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

add speed parameter

Browse Source
This commit is contained in:
ANLGBOY
2025-11-19 19:42:24 +09:00
parent c31b6745e4
commit 8518b839c1
30 changed files with 246 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
java/Helper.java
View File

@@ -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 {