101 lines
2.6 KiB
JavaScript
101 lines
2.6 KiB
JavaScript
// Copyright (c) 2023-2024 Xiaomi Corporation (authors: Fangjun Kuang)
|
|
//
|
|
const fs = require('fs');
|
|
const {Readable} = require('stream');
|
|
const wav = require('wav');
|
|
|
|
const sherpa_onnx = require('sherpa-onnx');
|
|
|
|
function createOfflineRecognizer() {
|
|
let featConfig = {
|
|
sampleRate: 16000,
|
|
featureDim: 80,
|
|
};
|
|
|
|
let modelConfig = {
|
|
nemoCtc: {
|
|
model: './sherpa-onnx-nemo-ctc-en-conformer-small/model.int8.onnx',
|
|
},
|
|
tokens: './sherpa-onnx-nemo-ctc-en-conformer-small/tokens.txt',
|
|
numThreads: 1,
|
|
debug: 0,
|
|
provider: 'cpu',
|
|
modelType: 'nemo_ctc',
|
|
};
|
|
|
|
let config = {
|
|
featConfig: featConfig,
|
|
modelConfig: modelConfig,
|
|
decodingMethod: 'greedy_search',
|
|
maxActivePaths: 4,
|
|
};
|
|
|
|
return sherpa_onnx.createOfflineRecognizer(config);
|
|
}
|
|
|
|
const recognizer = createOfflineRecognizer();
|
|
const stream = recognizer.createStream();
|
|
|
|
const waveFilename =
|
|
'./sherpa-onnx-nemo-ctc-en-conformer-small/test_wavs/0.wav';
|
|
|
|
const reader = new wav.Reader();
|
|
const readable = new Readable().wrap(reader);
|
|
const buf = [];
|
|
|
|
reader.on('format', ({audioFormat, bitDepth, channels, sampleRate}) => {
|
|
if (sampleRate != recognizer.config.featConfig.sampleRate) {
|
|
throw new Error(`Only support sampleRate ${
|
|
recognizer.config.featConfig.sampleRate}. Given ${sampleRate}`);
|
|
}
|
|
|
|
if (audioFormat != 1) {
|
|
throw new Error(`Only support PCM format. Given ${audioFormat}`);
|
|
}
|
|
|
|
if (channels != 1) {
|
|
throw new Error(`Only a single channel. Given ${channel}`);
|
|
}
|
|
|
|
if (bitDepth != 16) {
|
|
throw new Error(`Only support 16-bit samples. Given ${bitDepth}`);
|
|
}
|
|
});
|
|
|
|
fs.createReadStream(waveFilename, {highWaterMark: 4096})
|
|
.pipe(reader)
|
|
.on('finish', function(err) {
|
|
// tail padding
|
|
const floatSamples =
|
|
new Float32Array(recognizer.config.featConfig.sampleRate * 0.5);
|
|
|
|
buf.push(floatSamples);
|
|
const flattened =
|
|
Float32Array.from(buf.reduce((a, b) => [...a, ...b], []));
|
|
|
|
stream.acceptWaveform(recognizer.config.featConfig.sampleRate, flattened);
|
|
recognizer.decode(stream);
|
|
const text = recognizer.getResult(stream).text;
|
|
console.log(text);
|
|
|
|
stream.free();
|
|
recognizer.free();
|
|
});
|
|
|
|
readable.on('readable', function() {
|
|
let chunk;
|
|
while ((chunk = readable.read()) != null) {
|
|
const int16Samples = new Int16Array(
|
|
chunk.buffer, chunk.byteOffset,
|
|
chunk.length / Int16Array.BYTES_PER_ELEMENT);
|
|
|
|
const floatSamples = new Float32Array(int16Samples.length);
|
|
|
|
for (let i = 0; i < floatSamples.length; i++) {
|
|
floatSamples[i] = int16Samples[i] / 32768.0;
|
|
}
|
|
|
|
buf.push(floatSamples);
|
|
}
|
|
});
|