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

28
nodejs/README.md
View File

@@ -2,6 +2,10 @@
Node.js implementation for TTS inference. Uses ONNX Runtime to generate speech from text.
## 📰 Update News
**2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
## Requirements
- Node.js v16 or higher
@@ -39,14 +43,16 @@ Process multiple voice styles and texts at once:
```bash
node example_onnx.js \
--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:
@@ -61,6 +67,22 @@ 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
node example_onnx.js \
--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 |
@@ -72,10 +94,12 @@ This will:
| `--voice-style` | str+ | `assets/voice_styles/M1.json` | Voice style file path(s). Separate multiple files with commas |
| `--text` | str+ | (long default text) | Text(s) to synthesize. Separate multiple texts with pipes |
| `--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 texts. Use commas to separate files and pipes to separate texts
- **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

13
nodejs/example_onnx.js
View File

@@ -18,13 +18,16 @@ function parseArgs() {
nTest: 4,
voiceStyle: ['assets/voice_styles/M1.json'],
text: ['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.'],
saveDir: 'results'
saveDir: 'results',
batch: false
};
for (let i = 2; i < process.argv.length; i++) {
const arg = process.argv[i];
if (arg === '--use-gpu') {
args.useGpu = true;
} else if (arg === '--batch') {
args.batch = true;
} else if (arg === '--onnx-dir' && i + 1 < process.argv.length) {
args.onnxDir = process.argv[++i];
} else if (arg === '--total-step' && i + 1 < process.argv.length) {
@@ -56,11 +59,11 @@ async function main() {
const saveDir = args.saveDir;
const voiceStylePaths = args.voiceStyle.map(p => path.resolve(__dirname, p));
const textList = args.text;
const batch = args.batch;
if (voiceStylePaths.length !== textList.length) {
throw new Error(`Number of voice styles (${voiceStylePaths.length}) must match number of texts (${textList.length})`);
}
const bsz = voiceStylePaths.length;
// --- 2. Load Text to Speech --- //
@@ -75,7 +78,11 @@ async function main() {
console.log(`\n[${n + 1}/${nTest}] Starting synthesis...`);
const { wav, duration } = await timer('Generating speech from text', async () => {
return await textToSpeech.call(textList, style, totalStep);
if (batch) {
return await textToSpeech.batch(textList, style, totalStep);
} else {
return await textToSpeech.call(textList[0], style, totalStep);
}
});
if (!fs.existsSync(saveDir)) {

73
nodejs/helper.js
View File

@@ -114,7 +114,7 @@ class TextToSpeech {
return { noisyLatent, latentMask };
}
async call(textList, style, totalStep) {
async _infer(textList, style, totalStep) {
if (textList.length !== style.ttl.dims[0]) {
throw new Error('Number of texts must match number of style vectors');
}
@@ -184,6 +184,35 @@ class TextToSpeech {
const wav = Array.from(vocoderResult.wav_tts.data);
return { wav, duration: durOnnx };
}
async call(text, style, totalStep, silenceDuration = 0.3) {
if (style.ttl.dims[0] !== 1) {
throw new Error('Single speaker text to speech only supports single style');
}
const textList = chunkText(text);
let wavCat = null;
let durCat = 0;
for (const chunk of textList) {
const { wav, duration } = await this._infer([chunk], style, totalStep);
if (wavCat === null) {
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) {
return await this._infer(textList, style, totalStep);
}
}
/**
@@ -390,3 +419,45 @@ export async function timer(name, fn) {
console.log(` -> ${name} completed in ${elapsed} sec`);
return result;
}
/**
* 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;
}