48 lines
1.3 KiB
JavaScript
48 lines
1.3 KiB
JavaScript
// Copyright (c) 2024 Xiaomi Corporation
|
|
const sherpa_onnx = require('sherpa-onnx-node');
|
|
|
|
// please download model files from
|
|
// https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
|
|
function createOfflineTts() {
|
|
const config = {
|
|
model: {
|
|
vits: {
|
|
model: './vits-coqui-de-css10/model.onnx',
|
|
tokens: './vits-coqui-de-css10/tokens.txt',
|
|
},
|
|
debug: true,
|
|
numThreads: 1,
|
|
provider: 'cpu',
|
|
},
|
|
maxNumSentences: 1,
|
|
};
|
|
return new sherpa_onnx.OfflineTts(config);
|
|
}
|
|
|
|
const tts = createOfflineTts();
|
|
|
|
const text = 'Alles hat ein Ende, nur die Wurst hat zwei.'
|
|
|
|
let start = Date.now();
|
|
const audio = tts.generate({
|
|
text: text,
|
|
sid: 0,
|
|
speed: 1.0,
|
|
enableExternalBuffer: true,
|
|
});
|
|
let stop = Date.now();
|
|
const elapsed_seconds = (stop - start) / 1000;
|
|
const duration = audio.samples.length / audio.sampleRate;
|
|
const real_time_factor = elapsed_seconds / duration;
|
|
console.log('Wave duration', duration.toFixed(3), 'seconds')
|
|
console.log('Elapsed', elapsed_seconds.toFixed(3), 'seconds')
|
|
console.log(
|
|
`RTF = ${elapsed_seconds.toFixed(3)}/${duration.toFixed(3)} =`,
|
|
real_time_factor.toFixed(3))
|
|
|
|
const filename = 'test-coqui-de.wav';
|
|
sherpa_onnx.writeWave(
|
|
filename, {samples: audio.samples, sampleRate: audio.sampleRate});
|
|
|
|
console.log(`Saved to ${filename}`);
|