mirror of
https://github.com/k2-fsa/sherpa-onnx.git
synced 2026-11-10 13:04:05 +08:00
Fixes #3731 espeak-ng and piper-phonemize are no longer built into sherpa-onnx. Text frontends are now: - **lexicon** — built in, no extra dependency - **phonemize** — phonemize outside sherpa-onnx (e.g. [piper-phonemize](https://github.com/csukuangfj/piper-phonemize)) and pass the result in. That library is GPL, so it stays optional: sherpa-onnx is GPL-free after this PR. ## API - `SherpaOnnxGenerationConfig` gains `phoneme_codepoints` and `tokens` (mutually exclusive alternatives to `text`) - `data_dir` on the TTS model configs is deprecated and ignored; the ABI slot is kept - all bindings updated: C/C++, Python, Java, Kotlin, Go, Rust, C#, Swift, Pascal, Dart/Flutter, node-addon, WASM, HarmonyOS
48 lines
1.7 KiB
JavaScript
48 lines
1.7 KiB
JavaScript
// Copyright (c) 2025 Xiaomi Corporation (authors: Fangjun Kuang)
|
|
|
|
const sherpa_onnx = require('sherpa-onnx');
|
|
|
|
const silenceScale = 0.2;
|
|
|
|
function createOfflineTts() {
|
|
let offlineTtsMatchaModelConfig = {
|
|
acousticModel: './matcha-icefall-zh-baker/model-steps-3.onnx',
|
|
vocoder: './vocos-22khz-univ.onnx',
|
|
lexicon: './matcha-icefall-zh-baker/lexicon.txt',
|
|
tokens: './matcha-icefall-zh-baker/tokens.txt',
|
|
noiseScale: 0.667,
|
|
lengthScale: 1.0,
|
|
};
|
|
let offlineTtsModelConfig = {
|
|
offlineTtsMatchaModelConfig: offlineTtsMatchaModelConfig,
|
|
numThreads: 1,
|
|
debug: 1,
|
|
provider: 'cpu',
|
|
};
|
|
|
|
let offlineTtsConfig = {
|
|
offlineTtsModelConfig: offlineTtsModelConfig,
|
|
maxNumSentences: 1,
|
|
silenceScale: silenceScale,
|
|
ruleFsts:
|
|
'./matcha-icefall-zh-baker/phone.fst,./matcha-icefall-zh-baker/date.fst,./matcha-icefall-zh-baker/number.fst',
|
|
};
|
|
|
|
return sherpa_onnx.createOfflineTts(offlineTtsConfig);
|
|
}
|
|
|
|
const tts = createOfflineTts();
|
|
const text =
|
|
'当夜幕降临,星光点点,伴随着微风拂面,我在静谧中感受着时光的流转,思念如涟漪荡漾,梦境如画卷展开,我与自然融为一体,沉静在这片宁静的美丽之中,感受着生命的奇迹与温柔. 某某银行的副行长和一些行政领导表示,他们去过长江和长白山; 经济不断增长。2024年12月31号,拨打110或者18920240511。123456块钱。';
|
|
|
|
const generationConfig = {
|
|
sid: 0,
|
|
speed: 1.0,
|
|
silenceScale: silenceScale,
|
|
};
|
|
|
|
const audio = tts.generateWithConfig(text, generationConfig);
|
|
tts.save('./test-matcha-zh-lexicon.wav', audio);
|
|
console.log('Saved to test-matcha-zh-lexicon.wav successfully.');
|
|
tts.free();
|