mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-22 22:12:21 +00:00
500 lines
19 KiB
HTML
500 lines
19 KiB
HTML
|
<!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=0.7, maximum-scale=1, minimum-scale=0.7, 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; /* Safari */
|
||
|
|
-webkit-user-select: none; /* Chrome */
|
||
|
|
-moz-user-select: none; /* Firefox */
|
||
|
|
-ms-user-select: none; /* Internet Explorer/Edge */
|
||
|
|
user-select: none;
|
||
|
|
}
|
||
|
|
button[disabled]{
|
||
|
|
background-color: #cccccc;
|
||
|
|
color: #666666;
|
||
|
|
padding: 20px;
|
||
|
|
border-radius: 10px;
|
||
|
|
-moz-border-radius: 10px;
|
||
|
|
-webkit-border-radius: 10px;
|
||
|
|
margin:10px;
|
||
|
|
width: 100px;
|
||
|
|
}
|
||
|
|
.center {
|
||
|
|
display: flex;
|
||
|
|
justify-content: center;
|
||
|
|
align-items: center;
|
||
|
|
width: 500px;
|
||
|
|
}
|
||
|
|
#description {
|
||
|
|
width: 500px;
|
||
|
|
}
|
||
|
|
</style>
|
||
|
|
<link rel="stylesheet" href="css/chessboard-1.0.0.min.css" integrity="sha384-q94+BZtLrkL1/ohfjR8c6L+A6qzNH9R2hBLwyoAfu3i/WCvQjzL2RQJ3uNHDISdU" crossorigin="anonymous">
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<div id="main-container">
|
||
|
|
<div id="description">
|
||
|
|
<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>Select a Whisper model</li>
|
||
|
|
<li>Accept the microphone permission request if prompted</li>
|
||
|
|
<li>Hold the button and say a chess move (e.g. "Knight to c3")</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 f3"</b></li>
|
||
|
|
<li><b>"Bishop to b5"</b></li>
|
||
|
|
</ul>
|
||
|
|
|
||
|
|
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>
|
||
|
|
|
||
|
|
<b>
|
||
|
|
Note that not all chess moves are supported. For example, castling and pawn promotion
|
||
|
|
currently do not work, but can be easily implemented. There could also be some bugs in
|
||
|
|
the move handling logic in general. The main reason for that is to keep the implementation
|
||
|
|
simple. The assumption is that a real application would already have a proper move
|
||
|
|
validation logic in place.<br><br>
|
||
|
|
|
||
|
|
The main purpose of this example is to demonstrate the capabilities of whisper.cpp and
|
||
|
|
its application in the browser for voice recognition locally on your device.
|
||
|
|
</b>
|
||
|
|
|
||
|
|
<br><br>
|
||
|
|
|
||
|
|
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>
|
||
|
|
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<hr>
|
||
|
|
|
||
|
|
<div id="model-whisper">
|
||
|
|
Whisper model: <span id="model-whisper-status"></span>
|
||
|
|
<button id="fetch-whisper-tiny-en" onclick="loadWhisper()">tiny.en (Q8_0, 42 MB)</button>
|
||
|
|
<span id="fetch-whisper-progress"></span>
|
||
|
|
<br><br>
|
||
|
|
<button id="clear" onclick="clearCache()">Clear browser cache</button>
|
||
|
|
<!--
|
||
|
|
<input type="file" id="file" name="file" onchange="loadFile(event, 'whisper.bin')" />
|
||
|
|
-->
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<div id="game">
|
||
|
|
<br>
|
||
|
|
<div id="chessboard" style="width: 500px"></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="state">
|
||
|
|
Status: <b><span id="state-status">select model</span></b>
|
||
|
|
|
||
|
|
<div id="input" class="center">
|
||
|
|
<button id="toggler" class="button" onselectstart="return false" style="display: none">Hold</button>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<pre id="state-grammar">[The grammar will be displayed here]</pre>
|
||
|
|
|
||
|
|
<pre id="state-moves">[The moves will be displayed here]</pre>
|
||
|
|
</div>
|
||
|
|
</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">@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="js/helpers.js"></script>
|
||
|
|
<script type='text/javascript'>
|
||
|
|
// web audio context
|
||
|
|
var context = null;
|
||
|
|
|
||
|
|
// the command instance
|
||
|
|
var instance = null;
|
||
|
|
|
||
|
|
// model name
|
||
|
|
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) {
|
||
|
|
setStatus('Ready');
|
||
|
|
printTextarea("js: whisper initialized, instance: " + instance);
|
||
|
|
}
|
||
|
|
else {
|
||
|
|
printTextarea("js: failed to initialize whisper");
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
function setStatus(text) {
|
||
|
|
document.getElementById('state-status').innerHTML = text;
|
||
|
|
}
|
||
|
|
|
||
|
|
//
|
||
|
|
// 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 + '"!';
|
||
|
|
|
||
|
|
model_file = fname;
|
||
|
|
initInstance();
|
||
|
|
}
|
||
|
|
|
||
|
|
function loadWhisper() {
|
||
|
|
setStatus('Loading')
|
||
|
|
//let url = 'https://whisper.ggerganov.com/ggml-model-whisper-tiny.en-q8_0.bin';
|
||
|
|
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 + '" ... ';
|
||
|
|
document.getElementById('fetch-whisper-tiny-en').style.display = 'none';
|
||
|
|
|
||
|
|
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);
|
||
|
|
|
||
|
|
// init audio capture so that the user receives a permission request
|
||
|
|
{
|
||
|
|
let context = new AudioContext({
|
||
|
|
sampleRate: 16000,
|
||
|
|
channelCount: 1,
|
||
|
|
echoCancellation: false,
|
||
|
|
autoGainControl: true,
|
||
|
|
noiseSuppression: true,
|
||
|
|
});
|
||
|
|
navigator.mediaDevices.getUserMedia({audio: true, video: false})
|
||
|
|
.then(function(s) {
|
||
|
|
stream = s;
|
||
|
|
stream.getTracks().forEach(function(track) {
|
||
|
|
track.stop();
|
||
|
|
});
|
||
|
|
})
|
||
|
|
.catch(function(err) {
|
||
|
|
printTextarea('js: error getting audio stream: ' + err);
|
||
|
|
});
|
||
|
|
context.close();
|
||
|
|
}
|
||
|
|
|
||
|
|
document.getElementById('toggler').style.display = 'block';
|
||
|
|
}
|
||
|
|
|
||
|
|
//
|
||
|
|
// 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() {
|
||
|
|
if (mediaRecorder) {
|
||
|
|
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);
|
||
|
|
});
|
||
|
|
}
|
||
|
|
|
||
|
|
//
|
||
|
|
// main
|
||
|
|
//
|
||
|
|
|
||
|
|
var nLines = 0;
|
||
|
|
var movesAll = '';
|
||
|
|
|
||
|
|
// document.body.addEventListener('keydown', function(event) {
|
||
|
|
// if (event.keyCode === 32) {
|
||
|
|
// document.getElementById('toggler').innerText = "";
|
||
|
|
// onStart();
|
||
|
|
// }
|
||
|
|
// }, true);
|
||
|
|
|
||
|
|
// document.body.addEventListener('keyup', function(event) {
|
||
|
|
// if (event.keyCode === 32) {
|
||
|
|
// document.getElementById('toggler').innerText = "Hold";
|
||
|
|
// onStop();
|
||
|
|
// }
|
||
|
|
// }, true);
|
||
|
|
|
||
|
|
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 more than 10 lines, remove the first line
|
||
|
|
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'));
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
function setGrammar(grammar) {
|
||
|
|
document.getElementById('state-grammar').innerHTML = grammar;
|
||
|
|
}
|
||
|
|
|
||
|
|
</script>
|
||
|
|
<script type="text/javascript" src="js/chess.js"></script>
|
||
|
|
</body>
|
||
|
|
</html>
|