mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2023-11-04 02:52:44 +03:00
command.wasm : add voice assistant example for the Web (#171)
Same as the command-line tool "command", but runs in the browser Also, added helper script "extra/deploy-wasm.sh" and fixed some timing constants for the WASM examples.
This commit is contained in:
Georgi Gerganov
386
examples/command.wasm/index-tmpl.html
Normal file
386
examples/command.wasm/index-tmpl.html
Normal file
@@ -0,0 +1,386 @@
|
||||
<!doctype html>
|
||||
<html lang="en-us">
|
||||
<head>
|
||||
<title>command : Voice assistant example using Whisper + WebAssembly</title>
|
||||
|
||||
<style>
|
||||
#output {
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
margin: 0 auto;
|
||||
margin-top: 10px;
|
||||
border-left: 0px;
|
||||
border-right: 0px;
|
||||
padding-left: 0px;
|
||||
padding-right: 0px;
|
||||
display: block;
|
||||
background-color: black;
|
||||
color: white;
|
||||
font-size: 10px;
|
||||
font-family: 'Lucida Console', Monaco, monospace;
|
||||
outline: none;
|
||||
white-space: pre;
|
||||
overflow-wrap: normal;
|
||||
overflow-x: scroll;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div id="main-container">
|
||||
<b>command : Voice assistant example using Whisper + WebAssembly</b>
|
||||
|
||||
<br><br>
|
||||
|
||||
You can find more about this project on <a href="https://github.com/ggerganov/whisper.cpp/tree/master/examples/command.wasm">GitHub</a>.
|
||||
|
||||
<br><br>
|
||||
|
||||
<hr>
|
||||
|
||||
Select the model you would like to use, click the "Start" button and follow the instructions.
|
||||
|
||||
<br><br>
|
||||
|
||||
<div id="model-whisper">
|
||||
Whisper model: <span id="model-whisper-status"></span>
|
||||
<button id="fetch-whisper-tiny-en" onclick="loadWhisper('tiny.en')">tiny.en (75 MB)</button>
|
||||
<button id="fetch-whisper-base-en" onclick="loadWhisper('base.en')">base.en (142 MB)</button>
|
||||
<span id="fetch-whisper-progress"></span>
|
||||
|
||||
<!--
|
||||
<input type="file" id="file" name="file" onchange="loadFile(event, 'whisper.bin')" />
|
||||
-->
|
||||
</div>
|
||||
|
||||
<br>
|
||||
|
||||
<div id="input">
|
||||
<button id="start" onclick="onStart()" disabled>Start</button>
|
||||
<button id="stop" onclick="onStop()" disabled>Stop</button>
|
||||
<button id="clear" onclick="clearCache()">Clear Cache</button>
|
||||
</div>
|
||||
|
||||
<br>
|
||||
|
||||
<div id="state">
|
||||
Status: <b><span id="state-status">not started</span></b>
|
||||
|
||||
<pre id="state-transcribed">[The recognized voice commands will be displayed here]</pre>
|
||||
</div>
|
||||
|
||||
<hr>
|
||||
|
||||
Debug output:
|
||||
<textarea id="output" rows="20"></textarea>
|
||||
|
||||
<br>
|
||||
|
||||
<b>Troubleshooting</b>
|
||||
|
||||
<br><br>
|
||||
|
||||
The page does some heavy computations, so make sure:
|
||||
|
||||
<ul>
|
||||
<li>To use a modern web browser (e.g. Chrome, Firefox)</li>
|
||||
<li>To use a fast desktop or laptop computer (i.e. not a mobile phone)</li>
|
||||
<li>Your browser supports WASM <a href="https://webassembly.org/roadmap/">Fixed-width SIMD</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="cell-version">
|
||||
<span>
|
||||
|
|
||||
Build time: <span class="nav-link">@GIT_DATE@</span> |
|
||||
Commit hash: <a class="nav-link" href="https://github.com/ggerganov/whisper.cpp/commit/@GIT_SHA1@">@GIT_SHA1@</a> |
|
||||
Commit subject: <span class="nav-link">@GIT_COMMIT_SUBJECT@</span> |
|
||||
<a class="nav-link" href="https://github.com/ggerganov/whisper.cpp/tree/master/examples/command.wasm">Source Code</a> |
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script type="text/javascript" src="helpers.js"></script>
|
||||
<script type='text/javascript'>
|
||||
// web audio context
|
||||
var context = null;
|
||||
|
||||
// audio data
|
||||
var audio = null;
|
||||
var audio0 = null;
|
||||
|
||||
// the command instance
|
||||
var instance = null;
|
||||
|
||||
// model name
|
||||
var model_whisper = null;
|
||||
|
||||
var Module = {
|
||||
print: printTextarea,
|
||||
printErr: printTextarea,
|
||||
setStatus: function(text) {
|
||||
printTextarea('js: ' + text);
|
||||
},
|
||||
monitorRunDependencies: function(left) {
|
||||
},
|
||||
preRun: function() {
|
||||
printTextarea('js: Preparing ...');
|
||||
},
|
||||
postRun: function() {
|
||||
printTextarea('js: Initialized successfully!');
|
||||
}
|
||||
};
|
||||
|
||||
//
|
||||
// fetch models
|
||||
//
|
||||
|
||||
let dbVersion = 1
|
||||
let dbName = 'whisper.ggerganov.com';
|
||||
let indexedDB = window.indexedDB || window.mozIndexedDB || window.webkitIndexedDB || window.msIndexedDB
|
||||
|
||||
function storeFS(fname, buf) {
|
||||
// write to WASM file using FS_createDataFile
|
||||
// if the file exists, delete it
|
||||
try {
|
||||
Module.FS_unlink(fname);
|
||||
} catch (e) {
|
||||
// ignore
|
||||
}
|
||||
|
||||
Module.FS_createDataFile("/", fname, buf, true, true);
|
||||
|
||||
printTextarea('storeFS: stored model: ' + fname + ' size: ' + buf.length);
|
||||
|
||||
document.getElementById('model-whisper-status').innerHTML = 'loaded "' + model_whisper + '"!';
|
||||
|
||||
if (model_whisper != null) {
|
||||
document.getElementById('start').disabled = false;
|
||||
document.getElementById('stop' ).disabled = true;
|
||||
}
|
||||
}
|
||||
|
||||
function loadWhisper(model) {
|
||||
let urls = {
|
||||
'tiny.en': 'https://whisper.ggerganov.com/ggml-model-whisper-tiny.en.bin',
|
||||
'base.en': 'https://whisper.ggerganov.com/ggml-model-whisper-base.en.bin',
|
||||
};
|
||||
|
||||
let sizes = {
|
||||
'tiny.en': 75,
|
||||
'base.en': 142,
|
||||
};
|
||||
|
||||
let url = urls[model];
|
||||
let dst = 'whisper.bin';
|
||||
let size_mb = sizes[model];
|
||||
|
||||
model_whisper = model;
|
||||
|
||||
document.getElementById('fetch-whisper-tiny-en').style.display = 'none';
|
||||
document.getElementById('fetch-whisper-base-en').style.display = 'none';
|
||||
document.getElementById('model-whisper-status').innerHTML = 'loading "' + model + '" ... ';
|
||||
|
||||
cbProgress = function(p) {
|
||||
let el = document.getElementById('fetch-whisper-progress');
|
||||
el.innerHTML = Math.round(100*p) + '%';
|
||||
};
|
||||
|
||||
cbCancel = function() {
|
||||
var el;
|
||||
el = document.getElementById('fetch-whisper-tiny-en'); if (el) el.style.display = 'inline-block';
|
||||
el = document.getElementById('fetch-whisper-base-en'); if (el) el.style.display = 'inline-block';
|
||||
el = document.getElementById('model-whisper-status'); if (el) el.innerHTML = '';
|
||||
};
|
||||
|
||||
loadRemote(url, dst, size_mb, cbProgress, storeFS, cbCancel, printTextarea);
|
||||
}
|
||||
|
||||
//
|
||||
// microphone
|
||||
//
|
||||
|
||||
const kSampleRate = 16000;
|
||||
const kRestartRecording_s = 120;
|
||||
const kIntervalAudio_ms = 250; // pass the recorded audio to the C++ instance at this rate
|
||||
|
||||
var mediaRecorder = null;
|
||||
var doRecording = false;
|
||||
var startTime = 0;
|
||||
|
||||
window.AudioContext = window.AudioContext || window.webkitAudioContext;
|
||||
window.OfflineAudioContext = window.OfflineAudioContext || window.webkitOfflineAudioContext;
|
||||
|
||||
function stopRecording() {
|
||||
Module.set_status("paused");
|
||||
doRecording = false;
|
||||
audio0 = null;
|
||||
audio = null;
|
||||
context = null;
|
||||
}
|
||||
|
||||
function startRecording() {
|
||||
if (!context) {
|
||||
context = new AudioContext({
|
||||
sampleRate: kSampleRate,
|
||||
channelCount: 1,
|
||||
echoCancellation: false,
|
||||
autoGainControl: true,
|
||||
noiseSuppression: true,
|
||||
});
|
||||
}
|
||||
|
||||
Module.set_status("");
|
||||
|
||||
document.getElementById('start').disabled = true;
|
||||
document.getElementById('stop').disabled = false;
|
||||
|
||||
doRecording = true;
|
||||
startTime = Date.now();
|
||||
|
||||
var chunks = [];
|
||||
var stream = null;
|
||||
|
||||
navigator.mediaDevices.getUserMedia({audio: true, video: false})
|
||||
.then(function(s) {
|
||||
stream = s;
|
||||
mediaRecorder = new MediaRecorder(stream);
|
||||
mediaRecorder.ondataavailable = function(e) {
|
||||
chunks.push(e.data);
|
||||
|
||||
var blob = new Blob(chunks, { 'type' : 'audio/ogg; codecs=opus' });
|
||||
var reader = new FileReader();
|
||||
|
||||
reader.onload = function(event) {
|
||||
var buf = new Uint8Array(reader.result);
|
||||
|
||||
if (!context) {
|
||||
return;
|
||||
}
|
||||
context.decodeAudioData(buf.buffer, function(audioBuffer) {
|
||||
var offlineContext = new OfflineAudioContext(audioBuffer.numberOfChannels, audioBuffer.length, audioBuffer.sampleRate);
|
||||
var source = offlineContext.createBufferSource();
|
||||
source.buffer = audioBuffer;
|
||||
source.connect(offlineContext.destination);
|
||||
source.start(0);
|
||||
|
||||
offlineContext.startRendering().then(function(renderedBuffer) {
|
||||
audio = renderedBuffer.getChannelData(0);
|
||||
|
||||
//printTextarea('js: audio recorded, size: ' + audio.length + ', old size: ' + (audio0 == null ? 0 : audio0.length));
|
||||
|
||||
var audioAll = new Float32Array(audio0 == null ? audio.length : audio0.length + audio.length);
|
||||
if (audio0 != null) {
|
||||
audioAll.set(audio0, 0);
|
||||
}
|
||||
audioAll.set(audio, audio0 == null ? 0 : audio0.length);
|
||||
|
||||
if (instance) {
|
||||
Module.set_audio(instance, audioAll);
|
||||
}
|
||||
});
|
||||
}, function(e) {
|
||||
audio = null;
|
||||
});
|
||||
}
|
||||
|
||||
reader.readAsArrayBuffer(blob);
|
||||
};
|
||||
|
||||
mediaRecorder.onstop = function(e) {
|
||||
if (doRecording) {
|
||||
setTimeout(function() {
|
||||
startRecording();
|
||||
});
|
||||
}
|
||||
};
|
||||
|
||||
mediaRecorder.start(kIntervalAudio_ms);
|
||||
})
|
||||
.catch(function(err) {
|
||||
printTextarea('js: error getting audio stream: ' + err);
|
||||
});
|
||||
|
||||
var interval = setInterval(function() {
|
||||
if (!doRecording) {
|
||||
clearInterval(interval);
|
||||
mediaRecorder.stop();
|
||||
stream.getTracks().forEach(function(track) {
|
||||
track.stop();
|
||||
});
|
||||
|
||||
document.getElementById('start').disabled = false;
|
||||
document.getElementById('stop').disabled = true;
|
||||
|
||||
mediaRecorder = null;
|
||||
}
|
||||
|
||||
// if audio length is more than kRestartRecording_s seconds, restart recording
|
||||
if (audio != null && audio.length > kSampleRate*kRestartRecording_s) {
|
||||
if (doRecording) {
|
||||
//printTextarea('js: restarting recording');
|
||||
|
||||
clearInterval(interval);
|
||||
audio0 = audio;
|
||||
audio = null;
|
||||
mediaRecorder.stop();
|
||||
stream.getTracks().forEach(function(track) {
|
||||
track.stop();
|
||||
});
|
||||
}
|
||||
}
|
||||
}, 100);
|
||||
}
|
||||
|
||||
//
|
||||
// main
|
||||
//
|
||||
|
||||
var nLines = 0;
|
||||
var intervalUpdate = null;
|
||||
var transcribedAll = '';
|
||||
|
||||
function onStart() {
|
||||
if (!instance) {
|
||||
instance = Module.init('whisper.bin');
|
||||
|
||||
if (instance) {
|
||||
printTextarea("js: whisper initialized, instance: " + instance);
|
||||
}
|
||||
}
|
||||
|
||||
if (!instance) {
|
||||
printTextarea("js: failed to initialize whisper");
|
||||
return;
|
||||
}
|
||||
|
||||
startRecording();
|
||||
|
||||
intervalUpdate = setInterval(function() {
|
||||
var transcribed = Module.get_transcribed();
|
||||
|
||||
if (transcribed != null && transcribed.length > 1) {
|
||||
transcribedAll += transcribed + '<br>';
|
||||
nLines++;
|
||||
|
||||
// if more than 10 lines, remove the first line
|
||||
if (nLines > 10) {
|
||||
var i = transcribedAll.indexOf('<br>');
|
||||
if (i > 0) {
|
||||
transcribedAll = transcribedAll.substring(i + 4);
|
||||
nLines--;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
document.getElementById('state-status').innerHTML = Module.get_status();
|
||||
document.getElementById('state-transcribed').innerHTML = transcribedAll;
|
||||
}, 100);
|
||||
}
|
||||
|
||||
function onStop() {
|
||||
stopRecording();
|
||||
}
|
||||
|
||||
</script>
|
||||
<script type="text/javascript" src="command.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user