text.replace('""', '"');
}
while (text.includes("''")) {
text = text.replace("''", "'");
}
while (text.includes('``')) {
text = text.replace('``', '`');
}
// Remove extra spaces
text = text.replace(/\s+/g, ' ').trim();
// If text doesn't end with punctuation, quotes, or closing brackets, add a period
if (!/[.!?;:,'\"')\]}…。」』】〉》›»]$/.test(text)) {
text += '.';
}
return text;
}
getTextMask(textIdsLengths) {
const maxLen = Math.max(...textIdsLengths);
return this.lengthToMask(textIdsLengths, maxLen);
}
lengthToMask(lengths, maxLen = null) {
const actualMaxLen = maxLen || Math.max(...lengths);
return lengths.map(len => {
const row = new Array(actualMaxLen).fill(0.0);
for (let j = 0; j < Math.min(len, actualMaxLen); j++) {
row[j] = 1.0;
}
return [row];
});
}
}
/**
* Style class to hold TTL and DP tensors
*/
export class Style {
constructor(ttlTensor, dpTensor) {
this.ttl = ttlTensor;
this.dp = dpTensor;
}
}
/**
* Text-to-Speech class
*/
export class TextToSpeech {
constructor(cfgs, textProcessor, dpOrt, textEncOrt, vectorEstOrt, vocoderOrt) {
this.cfgs = cfgs;
this.textProcessor = textProcessor;
this.dpOrt = dpOrt;
this.textEncOrt = textEncOrt;
this.vectorEstOrt = vectorEstOrt;
this.vocoderOrt = vocoderOrt;
this.sampleRate = cfgs.ae.sample_rate;
}
async _infer(textList, style, totalStep, speed = 1.05, progressCallback = null) {
const bsz = textList.length;
// Process text
const { textIds, textMask } = this.textProcessor.call(textList);
const textIdsFlat = new BigInt64Array(textIds.flat().map(x => BigInt(x)));
const textIdsShape = [bsz, textIds[0].length];
const textIdsTensor = new ort.Tensor('int64', textIdsFlat, textIdsShape);
const textMaskFlat = new Float32Array(textMask.flat(2));
const textMaskShape = [bsz, 1, textMask[0][0].length];
const textMaskTensor = new ort.Tensor('float32', textMaskFlat, textMaskShape);
// Predict duration
const dpOutputs = await this.dpOrt.run({
text_ids: textIdsTensor,
style_dp: style.dp,
text_mask: textMaskTensor
});
const duration = Array.from(dpOutputs.duration.data);
// Apply speed factor to duration
for (let i = 0; i < duration.length; i++) {
duration[i] /= speed;
}
// Encode text
const textEncOutputs = await this.textEncOrt.run({
text_ids: textIdsTensor,
style_ttl: style.ttl,
text_mask: textMaskTensor
});
const textEmb = textEncOutputs.text_emb;
// Sample noisy latent
let { xt, latentMask } = this.sampleNoisyLatent(
duration,
this.sampleRate,
this.cfgs.ae.base_chunk_size,
this.cfgs.ttl.chunk_compress_factor,
this.cfgs.ttl.latent_dim
);
const latentMaskFlat = new Float32Array(latentMask.flat(2));
const latentMaskShape = [bsz, 1, latentMask[0][0].length];
const latentMaskTensor = new ort.Tensor('float32', latentMaskFlat, latentMaskShape);
// Prepare constant arrays
const totalStepArray = new Float32Array(bsz).fill(totalStep);
const totalStepTensor = new ort.Tensor('float32', totalStepArray, [bsz]);
// Denoising loop
for (let step = 0; step < totalStep; step++) {
if (progressCallback) {
progressCallback(step + 1, totalStep);
}
const currentStepArray = new Float32Array(bsz).fill(step);
const currentStepTensor = new ort.Tensor('float32', currentStepArray, [bsz]);
const xtFlat = new Float32Array(xt.flat(2));
const xtShape = [bsz, xt[0].length, xt[0][0].length];
const xtTensor = new ort.Tensor('float32', xtFlat, xtShape);
const vectorEstOutputs = await this.vectorEstOrt.run({
noisy_latent: xtTensor,
text_emb: textEmb,
style_ttl: style.ttl,
latent_mask: latentMaskTensor,
text_mask: textMaskTensor,
current_step: currentStepTensor,
total_step: totalStepTensor
});
const denoised = Array.from(vectorEstOutputs.denoised_latent.data);
// Reshape to 3D
const latentDim = xt[0].length;
const latentLen = xt[0][0].length;
xt = [];
let idx = 0;
for (let b = 0; b < bsz; b++) {
const batch = [];
for (let d = 0; d < latentDim; d++) {
const row = [];
for (let t = 0; t < latentLen; t++) {
row.push(denoised[idx++]);
}
batch.push(row);
}
xt.push(batch);
}
}
// Generate waveform
const finalXtFlat = new Float32Array(xt.flat(2));
const finalXtShape = [bsz, xt[0].length, xt[0][0].length];
const finalXtTensor = new ort.Tensor('float32', finalXtFlat, finalXtShape);
const vocoderOutputs = await this.vocoderOrt.run({
latent: finalXtTensor
});
const wav = Array.from(vocoderOutputs.wav_tts.data);
return { wav, duration };
}
async call(text, style, totalStep, speed = 1.05, silenceDuration = 0.3, progressCallback = null) {
if (style.ttl.dims[0] !== 1) {
throw new Error('Single speaker text to speech only supports single style');
}
const textList = chunkText(text);
let wavCat = [];
let durCat = 0;
for (const chunk of textList) {
const { wav, duration } = await this._infer([chunk], style, totalStep, speed, progressCallback);
if (wavCat.length === 0) {
wavCat = wav;
durCat = duration[0];
} else {
const silenceLen = Math.floor(silenceDuration * this.sampleRate);
const silence = new Array(silenceLen).fill(0);
wavCat = [...wavCat, ...silence, ...wav];
durCat += duration[0] + silenceDuration;
}
}
return { wav: wavCat, duration: [durCat] };
}
async batch(textList, style, totalStep, speed = 1.05, progressCallback = null) {
return await this._infer(textList, style, totalStep, speed, progressCallback);
}
sampleNoisyLatent(duration, sampleRate, baseChunkSize, chunkCompress, latentDim) {
const bsz = duration.length;
const maxDur = Math.max(...duration);
const wavLenMax = Math.floor(maxDur * sampleRate);
const wavLengths = duration.map(d => Math.floor(d * sampleRate));
const chunkSize = baseChunkSize * chunkCompress;
const latentLen = Math.floor((wavLenMax + chunkSize - 1) / chunkSize);
const latentDimVal = latentDim * chunkCompress;
const xt = [];
for (let b = 0; b < bsz; b++) {
const batch = [];
for (let d = 0; d < latentDimVal; d++) {
const row = [];
for (let t = 0; t < latentLen; t++) {
// Box-Muller transform
const u1 = Math.max(0.0001, Math.random());
const u2 = Math.random();
const val = Math.sqrt(-2.0 * Math.log(u1)) * Math.cos(2.0 * Math.PI * u2);
row.push(val);
}
batch.push(row);
}
xt.push(batch);
}
const latentLengths = wavLengths.map(len => Math.floor((len + chunkSize - 1) / chunkSize));
const latentMask = this.lengthToMask(latentLengths, latentLen);
// Apply mask
for (let b = 0; b < bsz; b++) {
for (let d = 0; d < latentDimVal; d++) {
for (let t = 0; t < latentLen; t++) {
xt[b][d][t] *= latentMask[b][0][t];
}
}
}
return { xt, latentMask };
}
lengthToMask(lengths, maxLen = null) {
const actualMaxLen = maxLen || Math.max(...lengths);
return lengths.map(len => {
const row = new Array(actualMaxLen).fill(0.0);
for (let j = 0; j < Math.min(len, actualMaxLen); j++) {
row[j] = 1.0;
}
return [row];
});
}
}
/**
* Load voice style from JSON files
*/
export async function loadVoiceStyle(voiceStylePaths, verbose = false) {
const bsz = voiceStylePaths.length;
// Read first file to get dimensions
const firstResponse = await fetch(voiceStylePaths[0]);
const firstStyle = await firstResponse.json();
const ttlDims = firstStyle.style_ttl.dims;
const dpDims = firstStyle.style_dp.dims;
const ttlDim1 = ttlDims[1];
const ttlDim2 = ttlDims[2];
const dpDim1 = dpDims[1];
const dpDim2 = dpDims[2];
// Pre-allocate arrays with full batch size
const ttlSize = bsz * ttlDim1 * ttlDim2;
const dpSize = bsz * dpDim1 * dpDim2;
const ttlFlat = new Float32Array(ttlSize);
const dpFlat = new Float32Array(dpSize);
// Fill in the data
for (let i = 0; i < bsz; i++) {
const response = await fetch(voiceStylePaths[i]);
const voiceStyle = await response.json();
// Flatten TTL data
const ttlData = voiceStyle.style_ttl.data.flat(Infinity);
const ttlOffset = i * ttlDim1 * ttlDim2;
ttlFlat.set(ttlData, ttlOffset);
// Flatten DP data
const dpData = voiceStyle.style_dp.data.flat(Infinity);
const dpOffset = i * dpDim1 * dpDim2;
dpFlat.set(dpData, dpOffset);
}
const ttlShape = [bsz, ttlDim1, ttlDim2];
const dpShape = [bsz, dpDim1, dpDim2];
const ttlTensor = new ort.Tensor('float32', ttlFlat, ttlShape);
const dpTensor = new ort.Tensor('float32', dpFlat, dpShape);
if (verbose) {
console.log(`Loaded ${bsz} voice styles`);
}
return new Style(ttlTensor, dpTensor);
}
/**
* Load configuration from JSON
*/
export async function loadCfgs(onnxDir) {
const response = await fetch(`${onnxDir}/tts.json`);
const cfgs = await response.json();
return cfgs;
}
/**
* Load text processor
*/
export async function loadTextProcessor(onnxDir) {
const response = await fetch(`${onnxDir}/unicode_indexer.json`);
const indexer = await response.json();
return new UnicodeProcessor(indexer);
}
/**
* Load ONNX model
*/
export async function loadOnnx(onnxPath, options) {
const session = await ort.InferenceSession.create(onnxPath, options);
return session;
}
/**
* Load all TTS components
*/
export async function loadTextToSpeech(onnxDir, sessionOptions = {}, progressCallback = null) {
console.log('Using WebAssembly/WebGPU for inference');
const cfgs = await loadCfgs(onnxDir);
const dpPath = `${onnxDir}/duration_predictor.onnx`;
const textEncPath = `${onnxDir}/text_encoder.onnx`;
const vectorEstPath = `${onnxDir}/vector_estimator.onnx`;
const vocoderPath = `${onnxDir}/vocoder.onnx`;
const modelPaths = [
{ name: 'Duration Predictor', path: dpPath },
{ name: 'Text Encoder', path: textEncPath },
{ name: 'Vector Estimator', path: vectorEstPath },
{ name: 'Vocoder', path: vocoderPath }
];
const sessions = [];
for (let i = 0; i < modelPaths.length; i++) {
if (progressCallback) {
progressCallback(modelPaths[i].name, i + 1, modelPaths.length);
}
const session = await loadOnnx(modelPaths[i].path, sessionOptions);
sessions.push(session);
}
const [dpOrt, textEncOrt, vectorEstOrt, vocoderOrt] = sessions;
const textProcessor = await loadTextProcessor(onnxDir);
const textToSpeech = new TextToSpeech(cfgs, textProcessor, dpOrt, textEncOrt, vectorEstOrt, vocoderOrt);
return { textToSpeech, cfgs };
}
/**
* Chunk text into manageable segments
*/
function chunkText(text, maxLen = 300) {
if (typeof text !== 'string') {
throw new Error(`chunkText expects a string, got ${typeof text}`);
}
// Split by paragraph (two or more newlines)
const paragraphs = text.trim().split(/\n\s*\n+/).filter(p => p.trim());
const chunks = [];
for (let paragraph of paragraphs) {
paragraph = paragraph.trim();
if (!paragraph) continue;
// Split by sentence boundaries (period, question mark, exclamation mark followed by space)
// But exclude common abbreviations like Mr., Mrs., Dr., etc. and single capital letters like F.
const sentences = paragraph.split(/(?<!Mr\.|Mrs\.|Ms\.|Dr\.|Prof\.|Sr\.|Jr\.|Ph\.D\.|etc\.|e\.g\.|i\.e\.|vs\.|Inc\.|Ltd\.|Co\.|Corp\.|St\.|Ave\.|Blvd\.)(?<!\b[A-Z]\.)(?<=[.!?])\s+/);
let currentChunk = "";
for (let sentence of sentences) {
if (currentChunk.length + sentence.length + 1 <= maxLen) {
currentChunk += (currentChunk ? " " : "") + sentence;
} else {
if (currentChunk) {
chunks.push(currentChunk.trim());
}
currentChunk = sentence;
}
}
if (currentChunk) {
chunks.push(currentChunk.trim());
}
}
return chunks;
}
/**
* Write WAV file to ArrayBuffer
*/
export function writeWavFile(audioData, sampleRate) {
const numChannels = 1;
const bitsPerSample = 16;
const byteRate = sampleRate * numChannels * bitsPerSample / 8;
const blockAlign = numChannels * bitsPerSample / 8;
const dataSize = audioData.length * 2;
// Create ArrayBuffer
const buffer = new ArrayBuffer(44 + dataSize);
const view = new DataView(buffer);
// Write WAV header
const writeString = (offset, string) => {
for (let i = 0; i < string.length; i++) {
view.setUint8(offset + i, string.charCodeAt(i));
}
};
writeString(0, 'RIFF');
view.setUint32(4, 36 + dataSize, true);
writeString(8, 'WAVE');
writeString(12, 'fmt ');
view.setUint32(16, 16, true);
view.setUint16(20, 1, true); // PCM
view.setUint16(22, numChannels, true);
view.setUint32(24, sampleRate, true);
view.setUint32(28, byteRate, true);
view.setUint16(32, blockAlign, true);
view.setUint16(34, bitsPerSample, true);
writeString(36, 'data');
view.setUint32(40, dataSize, true);
// Write audio data
const int16Data = new Int16Array(audioData.length);
for (let i = 0; i < audioData.length; i++) {
const clamped = Math.max(-1.0, Math.min(1.0, audioData[i]));
int16Data[i] = Math.floor(clamped * 32767);
}
const dataView = new Uint8Array(buffer, 44);
dataView.set(new Uint8Array(int16Data.buffer));
return buffer;
}

78
web/index.html Normal file
View File

@@ -0,0 +1,78 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Supertonic - Web Demo</title>
<link rel="stylesheet" href="/style.css">
</head>
<body>
<div class="container">
<h1>🎤 Supertonic</h1>
<p class="subtitle">Text-to-Speech with ONNX Runtime Web</p>
<div id="statusBox" class="status-box">
<div class="status-text-wrapper">
<div id="statusText">ℹ️ <strong>Loading models...</strong>
Please wait...</div>
</div>
<div id="backendBadge" class="backend-badge">WebAssembly</div>
</div>
<div class="main-content">
<div class="left-panel">
<div class="section">
<div class="ref-audio-label">
<label for="voiceStyleSelect">Voice Style: </label>
<span id="voiceStyleInfo"
class="ref-audio-info">Loading...</span>
</div>
<select id="voiceStyleSelect">
<option value="assets/voice_styles/M1.json">Male 1 (M1)</option>
<option value="assets/voice_styles/M2.json">Male 2 (M2)</option>
<option value="assets/voice_styles/F1.json">Female 1 (F1)</option>
<option value="assets/voice_styles/F2.json">Female 2 (F2)</option>
</select>
</div>
<div class="section">
<label for="text">Text to Synthesize:</label>
<textarea id="text"
placeholder="Enter the text you want to convert to speech...">This morning, I took a walk in the park, and the sound of the birds and the breeze was so pleasant that I stopped for a long time just to listen.</textarea>
</div>
<div class="params-grid">
<div class="section">
<label for="totalStep">Total Steps (higher = better
quality):</label>
<input type="number" id="totalStep" value="5"
min="1" max="50">
</div>
<div class="section">
<label for="speed">Speed (0.9-1.5 recommended):</label>
<input type="number" id="speed" value="1.05"
min="0.5" max="2.0" step="0.05">
</div>
</div>
<button id="generateBtn">Generate Speech</button>
<div id="error" class="error"></div>
</div>
<div class="right-panel">
<div id="results" class="results">
<div class="results-placeholder">
<div class="results-placeholder-icon">🎤</div>
<p>Generated speech will appear here</p>
</div>
</div>
</div>
</div>
</div>
<script type="module" src="/main.js"></script>
</body>
</html>

288
web/main.js Normal file
View File

@@ -0,0 +1,288 @@
import {
loadTextToSpeech,
loadVoiceStyle,
writeWavFile
} from './helper.js';
// Configuration
const DEFAULT_VOICE_STYLE_PATH = 'assets/voice_styles/M1.json';
// Helper function to extract filename from path
function getFilenameFromPath(path) {
return path.split('/').pop();
}
// Global state
let textToSpeech = null;
let cfgs = null;
// Pre-computed style
let currentStyle = null;
let currentStylePath = DEFAULT_VOICE_STYLE_PATH;
// UI Elements
const textInput = document.getElementById('text');
const voiceStyleSelect = document.getElementById('voiceStyleSelect');
const voiceStyleInfo = document.getElementById('voiceStyleInfo');
const totalStepInput = document.getElementById('totalStep');
const speedInput = document.getElementById('speed');
const generateBtn = document.getElementById('generateBtn');
const statusBox = document.getElementById('statusBox');
const statusText = document.getElementById('statusText');
const backendBadge = document.getElementById('backendBadge');
const resultsContainer = document.getElementById('results');
const errorBox = document.getElementById('error');
function showStatus(message, type = 'info') {
statusText.innerHTML = message;
statusBox.className = 'status-box';
if (type === 'success') {
statusBox.classList.add('success');
} else if (type === 'error') {
statusBox.classList.add('error');
}
}
function showError(message) {
errorBox.textContent = message;
errorBox.classList.add('active');
}
function hideError() {
errorBox.classList.remove('active');
}
function showBackendBadge() {
backendBadge.classList.add('visible');
}
// Load voice style from JSON
async function loadStyleFromJSON(stylePath) {
try {
const style = await loadVoiceStyle([stylePath], true);
return style;
} catch (error) {
console.error('Error loading voice style:', error);
throw error;
}
}
// Load models on page load
async function initializeModels() {
try {
showStatus('ℹ️ <strong>Loading configuration...</strong>');
const basePath = 'assets/onnx';
// Try WebGPU first, fallback to WASM
let executionProvider = 'wasm';
try {
const result = await loadTextToSpeech(basePath, {
executionProviders: ['webgpu'],
graphOptimizationLevel: 'all'
}, (modelName, current, total) => {
showStatus(`ℹ️ <strong>Loading ONNX models (${current}/${total}):</strong> ${modelName}...`);
});
textToSpeech = result.textToSpeech;
cfgs = result.cfgs;
executionProvider = 'webgpu';
backendBadge.textContent = 'WebGPU';
backendBadge.style.background = '#4caf50';
} catch (webgpuError) {
console.log('WebGPU not available, falling back to WebAssembly');
const result = await loadTextToSpeech(basePath, {
executionProviders: ['wasm'],
graphOptimizationLevel: 'all'
}, (modelName, current, total) => {
showStatus(`ℹ️ <strong>Loading ONNX models (${current}/${total}):</strong> ${modelName}...`);
});
textToSpeech = result.textToSpeech;
cfgs = result.cfgs;
}
showStatus('ℹ️ <strong>Loading default voice style...</strong>');
// Load default voice style
currentStyle = await loadStyleFromJSON(currentStylePath);
voiceStyleInfo.textContent = `${getFilenameFromPath(currentStylePath)} (default)`;
showStatus(`✅ <strong>Models loaded!</strong> Using ${executionProvider.toUpperCase()}. You can now generate speech.`, 'success');
showBackendBadge();
generateBtn.disabled = false;
} catch (error) {
console.error('Error loading models:', error);
showStatus(`❌ <strong>Error loading models:</strong> ${error.message}`, 'error');
}
}
// Handle voice style selection
voiceStyleSelect.addEventListener('change', async (e) => {
const selectedValue = e.target.value;
if (!selectedValue) return;
try {
generateBtn.disabled = true;
showStatus(`ℹ️ <strong>Loading voice style...</strong>`, 'info');
currentStylePath = selectedValue;
currentStyle = await loadStyleFromJSON(currentStylePath);
voiceStyleInfo.textContent = getFilenameFromPath(currentStylePath);
showStatus(`✅ <strong>Voice style loaded:</strong> ${getFilenameFromPath(currentStylePath)}`, 'success');
generateBtn.disabled = false;
} catch (error) {
showError(`Error loading voice style: ${error.message}`);
// Restore default style
currentStylePath = DEFAULT_VOICE_STYLE_PATH;
voiceStyleSelect.value = currentStylePath;
try {
currentStyle = await loadStyleFromJSON(currentStylePath);
voiceStyleInfo.textContent = `${getFilenameFromPath(currentStylePath)} (default)`;
} catch (styleError) {
console.error('Error restoring default style:', styleError);
}
generateBtn.disabled = false;
}
});
// Main synthesis function
async function generateSpeech() {
const text = textInput.value.trim();
if (!text) {
showError('Please enter some text to synthesize.');
return;
}
if (!textToSpeech || !cfgs) {
showError('Models are still loading. Please wait.');
return;
}
if (!currentStyle) {
showError('Voice style is not ready. Please wait.');
return;
}
const startTime = Date.now();
try {
generateBtn.disabled = true;
hideError();
// Clear results and show placeholder
resultsContainer.innerHTML = `
<div class="results-placeholder generating">
<div class="results-placeholder-icon">⏳</div>
<p>Generating speech...</p>
</div>
`;
const totalStep = parseInt(totalStepInput.value);
const speed = parseFloat(speedInput.value);
showStatus('ℹ️ <strong>Generating speech from text...</strong>');
const tic = Date.now();
const { wav, duration } = await textToSpeech.call(
text,
currentStyle,
totalStep,
speed,
0.3,
(step, total) => {
showStatus(`ℹ️ <strong>Denoising (${step}/${total})...</strong>`);
}
);
const toc = Date.now();
console.log(`Text-to-speech synthesis: ${((toc - tic) / 1000).toFixed(2)}s`);
showStatus('ℹ️ <strong>Creating audio file...</strong>');
const wavLen = Math.floor(textToSpeech.sampleRate * duration[0]);
const wavOut = wav.slice(0, wavLen);
// Create WAV file
const wavBuffer = writeWavFile(wavOut, textToSpeech.sampleRate);
const blob = new Blob([wavBuffer], { type: 'audio/wav' });
const url = URL.createObjectURL(blob);
// Calculate total time and audio duration
const endTime = Date.now();
const totalTimeSec = ((endTime - startTime) / 1000).toFixed(2);
const audioDurationSec = duration[0].toFixed(2);
// Display result with full text
resultsContainer.innerHTML = `
<div class="result-item">
<div class="result-text-container">
<div class="result-text-label">Input Text</div>
<div class="result-text">${text}</div>
</div>
<div class="result-info">
<div class="info-item">
<span>📊 Audio Length</span>
<strong>${audioDurationSec}s</strong>
</div>
<div class="info-item">
<span>⏱️ Generation Time</span>
<strong>${totalTimeSec}s</strong>
</div>
</div>
<div class="result-player">
<audio controls>
<source src="${url}" type="audio/wav">
</audio>
</div>
<div class="result-actions">
<button onclick="downloadAudio('${url}', 'synthesized_speech.wav')">
<span>⬇️</span>
<span>Download WAV</span>
</button>
</div>
</div>
`;
showStatus('✅ <strong>Speech synthesis completed successfully!</strong>', 'success');
} catch (error) {
console.error('Error during synthesis:', error);
showStatus(`❌ <strong>Error during synthesis:</strong> ${error.message}`, 'error');
showError(`Error during synthesis: ${error.message}`);
// Restore placeholder
resultsContainer.innerHTML = `
<div class="results-placeholder">
<div class="results-placeholder-icon">🎤</div>
<p>Generated speech will appear here</p>
</div>
`;
} finally {
generateBtn.disabled = false;
}
}
// Download handler (make it global so it can be called from onclick)
window.downloadAudio = function(url, filename) {
const a = document.createElement('a');
a.href = url;
a.download = filename;
a.click();
};
// Attach generate function to button
generateBtn.addEventListener('click', generateSpeech);
// Initialize on load
window.addEventListener('load', async () => {
generateBtn.disabled = true;
await initializeModels();
});

21
web/package.json Normal file
View File

@@ -0,0 +1,21 @@
{
"name": "tts-onnx-web",
"version": "1.0.0",
"description": "TTS inference using ONNX Runtime for Web Browser",
"type": "module",
"scripts": {
"dev": "vite",
"build": "vite build",
"preview": "vite preview"
},
"keywords": ["tts", "onnx", "speech-synthesis", "web"],
"author": "",
"license": "MIT",
"dependencies": {
"fft.js": "^4.0.3",
"onnxruntime-web": "^1.17.0"
},
"devDependencies": {
"vite": "^5.0.0"
}
}

453
web/style.css Normal file
View File

@@ -0,0 +1,453 @@
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
min-height: 100vh;
display: flex;
justify-content: center;
align-items: center;
padding: 20px;
}
.container {
background: white;
border-radius: 20px;
padding: 40px;
max-width: 1400px;
width: 100%;
box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
}
.main-content {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 40px;
margin-top: 30px;
align-items: start;
}
.left-panel {
display: flex;
flex-direction: column;
}
.right-panel {
display: flex;
flex-direction: column;
height: 100%;
}
@media (max-width: 1024px) {
.main-content {
grid-template-columns: 1fr;
}
}
h1 {
color: #333;
margin-bottom: 10px;
font-size: 2em;
}
.subtitle {
color: #666;
margin-bottom: 30px;
font-size: 1.1em;
}
.section {
margin-bottom: 25px;
}
label {
display: block;
font-weight: 600;
color: #333;
margin-bottom: 8px;
font-size: 0.95em;
}
input[type="file"],
textarea,
input[type="number"] {
width: 100%;
padding: 12px;
border: 2px solid #e0e0e0;
border-radius: 8px;
font-size: 1em;
transition: border-color 0.3s;
}
input[type="file"]:focus,
textarea:focus,
input[type="number"]:focus {
outline: none;
border-color: #667eea;
}
textarea {
resize: vertical;
min-height: 100px;
font-family: inherit;
}
.params-grid {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 15px;
}
button {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
border: none;
padding: 15px 30px;
font-size: 1.1em;
font-weight: 600;
border-radius: 8px;
cursor: pointer;
width: 100%;
transition: transform 0.2s, box-shadow 0.2s;
}
button:hover:not(:disabled) {
transform: translateY(-2px);
box-shadow: 0 5px 20px rgba(102, 126, 234, 0.4);
}
button:disabled {
opacity: 0.6;
cursor: not-allowed;
}
.status-box {
background: #e3f2fd;
border-left: 4px solid #2196f3;
padding: 15px;
margin-bottom: 10px;
border-radius: 4px;
font-size: 0.9em;
color: #1565c0;
transition: all 0.3s ease;
display: flex;
justify-content: space-between;
align-items: center;
flex-wrap: wrap;
gap: 15px;
min-height: 50px;
}
.status-box.success {
background: #e8f5e9;
border-left-color: #4caf50;
color: #2e7d32;
}
.status-box.error {
background: #ffebee;
border-left-color: #f44336;
color: #c62828;
}
.status-text-wrapper {
flex: 1;
min-width: 200px;
}
.backend-badge {
display: inline-block;
visibility: hidden;
padding: 6px 12px;
background: #ff9800;
color: white;
border-radius: 12px;
font-size: 0.85em;
font-weight: 600;
margin-left: 10px;
white-space: nowrap;
}
.backend-badge.visible {
visibility: visible;
}
.ref-audio-info {
color: #4caf50;
font-weight: 700;
font-size: 0.95em;
}
.ref-audio-label {
margin-bottom: 8px;
}
.ref-audio-label label {
display: inline;
margin-bottom: 0;
}
.results {
flex: 1;
display: flex;
flex-direction: column;
}
.result-item {
background: white;
border-radius: 16px;
box-shadow: 0 2px 12px rgba(0, 0, 0, 0.08);
overflow: hidden;
transition: box-shadow 0.3s ease;
display: flex;
flex-direction: column;
flex: 1;
}
.result-item:hover {
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.12);
}
.result-item h3 {
color: #667eea;
margin-bottom: 15px;
font-size: 1.2em;
}
.result-text-container {
padding: 20px;
background: linear-gradient(135deg, #f8f9ff 0%, #ffffff 100%);
border-bottom: 1px solid #e8ecf5;
flex: 1;
display: flex;
flex-direction: column;
overflow: hidden;
}
.result-text-label {
font-size: 0.75em;
text-transform: uppercase;
letter-spacing: 0.5px;
color: #667eea;
font-weight: 600;
margin-bottom: 8px;
}
.result-text {
color: #333;
line-height: 1.7;
font-size: 0.95em;
word-wrap: break-word;
white-space: pre-wrap;
overflow-y: auto;
padding-right: 8px;
flex: 1;
}
.result-text::-webkit-scrollbar {
width: 6px;
}
.result-text::-webkit-scrollbar-track {
background: #f0f0f0;
border-radius: 3px;
}
.result-text::-webkit-scrollbar-thumb {
background: #c0c0c0;
border-radius: 3px;
}
.result-text::-webkit-scrollbar-thumb:hover {
background: #a0a0a0;
}
.result-info {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 0;
background: #fafbff;
}
.info-item {
padding: 16px 20px;
display: flex;
align-items: center;
gap: 8px;
font-size: 0.9em;
color: #666;
border-bottom: 1px solid #e8ecf5;
}
.info-item:nth-child(1) {
border-right: 1px solid #e8ecf5;
}
.info-item strong {
color: #333;
font-size: 1.1em;
font-weight: 600;
margin-left: auto;
}
.result-player {
padding: 20px;
background: white;
}
.result-item audio {
width: 100%;
height: 48px;
outline: none;
}
.result-item audio:focus {
outline: 2px solid #667eea;
outline-offset: 2px;
border-radius: 4px;
}
.result-actions {
padding: 16px 20px 20px;
background: white;
}
.result-item button {
width: 100%;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
border: none;
padding: 12px 24px;
font-size: 0.95em;
font-weight: 600;
border-radius: 8px;
cursor: pointer;
transition: all 0.3s ease;
display: flex;
align-items: center;
justify-content: center;
gap: 8px;
}
.result-item button:hover {
transform: translateY(-2px);
box-shadow: 0 4px 16px rgba(102, 126, 234, 0.3);
}
.result-item button:active {
transform: translateY(0);
}
@media (max-width: 640px) {
.result-info {
grid-template-columns: 1fr;
}
.info-item:nth-child(1) {
border-right: none;
}
}
audio {
width: 100%;
margin-top: 10px;
}
.error {
background: #fee;
color: #c00;
padding: 15px;
border-radius: 8px;
margin-top: 20px;
display: none;
}
.error.active {
display: block;
}
.warning-box {
background: #fff3cd;
color: #856404;
padding: 12px 15px;
border-radius: 8px;
margin-top: 10px;
border-left: 4px solid #ffc107;
font-size: 0.9em;
display: none;
line-height: 1.5;
}
.warning-box.active {
display: block;
}
.warning-box::before {
content: "⚠️ ";
margin-right: 5px;
}
.results-placeholder {
background: white;
border-radius: 16px;
box-shadow: 0 2px 12px rgba(0, 0, 0, 0.08);
padding: 60px 40px;
text-align: center;
color: #999;
transition: all 0.3s ease;
display: flex;
flex-direction: column;
justify-content: center;
align-items: center;
flex: 1;
min-height: 400px;
}
.results-placeholder:hover {
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.12);
}
.results-placeholder-icon {
font-size: 4em;
margin-bottom: 20px;
opacity: 0.6;
animation: float 3s ease-in-out infinite;
}
.results-placeholder.generating .results-placeholder-icon {
animation: spin 2s linear infinite;
}
@keyframes float {
0%, 100% {
transform: translateY(0px);
}
50% {
transform: translateY(-10px);
}
}
@keyframes spin {
0% {
transform: rotate(0deg);
}
100% {
transform: rotate(360deg);
}
}
.results-placeholder p {
font-size: 1.05em;
color: #888;
font-weight: 500;
margin: 0;
}
.hidden {
display: none;
}

14
web/vite.config.js Normal file
View File

@@ -0,0 +1,14 @@
import { defineConfig } from 'vite';
export default defineConfig({
server: {
port: 3000,
open: true
},
build: {
target: 'esnext'
},
optimizeDeps: {
exclude: ['onnxruntime-web']
}
});