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

54
java/ExampleONNX.java
View File

@@ -21,6 +21,7 @@ public class ExampleONNX {
"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."
);
String saveDir = "results";
boolean batch = false;
}
/**
@@ -56,6 +57,9 @@ public class ExampleONNX {
case "--save-dir":
if (i + 1 < args.length) result.saveDir = args[++i];
break;
case "--batch":
result.batch = true;
break;
}
}
@@ -76,10 +80,13 @@ public class ExampleONNX {
String saveDir = parsedArgs.saveDir;
List<String> voiceStylePaths = parsedArgs.voiceStyle;
List<String> textList = parsedArgs.text;
boolean batch = parsedArgs.batch;
if (voiceStylePaths.size() != textList.size()) {
throw new RuntimeException("Number of voice styles (" + voiceStylePaths.size() +
") must match number of texts (" + textList.size() + ")");
if (batch) {
if (voiceStylePaths.size() != textList.size()) {
throw new RuntimeException("Number of voice styles (" + voiceStylePaths.size() +
") must match number of texts (" + textList.size() + ")");
}
}
int bsz = voiceStylePaths.size();
@@ -100,25 +107,44 @@ public class ExampleONNX {
for (int n = 0; n < nTest; n++) {
System.out.println("\n[" + (n + 1) + "/" + nTest + "] Starting synthesis...");
TTSResult ttsResult = Helper.timer("Generating speech from text", () -> {
try {
return textToSpeech.call(textList, style, totalStep, env);
} catch (Exception e) {
throw new RuntimeException(e);
}
});
TTSResult ttsResult;
if (batch) {
ttsResult = Helper.timer("Generating speech from text", () -> {
try {
return textToSpeech.batch(textList, style, totalStep, env);
} catch (Exception e) {
throw new RuntimeException(e);
}
});
} else {
ttsResult = Helper.timer("Generating speech from text", () -> {
try {
return textToSpeech.call(textList.get(0), style, totalStep, 0.3f, env);
} catch (Exception e) {
throw new RuntimeException(e);
}
});
}
float[] wav = ttsResult.wav;
float[] duration = ttsResult.duration;
// Save outputs
int wavLen = wav.length / bsz;
for (int i = 0; i < bsz; i++) {
String fname = Helper.sanitizeFilename(textList.get(i), 20) + "_" + (n + 1) + ".wav";
int actualLen = (int) (textToSpeech.sampleRate * duration[i]);
float[] wavOut;
float[] wavOut = new float[actualLen];
System.arraycopy(wav, i * wavLen, wavOut, 0, Math.min(actualLen, wavLen));
if (batch) {
int wavLen = wav.length / bsz;
int actualLen = (int) (textToSpeech.sampleRate * duration[i]);
wavOut = new float[actualLen];
System.arraycopy(wav, i * wavLen, wavOut, 0, Math.min(actualLen, wavLen));
} else {
// For non-batch mode, wav is a single concatenated audio
int actualLen = (int) (textToSpeech.sampleRate * duration[0]);
wavOut = new float[Math.min(actualLen, wav.length)];
System.arraycopy(wav, 0, wavOut, 0, wavOut.length);
}
String outputPath = saveDir + "/" + fname;
Helper.writeWavFile(outputPath, wavOut, textToSpeech.sampleRate);

205
java/Helper.java
View File

@@ -15,6 +15,8 @@ import java.nio.file.Files;
import java.nio.file.Paths;
import java.text.Normalizer;
import java.util.*;
import java.util.regex.Pattern;
import java.util.regex.Matcher;
/**
* Configuration classes
@@ -152,7 +154,7 @@ class TextToSpeech {
this.ldim = config.ttl.latentDim;
}
public TTSResult call(List<String> textList, Style style, int totalStep, OrtEnvironment env)
private TTSResult _infer(List<String> textList, Style style, int totalStep, OrtEnvironment env)
throws OrtException {
int bsz = textList.size();
@@ -296,6 +298,57 @@ class TextToSpeech {
return new NoisyLatentResult(noisyLatent, latentMask);
}
/**
* Synthesize speech from a single text with automatic chunking
*/
public TTSResult call(String text, Style style, int totalStep, float silenceDuration, OrtEnvironment env)
throws OrtException {
List<String> chunks = Helper.chunkText(text, 0);
List<Float> wavCat = new ArrayList<>();
float durCat = 0.0f;
for (int i = 0; i < chunks.size(); i++) {
TTSResult result = _infer(Arrays.asList(chunks.get(i)), style, totalStep, env);
float dur = result.duration[0];
int wavLen = (int) (sampleRate * dur);
float[] wavChunk = new float[wavLen];
System.arraycopy(result.wav, 0, wavChunk, 0, Math.min(wavLen, result.wav.length));
if (i == 0) {
for (float val : wavChunk) {
wavCat.add(val);
}
durCat = dur;
} else {
int silenceLen = (int) (silenceDuration * sampleRate);
for (int j = 0; j < silenceLen; j++) {
wavCat.add(0.0f);
}
for (float val : wavChunk) {
wavCat.add(val);
}
durCat += silenceDuration + dur;
}
}
float[] wavArray = new float[wavCat.size()];
for (int i = 0; i < wavCat.size(); i++) {
wavArray[i] = wavCat.get(i);
}
return new TTSResult(wavArray, new float[]{durCat});
}
/**
* Batch synthesize speech from multiple texts
*/
public TTSResult batch(List<String> textList, Style style, int totalStep, OrtEnvironment env)
throws OrtException {
return _infer(textList, style, totalStep, env);
}
public void close() throws OrtException {
if (dpSession != null) dpSession.close();
if (textEncSession != null) textEncSession.close();
@@ -353,6 +406,156 @@ class NoisyLatentResult {
*/
public class Helper {
private static final int MAX_CHUNK_LENGTH = 300;
private static final String[] ABBREVIATIONS = {
"Dr.", "Mr.", "Mrs.", "Ms.", "Prof.", "Sr.", "Jr.",
"St.", "Ave.", "Rd.", "Blvd.", "Dept.", "Inc.", "Ltd.",
"Co.", "Corp.", "etc.", "vs.", "i.e.", "e.g.", "Ph.D."
};
/**
* Chunk text into smaller segments based on paragraphs and sentences
*/
public static List<String> chunkText(String text, int maxLen) {
if (maxLen == 0) {
maxLen = MAX_CHUNK_LENGTH;
}
text = text.trim();
if (text.isEmpty()) {
return Arrays.asList("");
}
// Split by paragraphs
String[] paragraphs = text.split("\\n\\s*\\n");
List<String> chunks = new ArrayList<>();
for (String para : paragraphs) {
para = para.trim();
if (para.isEmpty()) {
continue;
}
if (para.length() <= maxLen) {
chunks.add(para);
continue;
}
// Split by sentences
List<String> sentences = splitSentences(para);
StringBuilder current = new StringBuilder();
int currentLen = 0;
for (String sentence : sentences) {
sentence = sentence.trim();
if (sentence.isEmpty()) {
continue;
}
int sentenceLen = sentence.length();
if (sentenceLen > maxLen) {
// If sentence is longer than maxLen, split by comma or space
if (current.length() > 0) {
chunks.add(current.toString().trim());
current.setLength(0);
currentLen = 0;
}
// Try splitting by comma
String[] parts = sentence.split(",");
for (String part : parts) {
part = part.trim();
if (part.isEmpty()) {
continue;
}
int partLen = part.length();
if (partLen > maxLen) {
// Split by space as last resort
String[] words = part.split("\\s+");
StringBuilder wordChunk = new StringBuilder();
int wordChunkLen = 0;
for (String word : words) {
int wordLen = word.length();
if (wordChunkLen + wordLen + 1 > maxLen && wordChunk.length() > 0) {
chunks.add(wordChunk.toString().trim());
wordChunk.setLength(0);
wordChunkLen = 0;
}
if (wordChunk.length() > 0) {
wordChunk.append(" ");
wordChunkLen++;
}
wordChunk.append(word);
wordChunkLen += wordLen;
}
if (wordChunk.length() > 0) {
chunks.add(wordChunk.toString().trim());
}
} else {
if (currentLen + partLen + 1 > maxLen && current.length() > 0) {
chunks.add(current.toString().trim());
current.setLength(0);
currentLen = 0;
}
if (current.length() > 0) {
current.append(", ");
currentLen += 2;
}
current.append(part);
currentLen += partLen;
}
}
continue;
}
if (currentLen + sentenceLen + 1 > maxLen && current.length() > 0) {
chunks.add(current.toString().trim());
current.setLength(0);
currentLen = 0;
}
if (current.length() > 0) {
current.append(" ");
currentLen++;
}
current.append(sentence);
currentLen += sentenceLen;
}
if (current.length() > 0) {
chunks.add(current.toString().trim());
}
}
if (chunks.isEmpty()) {
return Arrays.asList("");
}
return chunks;
}
/**
* Split text into sentences, avoiding common abbreviations
*/
private static List<String> splitSentences(String text) {
// Build pattern that avoids abbreviations
StringBuilder abbrevPattern = new StringBuilder();
for (int i = 0; i < ABBREVIATIONS.length; i++) {
if (i > 0) abbrevPattern.append("|");
abbrevPattern.append(Pattern.quote(ABBREVIATIONS[i]));
}
// Match sentence endings, but not abbreviations
String patternStr = "(?<!(?:" + abbrevPattern.toString() + "))(?<=[.!?])\\s+";
Pattern pattern = Pattern.compile(patternStr);
return Arrays.asList(pattern.split(text));
}
/**
* Load voice style from JSON files
*/

27
java/README.md
View File

@@ -2,6 +2,10 @@
This guide provides examples for running TTS inference using `ExampleONNX.java`.
## 📰 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
This project uses [Maven](https://maven.apache.org/) for dependency management.
@@ -35,7 +39,7 @@ This will use:
### Example 2: Batch Inference
Process multiple voice styles and texts at once:
```bash
mvn exec:java -Dexec.args="--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.'"
mvn exec:java -Dexec.args="--batch --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.'"
```
This will:
@@ -54,7 +58,22 @@ This will:
- Use 10 denoising steps instead of the default 5
- Produce higher quality output at the cost of slower inference
**Note**: If your text contains apostrophes, use escaping or run the JAR directly:
### Example 4: Long-Form Inference
The system automatically chunks long texts into manageable segments, synthesizes each segment separately, and concatenates them with natural pauses (0.3 seconds by default) into a single audio file. This happens by default when you don't use the `--batch` flag:
```bash
mvn exec:java -Dexec.args="--voice-style assets/voice_styles/M1.json --text 'This is a very long text that will be automatically split into multiple chunks. The system will process each chunk separately and then concatenate them together with natural pauses between segments. This ensures that even very long texts can be processed efficiently while maintaining natural speech flow and avoiding memory issues.'"
```
This will:
- Automatically split the text into chunks based on paragraph and sentence boundaries
- Synthesize each chunk separately
- Add 0.3 seconds of silence between chunks for natural pauses
- Concatenate all chunks into a single audio file
**Note**: Automatic text chunking is disabled when using `--batch` mode. In batch mode, each text is processed as-is without chunking.
**Tip**: If your text contains apostrophes, use escaping or run the JAR directly:
```bash
java -jar target/tts-example.jar --total-step 10 --text "Text with apostrophe's here"
```
@@ -87,10 +106,12 @@ java -jar target/tts-example.jar --total-step 10 --text "Your custom text here"
| `--voice-style` | str+ | `assets/voice_styles/M1.json` | Voice style file path(s) |
| `--text` | str+ | (long default text) | Text(s) to synthesize |
| `--save-dir` | str | `results` | Output directory |
| `--batch` | flag | False | Enable batch mode (multiple text-style pairs, disables automatic chunking) |
## Notes
- **Batch Processing**: The number of `--voice-style` files must match the number of `--text` entries
- **Batch Processing**: When using `--batch`, the number of `--voice-style` files must match the number of `--text` entries
- **Automatic Chunking**: Without `--batch`, long texts are automatically split and concatenated with 0.3s pauses
- **Quality vs Speed**: Higher `--total-step` values produce better quality but take longer
- **GPU Support**: GPU mode is not supported yet
- **Voice Styles**: Uses pre-extracted voice style JSON files for fast inference