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

Supertonic 2

Browse Source
This commit is contained in:
ANLGBOY
2026-01-06 17:15:20 +09:00
parent ceedbbb835
commit e71c516714
44 changed files with 1105 additions and 581 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
csharp/ExampleONNX.cs
View File

@@ -19,6 +19,7 @@ namespace Supertonic
{
"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."
};
public List<string> Lang { get; set; } = new List<string> { "en" };
public string SaveDir { get; set; } = "results";
public bool Batch { get; set; } = false;
}
@@ -55,6 +56,9 @@ namespace Supertonic
case "--text" when i + 1 < args.Length:
result.Text = args[++i].Split('|').ToList();
break;
case "--lang" when i + 1 < args.Length:
result.Lang = args[++i].Split(',').ToList();
break;
case "--save-dir" when i + 1 < args.Length:
result.SaveDir = args[++i];
break;
@@ -76,6 +80,7 @@ namespace Supertonic
string saveDir = parsedArgs.SaveDir;
var voiceStylePaths = parsedArgs.VoiceStyle;
var textList = parsedArgs.Text;
var langList = parsedArgs.Lang;
bool batch = parsedArgs.Batch;
if (voiceStylePaths.Count != textList.Count)
@@ -101,11 +106,11 @@ namespace Supertonic
{
if (batch)
{
return textToSpeech.Batch(textList, style, totalStep, speed);
return textToSpeech.Batch(textList, langList, style, totalStep, speed);
}
else
{
return textToSpeech.Call(textList[0], style, totalStep, speed);
return textToSpeech.Call(textList[0], langList[0], style, totalStep, speed);
}
});

42
csharp/Helper.cs
View File

@@ -10,6 +10,12 @@ using Microsoft.ML.OnnxRuntime.Tensors;
namespace Supertonic
{
// Available languages for multilingual TTS
public static class Languages
{
public static readonly string[] Available = { "en", "ko", "es", "pt", "fr" };
}
// ============================================================================
// Configuration classes
// ============================================================================
@@ -118,13 +124,11 @@ namespace Supertonic
return result.ToString();
}
private string PreprocessText(string text)
private string PreprocessText(string text, string lang)
{
// TODO: Need advanced normalizer for better performance
text = text.Normalize(NormalizationForm.FormKD);
// FIXME: this should be fixed for non-English languages
// Remove emojis (wide Unicode range)
// C# doesn't support \u{...} syntax in regex, so we use character filtering instead
text = RemoveEmojis(text);
@@ -135,7 +139,6 @@ namespace Supertonic
{"–", "-"}, // en dash
{"‑", "-"}, // non-breaking hyphen
{"—", "-"}, // em dash
{"¯", " "}, // macron
{"_", " "}, // underscore
{"\u201C", "\""}, // left double quote
{"\u201D", "\""}, // right double quote
@@ -157,9 +160,6 @@ namespace Supertonic
text = text.Replace(kvp.Key, kvp.Value);
}
// Remove combining diacritics // FIXME: this should be fixed for non-English languages
text = Regex.Replace(text, @"[\u0302\u0303\u0304\u0305\u0306\u0307\u0308\u030A\u030B\u030C\u0327\u0328\u0329\u032A\u032B\u032C\u032D\u032E\u032F]", "");
// Remove special symbols
text = Regex.Replace(text, @"[♥☆♡©\\]", "");
@@ -208,6 +208,15 @@ namespace Supertonic
text += ".";
}
// Validate language
if (!Languages.Available.Contains(lang))
{
throw new ArgumentException($"Invalid language: {lang}. Available: {string.Join(", ", Languages.Available)}");
}
// Wrap text with language tags
text = $"<{lang}>" + text + $"</{lang}>";
return text;
}
@@ -221,9 +230,9 @@ namespace Supertonic
return Helper.LengthToMask(textIdsLengths);
}
public (long[][] textIds, float[][][] textMask) Call(List<string> textList)
public (long[][] textIds, float[][][] textMask) Call(List<string> textList, List<string> langList)
{
var processedTexts = textList.Select(t => PreprocessText(t)).ToList();
var processedTexts = textList.Select((t, i) => PreprocessText(t, langList[i])).ToList();
var textIdsLengths = processedTexts.Select(t => (long)t.Length).ToArray();
long maxLen = textIdsLengths.Max();
@@ -328,7 +337,7 @@ namespace Supertonic
return (noisyLatent, latentMask);
}
private (float[] wav, float[] duration) _Infer(List<string> textList, Style style, int totalStep, float speed = 1.05f)
private (float[] wav, float[] duration) _Infer(List<string> textList, List<string> langList, Style style, int totalStep, float speed = 1.05f)
{
int bsz = textList.Count;
if (bsz != style.TtlShape[0])
@@ -337,7 +346,7 @@ namespace Supertonic
}
// Process text
var (textIds, textMask) = _textProcessor.Call(textList);
var (textIds, textMask) = _textProcessor.Call(textList, langList);
var textIdsShape = new long[] { bsz, textIds[0].Length };
var textMaskShape = new long[] { bsz, 1, textMask[0][0].Length };
@@ -424,20 +433,21 @@ namespace Supertonic
return (wavTensor.ToArray(), durOnnx);
}
public (float[] wav, float[] duration) Call(string text, Style style, int totalStep, float speed = 1.05f, float silenceDuration = 0.3f)
public (float[] wav, float[] duration) Call(string text, string lang, Style style, int totalStep, float speed = 1.05f, float silenceDuration = 0.3f)
{
if (style.TtlShape[0] != 1)
{
throw new ArgumentException("Single speaker text to speech only supports single style");
}
var textList = Helper.ChunkText(text);
int maxLen = lang == "ko" ? 120 : 300;
var textList = Helper.ChunkText(text, maxLen);
var wavCat = new List<float>();
float durCat = 0.0f;
foreach (var chunk in textList)
{
var (wav, duration) = _Infer(new List<string> { chunk }, style, totalStep, speed);
var (wav, duration) = _Infer(new List<string> { chunk }, new List<string> { lang }, style, totalStep, speed);
if (wavCat.Count == 0)
{
@@ -457,9 +467,9 @@ namespace Supertonic
return (wavCat.ToArray(), new float[] { durCat });
}
public (float[] wav, float[] duration) Batch(List<string> textList, Style style, int totalStep, float speed = 1.05f)
public (float[] wav, float[] duration) Batch(List<string> textList, List<string> langList, Style style, int totalStep, float speed = 1.05f)
{
return _Infer(textList, style, totalStep, speed);
return _Infer(textList, langList, style, totalStep, speed);
}
}

12
csharp/README.md
View File

@@ -4,6 +4,8 @@ This guide provides examples for running TTS inference using `ExampleONNX.cs`.
## 📰 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)
@@ -45,15 +47,16 @@ Process multiple voice styles and texts at once:
```bash
dotnet run -- \
--voice-style assets/voice_styles/M1.json,assets/voice_styles/F1.json \
--text "The sun sets behind the mountains, painting the sky in shades of pink and orange.|The weather is beautiful and sunny outside. A gentle breeze makes the air feel fresh and pleasant." \
--text "The sun sets behind the mountains, painting the sky in shades of pink and orange.|오늘 아침에 공원을 산책했는데, 새소리와 바람 소리가 너무 좋아서 한참을 멈춰 서서 들었어요." \
--lang en,ko \
--batch
```
This will:
- Use `--batch` flag to enable batch processing mode
- Generate speech for 2 different voice-text pairs
- Use male voice style (M1.json) for the first text
- Use female voice style (F1.json) for the second text
- Use male voice style (M1.json) for the first English text
- Use female voice style (F1.json) for the second Korean text
- Process both samples in a single batch (automatic text chunking disabled)
### Example 3: High Quality Inference
@@ -92,15 +95,18 @@ This will:
| `--use-gpu` | flag | False | Use GPU for inference (not supported yet) |
| `--onnx-dir` | str | `assets/onnx` | Path to ONNX model directory |
| `--total-step` | int | 5 | Number of denoising steps (higher = better quality, slower) |
| `--speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
| `--n-test` | int | 4 | Number of times to generate each sample |
| `--voice-style` | str+ | `assets/voice_styles/M1.json` | Voice style file path(s) (comma-separated) |
| `--text` | str+ | (long default text) | Text(s) to synthesize (pipe-separated: `|`) |
| `--lang` | str+ | `en` | Language(s) for text(s): `en`, `ko`, `es`, `pt`, `fr` (comma-separated) |
| `--save-dir` | str | `results` | Output directory |
| `--batch` | flag | False | Enable batch mode (disables automatic text chunking) |
## Notes
- **Batch Processing**: The number of `--voice-style` files must match the number of `--text` entries
- **Multilingual Support**: Use `--lang` to specify language(s). Available: `en` (English), `ko` (Korean), `es` (Spanish), `pt` (Portuguese), `fr` (French)
- **Long-Form Inference**: Without `--batch` flag, long texts are automatically chunked and combined into a single audio file with natural pauses
- **Quality vs Speed**: Higher `--total-step` values produce better quality but take longer
- **GPU Support**: GPU mode is not supported yet