* Support streaming zipformer CTC * test online zipformer2 CTC * Update doc of sherpa-onnx.cc * Add Python APIs for streaming zipformer2 ctc * Add Python API examples for streaming zipformer2 ctc * Swift API for streaming zipformer2 CTC * NodeJS API for streaming zipformer2 CTC * Kotlin API for streaming zipformer2 CTC * Golang API for streaming zipformer2 CTC * C# API for streaming zipformer2 CTC * Release v1.9.6
98 lines
2.9 KiB
JavaScript
98 lines
2.9 KiB
JavaScript
// Copyright (c) 2023 Xiaomi Corporation (authors: Fangjun Kuang)
|
|
//
|
|
const fs = require('fs');
|
|
const {Readable} = require('stream');
|
|
const wav = require('wav');
|
|
|
|
const sherpa_onnx = require('sherpa-onnx');
|
|
|
|
function createRecognizer() {
|
|
const featConfig = new sherpa_onnx.FeatureConfig();
|
|
featConfig.sampleRate = 16000;
|
|
featConfig.featureDim = 80;
|
|
|
|
// test online recognizer
|
|
const zipformer2Ctc = new sherpa_onnx.OnlineZipformer2CtcModelConfig();
|
|
zipformer2Ctc.model =
|
|
'./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/ctc-epoch-20-avg-1-chunk-16-left-128.onnx';
|
|
const tokens =
|
|
'./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/tokens.txt';
|
|
|
|
const modelConfig = new sherpa_onnx.OnlineModelConfig();
|
|
modelConfig.zipformer2Ctc = zipformer2Ctc;
|
|
modelConfig.tokens = tokens;
|
|
|
|
const recognizerConfig = new sherpa_onnx.OnlineRecognizerConfig();
|
|
recognizerConfig.featConfig = featConfig;
|
|
recognizerConfig.modelConfig = modelConfig;
|
|
recognizerConfig.decodingMethod = 'greedy_search';
|
|
|
|
recognizer = new sherpa_onnx.OnlineRecognizer(recognizerConfig);
|
|
return recognizer;
|
|
}
|
|
recognizer = createRecognizer();
|
|
stream = recognizer.createStream();
|
|
|
|
const waveFilename =
|
|
'./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000000.wav';
|
|
|
|
const reader = new wav.Reader();
|
|
const readable = new Readable().wrap(reader);
|
|
|
|
function decode(samples) {
|
|
stream.acceptWaveform(recognizer.config.featConfig.sampleRate, samples);
|
|
|
|
while (recognizer.isReady(stream)) {
|
|
recognizer.decode(stream);
|
|
}
|
|
const r = recognizer.getResult(stream);
|
|
console.log(r.text);
|
|
}
|
|
|
|
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);
|
|
decode(floatSamples);
|
|
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;
|
|
}
|
|
|
|
decode(floatSamples);
|
|
}
|
|
});
|