65 lines
2.5 KiB
Java
65 lines
2.5 KiB
Java
// Copyright 2025 Xiaomi Corporation
|
|
|
|
// This file shows how to use a Kokoro multi-lingual model
|
|
// to convert Chinese and English text to speech
|
|
import com.k2fsa.sherpa.onnx.*;
|
|
|
|
public class NonStreamingTtsKokoroZhEn {
|
|
public static void main(String[] args) {
|
|
// please visit
|
|
// https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/kokoro.html
|
|
// to download model files
|
|
String model = "./kokoro-multi-lang-v1_0/model.onnx";
|
|
String voices = "./kokoro-multi-lang-v1_0/voices.bin";
|
|
String tokens = "./kokoro-multi-lang-v1_0/tokens.txt";
|
|
String dataDir = "./kokoro-multi-lang-v1_0/espeak-ng-data";
|
|
String dictDir = "./kokoro-multi-lang-v1_0/dict";
|
|
String lexicon =
|
|
"./kokoro-multi-lang-v1_0/lexicon-us-en.txt,./kokoro-multi-lang-v1_0/lexicon-zh.txt";
|
|
String text =
|
|
"中英文语音合成测试。This is generated by next generation Kaldi using Kokoro without Misaki."
|
|
+ " 你觉得中英文说的如何呢？";
|
|
|
|
OfflineTtsKokoroModelConfig kokoroModelConfig =
|
|
OfflineTtsKokoroModelConfig.builder()
|
|
.setModel(model)
|
|
.setVoices(voices)
|
|
.setTokens(tokens)
|
|
.setDataDir(dataDir)
|
|
.setDictDir(dictDir)
|
|
.setLexicon(lexicon)
|
|
.build();
|
|
|
|
OfflineTtsModelConfig modelConfig =
|
|
OfflineTtsModelConfig.builder()
|
|
.setKokoro(kokoroModelConfig)
|
|
.setNumThreads(2)
|
|
.setDebug(true)
|
|
.build();
|
|
|
|
OfflineTtsConfig config = OfflineTtsConfig.builder().setModel(modelConfig).build();
|
|
OfflineTts tts = new OfflineTts(config);
|
|
|
|
int sid = 0; // this model has 53 speakers. You can use sid in the range 0-52
|
|
float speed = 1.0f;
|
|
long start = System.currentTimeMillis();
|
|
GeneratedAudio audio = tts.generate(text, sid, speed);
|
|
long stop = System.currentTimeMillis();
|
|
|
|
float timeElapsedSeconds = (stop - start) / 1000.0f;
|
|
|
|
float audioDuration = audio.getSamples().length / (float) audio.getSampleRate();
|
|
float real_time_factor = timeElapsedSeconds / audioDuration;
|
|
|
|
String waveFilename = "tts-kokoro-zh-en.wav";
|
|
audio.save(waveFilename);
|
|
System.out.printf("-- elapsed : %.3f seconds\n", timeElapsedSeconds);
|
|
System.out.printf("-- audio duration: %.3f seconds\n", timeElapsedSeconds);
|
|
System.out.printf("-- real-time factor (RTF): %.3f\n", real_time_factor);
|
|
System.out.printf("-- text: %s\n", text);
|
|
System.out.printf("-- Saved to %s\n", waveFilename);
|
|
|
|
tts.release();
|
|
}
|
|
}
|