Supertonic 2

2026-01-06 17:15:20 +09:00
parent ceedbbb835
commit e71c516714
44 changed files with 1105 additions and 581 deletions
--- a/flutter/README.md
+++ b/flutter/README.md
@@ -1,18 +1,29 @@
 # Supertonic Flutter Example

-This example demonstrates how to use Supertonic in a Flutter application using ONNX Runtime.
+This example demonstrates how to use Supertonic 2 in a Flutter application using ONNX Runtime.

 > **Note:** This project uses the `flutter_onnxruntime` package ([https://pub.dev/packages/flutter_onnxruntime](https://pub.dev/packages/flutter_onnxruntime)). At the moment, only the macOS platform has been tested. Although the flutter_onnxruntime package supports several other platforms, they have not been tested in this project yet and may require additional verification.


 ## 📰 Update News

+**2026.01.06** - 🎉 **Supertonic 2** released with multilingual support! Now supports English (`en`), Korean (`ko`), Spanish (`es`), Portuguese (`pt`), and French (`fr`). [Demo](https://huggingface.co/spaces/Supertone/supertonic-2) | [Models](https://huggingface.co/Supertone/supertonic-2)
+
 **2025.12.10** - Added [6 new voice styles](https://huggingface.co/Supertone/supertonic/tree/b10dbaf18b316159be75b34d24f740008fddd381) (M3, M4, M5, F3, F4, F5). See [Voices](https://supertone-inc.github.io/supertonic-py/voices/) for details

 **2025.12.08** - Optimized ONNX models via [OnnxSlim](https://github.com/inisis/OnnxSlim) now available on [Hugging Face Models](https://huggingface.co/Supertone/supertonic)

 **2025.11.23** - Added and tested macos support.

+## Multilingual Support
+
+Supertonic 2 supports multiple languages. Select the appropriate language from the dropdown:
+- **English (en)**: Default language
+- **한국어 (ko)**: Korean
+- **Español (es)**: Spanish
+- **Português (pt)**: Portuguese
+- **Français (fr)**: French
+
 ## Requirements

 - Flutter SDK version ^3.5.0
--- a/flutter/lib/helper.dart
+++ b/flutter/lib/helper.dart
@@ -11,6 +11,205 @@ final logger = Logger(
  printer: PrettyPrinter(methodCount: 0, errorMethodCount: 5, lineLength: 80),
 );

+// Available languages for multilingual TTS
+const List<String> availableLangs = ['en', 'ko', 'es', 'pt', 'fr'];
+
+bool isValidLang(String lang) => availableLangs.contains(lang);
+
+// Hangul Jamo constants for NFKD decomposition
+const int _hangulSyllableBase = 0xAC00;
+const int _hangulSyllableEnd = 0xD7A3;
+const int _leadingJamoBase = 0x1100;
+const int _vowelJamoBase = 0x1161;
+const int _trailingJamoBase = 0x11A7;
+const int _vowelCount = 21;
+const int _trailingCount = 28;
+
+/// Decompose a Hangul syllable into Jamo (NFKD-like decomposition)
+List<int> _decomposeHangulSyllable(int codePoint) {
+  if (codePoint < _hangulSyllableBase || codePoint > _hangulSyllableEnd) {
+    return [codePoint];
+  }
+
+  final syllableIndex = codePoint - _hangulSyllableBase;
+  final leadingIndex = syllableIndex ~/ (_vowelCount * _trailingCount);
+  final vowelIndex =
+      (syllableIndex % (_vowelCount * _trailingCount)) ~/ _trailingCount;
+  final trailingIndex = syllableIndex % _trailingCount;
+
+  final result = <int>[
+    _leadingJamoBase + leadingIndex,
+    _vowelJamoBase + vowelIndex,
+  ];
+
+  if (trailingIndex > 0) {
+    result.add(_trailingJamoBase + trailingIndex);
+  }
+
+  return result;
+}
+
+/// Common Latin character decompositions (NFKD) for es, pt, fr
+const Map<int, List<int>> _latinDecompositions = {
+  // Uppercase with acute accent
+  0x00C1: [0x0041, 0x0301], // Á → A + ́
+  0x00C9: [0x0045, 0x0301], // É → E + ́
+  0x00CD: [0x0049, 0x0301], // Í → I + ́
+  0x00D3: [0x004F, 0x0301], // Ó → O + ́
+  0x00DA: [0x0055, 0x0301], // Ú → U + ́
+  // Lowercase with acute accent
+  0x00E1: [0x0061, 0x0301], // á → a + ́
+  0x00E9: [0x0065, 0x0301], // é → e + ́
+  0x00ED: [0x0069, 0x0301], // í → i + ́
+  0x00F3: [0x006F, 0x0301], // ó → o + ́
+  0x00FA: [0x0075, 0x0301], // ú → u + ́
+  // Grave accent
+  0x00C0: [0x0041, 0x0300], // À → A + ̀
+  0x00C8: [0x0045, 0x0300], // È → E + ̀
+  0x00CC: [0x0049, 0x0300], // Ì → I + ̀
+  0x00D2: [0x004F, 0x0300], // Ò → O + ̀
+  0x00D9: [0x0055, 0x0300], // Ù → U + ̀
+  0x00E0: [0x0061, 0x0300], // à → a + ̀
+  0x00E8: [0x0065, 0x0300], // è → e + ̀
+  0x00EC: [0x0069, 0x0300], // ì → i + ̀
+  0x00F2: [0x006F, 0x0300], // ò → o + ̀
+  0x00F9: [0x0075, 0x0300], // ù → u + ̀
+  // Circumflex
+  0x00C2: [0x0041, 0x0302], // Â → A + ̂
+  0x00CA: [0x0045, 0x0302], // Ê → E + ̂
+  0x00CE: [0x0049, 0x0302], // Î → I + ̂
+  0x00D4: [0x004F, 0x0302], // Ô → O + ̂
+  0x00DB: [0x0055, 0x0302], // Û → U + ̂
+  0x00E2: [0x0061, 0x0302], // â → a + ̂
+  0x00EA: [0x0065, 0x0302], // ê → e + ̂
+  0x00EE: [0x0069, 0x0302], // î → i + ̂
+  0x00F4: [0x006F, 0x0302], // ô → o + ̂
+  0x00FB: [0x0075, 0x0302], // û → u + ̂
+  // Tilde
+  0x00C3: [0x0041, 0x0303], // Ã → A + ̃
+  0x00D1: [0x004E, 0x0303], // Ñ → N + ̃
+  0x00D5: [0x004F, 0x0303], // Õ → O + ̃
+  0x00E3: [0x0061, 0x0303], // ã → a + ̃
+  0x00F1: [0x006E, 0x0303], // ñ → n + ̃
+  0x00F5: [0x006F, 0x0303], // õ → o + ̃
+  // Diaeresis/Umlaut
+  0x00C4: [0x0041, 0x0308], // Ä → A + ̈
+  0x00CB: [0x0045, 0x0308], // Ë → E + ̈
+  0x00CF: [0x0049, 0x0308], // Ï → I + ̈
+  0x00D6: [0x004F, 0x0308], // Ö → O + ̈
+  0x00DC: [0x0055, 0x0308], // Ü → U + ̈
+  0x00E4: [0x0061, 0x0308], // ä → a + ̈
+  0x00EB: [0x0065, 0x0308], // ë → e + ̈
+  0x00EF: [0x0069, 0x0308], // ï → i + ̈
+  0x00F6: [0x006F, 0x0308], // ö → o + ̈
+  0x00FC: [0x0075, 0x0308], // ü → u + ̈
+  // Cedilla
+  0x00C7: [0x0043, 0x0327], // Ç → C + ̧
+  0x00E7: [0x0063, 0x0327], // ç → c + ̧
+};
+
+/// Apply NFKD-like decomposition (Hangul + Latin accented characters)
+String _applyNfkdDecomposition(String text) {
+  final result = <int>[];
+  for (final codePoint in text.runes) {
+    // Check Hangul first
+    if (codePoint >= _hangulSyllableBase && codePoint <= _hangulSyllableEnd) {
+      result.addAll(_decomposeHangulSyllable(codePoint));
+    }
+    // Check Latin decomposition
+    else if (_latinDecompositions.containsKey(codePoint)) {
+      result.addAll(_latinDecompositions[codePoint]!);
+    }
+    // Keep as-is
+    else {
+      result.add(codePoint);
+    }
+  }
+  return String.fromCharCodes(result);
+}
+
+String preprocessText(String text, String lang) {
+  // Apply NFKD-like decomposition (especially for Hangul syllables → Jamo)
+  text = _applyNfkdDecomposition(text);
+
+  // Remove emojis
+  text = text.replaceAll(
+      RegExp(
+        r'[\u{1F600}-\u{1F64F}]|[\u{1F300}-\u{1F5FF}]|[\u{1F680}-\u{1F6FF}]|'
+        r'[\u{1F700}-\u{1F77F}]|[\u{1F780}-\u{1F7FF}]|[\u{1F800}-\u{1F8FF}]|'
+        r'[\u{1F900}-\u{1F9FF}]|[\u{1FA00}-\u{1FA6F}]|[\u{1FA70}-\u{1FAFF}]|'
+        r'[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]|[\u{1F1E6}-\u{1F1FF}]',
+        unicode: true,
+      ),
+      '');
+
+  // Replace various dashes and symbols
+  const replacements = {
+    '–': '-',
+    '‑': '-',
+    '—': '-',
+    '_': ' ',
+    '\u201C': '"',
+    '\u201D': '"',
+    '\u2018': "'",
+    '\u2019': "'",
+    '´': "'",
+    '`': "'",
+    '[': ' ',
+    ']': ' ',
+    '|': ' ',
+    '/': ' ',
+    '#': ' ',
+    '→': ' ',
+    '←': ' ',
+  };
+  for (final entry in replacements.entries) {
+    text = text.replaceAll(entry.key, entry.value);
+  }
+
+  // Remove special symbols
+  text = text.replaceAll(RegExp(r'[♥☆♡©\\]'), '');
+
+  // Replace known expressions
+  text = text.replaceAll('@', ' at ');
+  text = text.replaceAll('e.g.,', 'for example, ');
+  text = text.replaceAll('i.e.,', 'that is, ');
+
+  // Fix spacing around punctuation
+  text = text.replaceAll(' ,', ',');
+  text = text.replaceAll(' .', '.');
+  text = text.replaceAll(' !', '!');
+  text = text.replaceAll(' ?', '?');
+  text = text.replaceAll(' ;', ';');
+  text = text.replaceAll(' :', ':');
+  text = text.replaceAll(" '", "'");
+
+  // Remove duplicate quotes
+  while (text.contains('""')) text = text.replaceAll('""', '"');
+  while (text.contains("''")) text = text.replaceAll("''", "'");
+  while (text.contains('``')) text = text.replaceAll('``', '`');
+
+  // Remove extra spaces
+  text = text.replaceAll(RegExp(r'\s+'), ' ').trim();
+
+  // Add period if needed
+  if (text.isNotEmpty &&
+      !RegExp(r'[.!?;:,\x27\x22\u2018\u2019)\]}…。」』】〉》›»]$').hasMatch(text)) {
+    text += '.';
+  }
+
+  // Validate language
+  if (!isValidLang(lang)) {
+    throw ArgumentError(
+        'Invalid language: $lang. Available: ${availableLangs.join(", ")}');
+  }
+
+  // Wrap text with language tags
+  text = '<$lang>$text</$lang>';
+
+  return text;
+}
+
 class UnicodeProcessor {
  final Map<int, int> indexer;

@@ -34,11 +233,17 @@ class UnicodeProcessor {
    return UnicodeProcessor._(indexer);
  }

-  Map<String, dynamic> call(List<String> textList) {
-    final lengths = textList.map((t) => t.length).toList();
+  Map<String, dynamic> call(List<String> textList, List<String> langList) {
+    // Preprocess texts with language tags
+    final processedTexts = <String>[];
+    for (var i = 0; i < textList.length; i++) {
+      processedTexts.add(preprocessText(textList[i], langList[i]));
+    }
+
+    final lengths = processedTexts.map((t) => t.runes.length).toList();
    final maxLen = lengths.reduce(math.max);

-    final textIds = textList.map((text) {
+    final textIds = processedTexts.map((text) {
      final row = List<int>.filled(maxLen, 0);
      final runes = text.runes.toList();
      for (var i = 0; i < runes.length; i++) {
@@ -77,14 +282,18 @@ class TextToSpeech {
        chunkCompressFactor = cfgs['ttl']['chunk_compress_factor'],
        ldim = cfgs['ttl']['latent_dim'];

-  Future<Map<String, dynamic>> call(String text, Style style, int totalStep,
+  Future<Map<String, dynamic>> call(
+      String text, String lang, Style style, int totalStep,
      {double speed = 1.05, double silenceDuration = 0.3}) async {
-    final chunks = _chunkText(text);
+    final maxLen = lang == 'ko' ? 120 : 300;
+    final chunks = _chunkText(text, maxLen: maxLen);
+    final langList = List.filled(chunks.length, lang);
    List<double>? wavCat;
    double durCat = 0;

-    for (final chunk in chunks) {
-      final result = await _infer([chunk], style, totalStep, speed: speed);
+    for (var i = 0; i < chunks.length; i++) {
+      final result = await _infer([chunks[i]], [langList[i]], style, totalStep,
+          speed: speed);
      final wav = _safeCast<double>(result['wav']);
      final duration = _safeCast<double>(result['duration']);

@@ -108,10 +317,10 @@ class TextToSpeech {
  }

  Future<Map<String, dynamic>> _infer(
-      List<String> textList, Style style, int totalStep,
+      List<String> textList, List<String> langList, Style style, int totalStep,
      {double speed = 1.05}) async {
    final bsz = textList.length;
-    final result = textProcessor.call(textList);
+    final result = textProcessor.call(textList, langList);

    final textIdsRaw = result['textIds'];
    final textIds = textIdsRaw is List<List<int>>
--- a/flutter/lib/main.dart
+++ b/flutter/lib/main.dart
@@ -14,7 +14,7 @@ class SupertonicApp extends StatelessWidget {
  @override
  Widget build(BuildContext context) {
    return MaterialApp(
-      title: 'Supertonic',
+      title: 'Supertonic 2',
      theme: ThemeData(
        colorScheme: ColorScheme.fromSeed(seedColor: Colors.deepPurple),
        useMaterial3: true,
@@ -44,6 +44,7 @@ class _TTSPageState extends State<TTSPage> {
  String _status = 'Not initialized';
  int _totalSteps = 5;
  double _speed = 1.05;
+  String _selectedLang = 'en';
  bool _isPlaying = false;
  String? _lastGeneratedFilePath;

@@ -119,6 +120,7 @@ class _TTSPageState extends State<TTSPage> {
    try {
      final result = await _textToSpeech!.call(
        _textController.text,
+        _selectedLang,
        _style!,
        _totalSteps,
        speed: _speed,
@@ -208,7 +210,7 @@ class _TTSPageState extends State<TTSPage> {
    return Scaffold(
      appBar: AppBar(
        backgroundColor: Theme.of(context).colorScheme.inversePrimary,
-        title: const Text('Supertonic'),
+        title: const Text('Supertonic 2'),
      ),
      body: Padding(
        padding: const EdgeInsets.all(16.0),
@@ -310,6 +312,31 @@ class _TTSPageState extends State<TTSPage> {
                ),
              ],
            ),
+            const SizedBox(height: 12),
+
+            // Language selector
+            Row(
+              children: [
+                const Expanded(flex: 2, child: Text('Language:')),
+                Expanded(
+                  flex: 3,
+                  child: DropdownButton<String>(
+                    value: _selectedLang,
+                    isExpanded: true,
+                    items: const [
+                      DropdownMenuItem(value: 'en', child: Text('English')),
+                      DropdownMenuItem(value: 'ko', child: Text('한국어')),
+                      DropdownMenuItem(value: 'es', child: Text('Español')),
+                      DropdownMenuItem(value: 'pt', child: Text('Português')),
+                      DropdownMenuItem(value: 'fr', child: Text('Français')),
+                    ],
+                    onChanged: _isLoading || _isGenerating
+                        ? null
+                        : (value) => setState(() => _selectedLang = value!),
+                  ),
+                ),
+              ],
+            ),
            const SizedBox(height: 24),

            // Generate button
--- a/flutter/macos/Podfile.lock
+++ b/flutter/macos/Podfile.lock
@@ -41,11 +41,11 @@ EXTERNAL SOURCES:
    :path: Flutter/ephemeral/.symlinks/plugins/objective_c/macos

 SPEC CHECKSUMS:
-  audio_session: eaca2512cf2b39212d724f35d11f46180ad3a33e
-  flutter_onnxruntime: 546c7c7630c9259f59021319639b30bdaff148c2
+  audio_session: 728ae3823d914f809c485d390274861a24b0904e
+  flutter_onnxruntime: e6887abc1032d3e5c92f84b912ad42c33e9ce1c9
  FlutterMacOS: d0db08ddef1a9af05a5ec4b724367152bb0500b1
-  just_audio: 4e391f57b79cad2b0674030a00453ca5ce817eed
-  objective_c: ec13431e45ba099cb734eb2829a5c1cd37986cba
+  just_audio: a42c63806f16995daf5b219ae1d679deb76e6a79
+  objective_c: e5f8194456e8fc943e034d1af00510a1bc29c067
  onnxruntime-c: ac65025f01072d25d7d394a2b43ac30d9397b260
  onnxruntime-objc: 5fa03134356d47b642ec85b1023d9907a123d201