add speed parameter

java/ExampleONNX.java

@@ -15,6 +15,7 @@ public class ExampleONNX {
         boolean useGpu = false;
         String onnxDir = "assets/onnx";
         int totalStep = 5;
+        float speed = 1.05f;
         int nTest = 4;
         List<String> voiceStyle = Arrays.asList("assets/voice_styles/M1.json");
         List<String> text = Arrays.asList(
@@ -41,6 +42,9 @@ public class ExampleONNX {
                 case "--total-step":
                     if (i + 1 < args.length) result.totalStep = Integer.parseInt(args[++i]);
                     break;
+                case "--speed":
+                    if (i + 1 < args.length) result.speed = Float.parseFloat(args[++i]);
+                    break;
                 case "--n-test":
                     if (i + 1 < args.length) result.nTest = Integer.parseInt(args[++i]);
                     break;
@@ -76,6 +80,7 @@ public class ExampleONNX {
             // --- 1. Parse arguments --- //
             Args parsedArgs = parseArgs(args);
             int totalStep = parsedArgs.totalStep;
+            float speed = parsedArgs.speed;
             int nTest = parsedArgs.nTest;
             String saveDir = parsedArgs.saveDir;
             List<String> voiceStylePaths = parsedArgs.voiceStyle;
@@ -111,7 +116,7 @@ public class ExampleONNX {
                 if (batch) {
                     ttsResult = Helper.timer("Generating speech from text", () -> {
                         try {
-                            return textToSpeech.batch(textList, style, totalStep, env);
+                            return textToSpeech.batch(textList, style, totalStep, speed, env);
                         } catch (Exception e) {
                             throw new RuntimeException(e);
                         }
@@ -119,7 +124,7 @@ public class ExampleONNX {
                 } else {
                     ttsResult = Helper.timer("Generating speech from text", () -> {
                         try {
-                            return textToSpeech.call(textList.get(0), style, totalStep, 0.3f, env);
+                            return textToSpeech.call(textList.get(0), style, totalStep, speed, 0.3f, env);
                         } catch (Exception e) {
                             throw new RuntimeException(e);
                         }

java/Helper.java

@@ -154,7 +154,7 @@ class TextToSpeech {
         this.ldim = config.ttl.latentDim;
     }
     
-    private TTSResult _infer(List<String> textList, Style style, int totalStep, OrtEnvironment env) 
+    private TTSResult _infer(List<String> textList, Style style, int totalStep, float speed, OrtEnvironment env) 
             throws OrtException {
         int bsz = textList.size();
         
@@ -182,6 +182,11 @@ class TextToSpeech {
             duration = (float[]) dpValue;
         }
         
+        // Apply speed factor to duration
+        for (int i = 0; i < duration.length; i++) {
+            duration[i] /= speed;
+        }
+        
         // Encode text
         Map<String, OnnxTensor> textEncInputs = new HashMap<>();
         textEncInputs.put("text_ids", textIdsTensor);
@@ -301,7 +306,7 @@ class TextToSpeech {
     /**
      * Synthesize speech from a single text with automatic chunking
      */
-    public TTSResult call(String text, Style style, int totalStep, float silenceDuration, OrtEnvironment env) 
+    public TTSResult call(String text, Style style, int totalStep, float speed, float silenceDuration, OrtEnvironment env) 
             throws OrtException {
         List<String> chunks = Helper.chunkText(text, 0);
         
@@ -309,7 +314,7 @@ class TextToSpeech {
         float durCat = 0.0f;
         
         for (int i = 0; i < chunks.size(); i++) {
-            TTSResult result = _infer(Arrays.asList(chunks.get(i)), style, totalStep, env);
+            TTSResult result = _infer(Arrays.asList(chunks.get(i)), style, totalStep, speed, env);
             
             float dur = result.duration[0];
             int wavLen = (int) (sampleRate * dur);
@@ -344,9 +349,9 @@ class TextToSpeech {
     /**
      * Batch synthesize speech from multiple texts
      */
-    public TTSResult batch(List<String> textList, Style style, int totalStep, OrtEnvironment env) 
+    public TTSResult batch(List<String> textList, Style style, int totalStep, float speed, OrtEnvironment env) 
             throws OrtException {
-        return _infer(textList, style, totalStep, env);
+        return _infer(textList, style, totalStep, speed, env);
     }
     
     public void close() throws OrtException {

java/README.md

@@ -4,6 +4,8 @@ This guide provides examples for running TTS inference using `ExampleONNX.java`.
 
 ## 📰 Update News
 
+**2025.11.19** - Added `--speed` parameter to control speech synthesis speed (default: 1.05, recommended range: 0.9-1.5).
+
 **2025.11.19** - Added automatic text chunking for long-form inference. Long texts are split into chunks and synthesized with natural pauses.
 
 ## Installation