|
<!doctype html> |
|
<html lang="en-us"> |
|
<head> |
|
<title>wchess : voice-controlled chess using Whisper + WebAssembly</title> |
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/iframe-resizer/4.3.1/iframeResizer.contentWindow.min.js"></script> |
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=0.4, maximum-scale=1, minimum-scale=1, user-scalable=no"/> |
|
<meta name="apple-mobile-web-app-capable" content="yes" /> |
|
|
|
<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; |
|
} |
|
.button { |
|
background-color: #000000; |
|
color: #FFFFFF; |
|
padding: 20px; |
|
border-radius: 10px; |
|
-moz-border-radius: 10px; |
|
-webkit-border-radius: 10px; |
|
margin:10px; |
|
width: 100px; |
|
height: 50px; |
|
-webkit-touch-callout: none; |
|
-webkit-user-select: none; |
|
-moz-user-select: none; |
|
-ms-user-select: none; |
|
user-select: none; |
|
} |
|
.center { |
|
display: flex; |
|
justify-content: center; |
|
align-items: center; |
|
width: 300px; |
|
} |
|
</style> |
|
<link rel="stylesheet" href="css/chessboard-1.0.0.min.css" integrity="sha384-q94+BZtLrkL1/ohfjR8c6L+A6qzNH9R2hBLwyoAfu3i/WCvQjzL2RQJ3uNHDISdU" crossorigin="anonymous"> |
|
</head> |
|
<body onload="loadWhisper()"> |
|
<div id="main-container"> |
|
<b>wchess : voice-controlled chess using Whisper + WebAssembly</b> |
|
|
|
<br><br> |
|
|
|
This is a demonstration of using Whisper to recognize voice commands in the browser. |
|
|
|
<br><br> |
|
|
|
Usage:<br> |
|
|
|
<ul> |
|
<li>Hold the button and say a chess move (e.g. "e2-e4")</li> |
|
<li>Release the button and wait for the move to be recognized</li> |
|
<li>Repeat</li> |
|
</ul> |
|
|
|
Examples:<br> |
|
|
|
<ul> |
|
<li><b>"d4"</b></li> |
|
<li><b>"e2 e4"</b></li> |
|
<li><b>"Knight to f3"</b></li> |
|
<li><b>"Bishop to b5"</b></li> |
|
</ul> |
|
|
|
Note that not all chess moves are supported. For example, castling and pawn promotion<br> |
|
currently do not work, but can be easily implemented. The main purpose of this example<br> |
|
is to demonstrate the capabilities of Whisper and it's application in the browser. |
|
|
|
<br><br> |
|
|
|
Features:<br> |
|
|
|
<ul> |
|
<li>Model quantization for reduced memory footprint (~42MB)</li> |
|
<li><a href="https://github.com/ggerganov/whisper.cpp/pull/1229">Grammar-based sampling</a> for improved recognition accuracy</li> |
|
</ul> |
|
|
|
You can find more about this project on <a href="https://github.com/ggerganov/whisper.cpp/tree/master/examples/wchess">GitHub</a>. |
|
|
|
<br><br> |
|
|
|
<b>More examples:</b> |
|
<a href="https://whisper.ggerganov.com/">main</a> | |
|
<a href="https://whisper.ggerganov.com/bench">bench</a> | |
|
<a href="https://whisper.ggerganov.com/stream">stream</a> | |
|
<a href="https://whisper.ggerganov.com/command">command</a> | |
|
<a href="https://whisper.ggerganov.com/talk">talk</a> | |
|
|
|
<br><br> |
|
|
|
<hr> |
|
|
|
<div id="model-whisper"> |
|
Whisper model: <span id="model-whisper-status"></span> |
|
<span id="fetch-whisper-progress"></span> |
|
<br><br> |
|
<button id="clear" onclick="clearCache()">Clear Cache</button> |
|
|
|
|
|
|
|
</div> |
|
|
|
<br> |
|
<div id="chessboard" style="width: 300px"></div> |
|
<script src="js/jquery-3.7.1.min.js"></script> |
|
<script src="js/chessboard-1.0.0.min.js"></script> |
|
<script> |
|
var board = Chessboard('chessboard', 'start') |
|
var move_count = 0; |
|
</script> |
|
|
|
<br> |
|
|
|
<div id="input" class="center"> |
|
<button id="toggler" class="button" onselectstart="return false" disabled>Hold</button> |
|
</div> |
|
|
|
<br> |
|
|
|
<div id="state"> |
|
Status: <b><span id="state-status">not started</span></b> |
|
|
|
<pre id="state-moves">[The moves 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>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">Fri Dec 8 10:03:41 2023</span> | |
|
Commit hash: <a class="nav-link" href="https://github.com/ggerganov/whisper.cpp/commit/be5cd736">be5cd736</a> | |
|
Commit subject: <span class="nav-link">wchess: touchstart, touchend events</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="js/helpers.js"></script> |
|
<script type='text/javascript'> |
|
document.addEventListener("DOMContentLoaded", () => { |
|
|
|
if (!window.SharedArrayBuffer) { |
|
document.querySelector("#warning").style.display = "block"; |
|
} |
|
}); |
|
|
|
var context = null; |
|
|
|
|
|
var instance = null; |
|
|
|
|
|
var model_whisper = null; |
|
var model_file = null; |
|
|
|
var module_ready = 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: Module initialized successfully!'); |
|
module_ready = true; |
|
initInstance(); |
|
} |
|
}; |
|
|
|
function initInstance() { |
|
if (!module_ready || !model_file || instance) return |
|
|
|
instance = Module.init(model_file); |
|
|
|
if (instance) { |
|
document.getElementById('toggler').disabled = false; |
|
setStatus('Ready'); |
|
printTextarea("js: whisper initialized, instance: " + instance); |
|
} |
|
else { |
|
printTextarea("js: failed to initialize whisper"); |
|
} |
|
} |
|
|
|
function setStatus(text) { |
|
document.getElementById('state-status').innerHTML = text; |
|
} |
|
|
|
|
|
|
|
|
|
|
|
let dbVersion = 1 |
|
let dbName = 'whisper.ggerganov.com'; |
|
let indexedDB = window.indexedDB || window.mozIndexedDB || window.webkitIndexedDB || window.msIndexedDB |
|
|
|
function storeFS(fname, buf) { |
|
|
|
|
|
try { |
|
Module.FS_unlink(fname); |
|
} catch (e) { |
|
|
|
} |
|
|
|
Module.FS_createDataFile("/", fname, buf, true, true); |
|
|
|
printTextarea('storeFS: stored model: ' + fname + ' size: ' + buf.length); |
|
|
|
document.getElementById('model-whisper-status').innerHTML = 'loaded "' + model_whisper + '"!'; |
|
|
|
model_file = fname; |
|
initInstance(); |
|
} |
|
|
|
function loadWhisper() { |
|
setStatus('Loading') |
|
|
|
let url = 'https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.en-q8_0.bin'; |
|
let dst = 'whisper.bin'; |
|
let size_mb = 42; |
|
|
|
model_whisper = 'tiny.en-q8_0'; |
|
|
|
document.getElementById('model-whisper-status').innerHTML = 'loading "' + model_whisper + '" ... '; |
|
|
|
cbProgress = function(p) { |
|
let el = document.getElementById('fetch-whisper-progress'); |
|
el.innerHTML = Math.round(100*p) + '%'; |
|
}; |
|
|
|
cbCancel = function() { |
|
var el; |
|
el = document.getElementById('model-whisper-status'); if (el) el.innerHTML = ''; |
|
}; |
|
|
|
loadRemote(url, dst, size_mb, cbProgress, storeFS, cbCancel, printTextarea); |
|
} |
|
|
|
|
|
|
|
|
|
|
|
const kSampleRate = 16000; |
|
const kRestartRecording_s = 120; |
|
const kIntervalAudio_ms = 250; |
|
|
|
var mediaRecorder = null; |
|
var doRecording = false; |
|
var startTime = 0; |
|
|
|
window.AudioContext = window.AudioContext || window.webkitAudioContext; |
|
window.OfflineAudioContext = window.OfflineAudioContext || window.webkitOfflineAudioContext; |
|
|
|
function stopRecording() { |
|
mediaRecorder.stop(); |
|
} |
|
|
|
function startRecording() { |
|
if (!context) { |
|
context = new AudioContext({ |
|
sampleRate: kSampleRate, |
|
channelCount: 1, |
|
echoCancellation: false, |
|
autoGainControl: true, |
|
noiseSuppression: 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); |
|
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) { |
|
let audio = renderedBuffer.getChannelData(0); |
|
printTextarea('js: number of samples: ' + audio.length); |
|
Module.set_audio(instance, audio); |
|
}); |
|
|
|
mediaRecorder = null; |
|
context = null; |
|
}); |
|
} |
|
|
|
reader.readAsArrayBuffer(blob); |
|
}; |
|
|
|
mediaRecorder.onstop = function(e) { |
|
stream.getTracks().forEach(function(track) { |
|
track.stop(); |
|
}); |
|
}; |
|
|
|
mediaRecorder.start(); |
|
}) |
|
.catch(function(err) { |
|
printTextarea('js: error getting audio stream: ' + err); |
|
}); |
|
} |
|
|
|
|
|
|
|
|
|
|
|
var nLines = 0; |
|
var movesAll = ''; |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
document.getElementById('toggler').addEventListener("touchstart", function(event){ |
|
this.innerText = ""; |
|
onStart(); |
|
}, true); |
|
|
|
document.getElementById('toggler').addEventListener("touchend", function(event){ |
|
this.innerText = "Hold"; |
|
onStop(); |
|
}, true) |
|
|
|
document.getElementById('toggler').addEventListener('mousedown', function(event) { |
|
this.innerText = ""; |
|
onStart(); |
|
}, true); |
|
|
|
document.getElementById('toggler').addEventListener('mouseup', function(event) { |
|
this.innerText = "Hold"; |
|
onStop(); |
|
}, true); |
|
|
|
function onStart() { |
|
if (!instance) return; |
|
setStatus('Listening'); |
|
|
|
startRecording(); |
|
} |
|
|
|
function onStop() { |
|
setStatus('Processing'); |
|
printTextarea('js: stopping recording ...'); |
|
stopRecording(); |
|
} |
|
|
|
function setMove(move, prob) { |
|
if (move != null && move.length > 1) { |
|
let gameOver = move[move.length - 1] === '#'; |
|
if (gameOver) { |
|
move = move.substring(0, move.length - 1); |
|
document.getElementById('toggler').disabled = true; |
|
} |
|
board.move(move); |
|
|
|
movesAll += move + ', prob = ' + prob.toFixed(2) + '% <br>'; |
|
nLines++; |
|
|
|
|
|
if (nLines > 10) { |
|
var i = movesAll.indexOf('<br>'); |
|
if (i > 0) { |
|
movesAll = movesAll.substring(i + 4); |
|
nLines--; |
|
} |
|
} |
|
++move_count; |
|
setStatus(gameOver ? 'Done' : move_count % 2 ? 'Black\'s turn' : 'White\'s turn'); |
|
document.getElementById('state-moves').innerHTML = movesAll; |
|
} |
|
else { |
|
setStatus('Failed. ' + (move_count % 2 ? 'Black\'s turn' : 'White\'s turn')); |
|
} |
|
} |
|
|
|
</script> |
|
<script type="text/javascript" src="js/chess.js"></script> |
|
</body> |
|
</html> |
|
|
