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

add text chunking for long-form generation (Fixes #4)

Browse Source
This commit is contained in:
ANLGBOY
2025-11-19 18:08:30 +09:00
parent d31536d9fc
commit c31b6745e4
30 changed files with 1813 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
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 string SaveDir { get; set; } = "results";
public bool Batch { get; set; } = false;
}
static Args ParseArgs(string[] args)
@@ -32,6 +33,9 @@ namespace Supertonic
case "--use-gpu":
result.UseGpu = true;
break;
case "--batch":
result.Batch = true;
break;
case "--onnx-dir" when i + 1 < args.Length:
result.OnnxDir = args[++i];
break;
@@ -67,13 +71,13 @@ namespace Supertonic
string saveDir = parsedArgs.SaveDir;
var voiceStylePaths = parsedArgs.VoiceStyle;
var textList = parsedArgs.Text;
bool batch = parsedArgs.Batch;
if (voiceStylePaths.Count != textList.Count)
{
throw new ArgumentException(
$"Number of voice styles ({voiceStylePaths.Count}) must match number of texts ({textList.Count})");
}
int bsz = voiceStylePaths.Count;
// --- 2. Load Text to Speech --- //
@@ -88,9 +92,17 @@ namespace Supertonic
{
Console.WriteLine($"\n[{n + 1}/{nTest}] Starting synthesis...");
var (wav, duration) = Helper.Timer("Generating speech from text", () =>
textToSpeech.Call(textList, style, totalStep)
);
var (wav, duration) = Helper.Timer("Generating speech from text", () =>
{
if (batch)
{
return textToSpeech.Batch(textList, style, totalStep);
}
else
{
return textToSpeech.Call(textList[0], style, totalStep);
}
});
if (!Directory.Exists(saveDir))
{

101
csharp/Helper.cs
View File

@@ -4,6 +4,7 @@ using System.IO;
using System.Linq;
using System.Text;
using System.Text.Json;
using System.Text.RegularExpressions;
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
@@ -193,7 +194,7 @@ namespace Supertonic
return (noisyLatent, latentMask);
}
public (float[] wav, float[] duration) Call(List<string> textList, Style style, int totalStep)
private (float[] wav, float[] duration) _Infer(List<string> textList, Style style, int totalStep)
{
int bsz = textList.Count;
if (bsz != style.TtlShape[0])
@@ -282,6 +283,44 @@ namespace Supertonic
return (wavTensor.ToArray(), durOnnx);
}
public (float[] wav, float[] duration) Call(string text, Style style, int totalStep, 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);
var wavCat = new List<float>();
float durCat = 0.0f;
foreach (var chunk in textList)
{
var (wav, duration) = _Infer(new List<string> { chunk }, style, totalStep);
if (wavCat.Count == 0)
{
wavCat.AddRange(wav);
durCat = duration[0];
}
else
{
int silenceLen = (int)(silenceDuration * SampleRate);
var silence = new float[silenceLen];
wavCat.AddRange(silence);
wavCat.AddRange(wav);
durCat += duration[0] + silenceDuration;
}
}
return (wavCat.ToArray(), new float[] { durCat });
}
public (float[] wav, float[] duration) Batch(List<string> textList, Style style, int totalStep)
{
return _Infer(textList, style, totalStep);
}
}
// ============================================================================
@@ -608,5 +647,65 @@ namespace Supertonic
}
return result.ToString();
}
// ============================================================================
// Chunk text
// ============================================================================
public static List<string> ChunkText(string text, int maxLen = 300)
{
var chunks = new List<string>();
// Split by paragraph (two or more newlines)
var paragraphRegex = new Regex(@"\n\s*\n+");
var paragraphs = paragraphRegex.Split(text.Trim())
.Select(p => p.Trim())
.Where(p => !string.IsNullOrEmpty(p))
.ToList();
// Split by sentence boundaries, excluding abbreviations
var sentenceRegex = new Regex(@"(?<!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+");
foreach (var paragraph in paragraphs)
{
var sentences = sentenceRegex.Split(paragraph);
string currentChunk = "";
foreach (var sentence in sentences)
{
if (string.IsNullOrEmpty(sentence)) continue;
if (currentChunk.Length + sentence.Length + 1 <= maxLen)
{
if (!string.IsNullOrEmpty(currentChunk))
{
currentChunk += " ";
}
currentChunk += sentence;
}
else
{
if (!string.IsNullOrEmpty(currentChunk))
{
chunks.Add(currentChunk.Trim());
}
currentChunk = sentence;
}
}
if (!string.IsNullOrEmpty(currentChunk))
{
chunks.Add(currentChunk.Trim());
}
}
// If no chunks were created, return the original text
if (chunks.Count == 0)
{
chunks.Add(text.Trim());
}
return chunks;
}
}
}

28
csharp/README.md
View File

@@ -2,6 +2,10 @@
This guide provides examples for running TTS inference using `ExampleONNX.cs`.
## 📰 Update News
**2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
## Installation
### Prerequisites
@@ -33,14 +37,16 @@ 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.|The weather is beautiful and sunny outside. A gentle breeze makes the air feel fresh and pleasant." \
--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
- Process both samples in a single batch
- Process both samples in a single batch (automatic text chunking disabled)
### Example 3: High Quality Inference
Increase denoising steps for better quality:
@@ -55,6 +61,22 @@ This will:
- Use 10 denoising steps instead of the default 5
- Produce higher quality output at the cost of slower inference
### Example 4: Long-Form Inference
For long texts, the system automatically chunks the text into manageable segments and generates a single audio file:
```bash
dotnet run -- \
--voice-style assets/voice_styles/M1.json \
--text "Once upon a time, in a small village nestled between rolling hills, there lived a young artist named Clara. Every morning, she would wake up before dawn to capture the first light of day. The golden rays streaming through her window inspired countless paintings. Her work was known throughout the region for its vibrant colors and emotional depth. People from far and wide came to see her gallery, and many said her paintings could tell stories that words never could."
```
This will:
- Automatically split the long text into smaller chunks (max 300 characters by default)
- Process each chunk separately while maintaining natural speech flow
- Insert brief silences (0.3 seconds) between chunks for natural pacing
- Combine all chunks into a single output audio file
**Note**: When using batch mode (`--batch`), automatic text chunking is disabled. Use non-batch mode for long-form text synthesis.
## Available Arguments
| Argument | Type | Default | Description |
@@ -66,10 +88,12 @@ This will:
| `--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: `|`) |
| `--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
- **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