whisper.cpp/examples/bench.wasm/index-tmpl.html
Georgi Gerganov 794b162a46
whisper : add integer quantization support (#540)
* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
2023-04-30 18:51:57 +03:00

284 lines
12 KiB
HTML

<!doctype html>
<html lang="en-us">
<head>
<title>bench : Benchmark whisper.cpp performance in the browser</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>bench : Benchmark whisper.cpp performance in the browser</b>
<br><br>
You can find more about this project on <a href="https://github.com/ggerganov/whisper.cpp/tree/master/examples/bench.wasm">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>
Select the model you would like to use and click the "Bench" button.<br>
The results will be displayed in the textarea below.
<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>
<button id="fetch-whisper-small-en" onclick="loadWhisper('small.en')">small.en (466 MB)</button>
<input type="file" id="whisper-file" name="file" onchange="loadFile(event, 'whisper.bin')" />
<br><br>
Quantized models:<br><br>
<button id="fetch-whisper-tiny-en-q5_1" onclick="loadWhisper('tiny-en-q5_1')">tiny.en (Q5_1, 31 MB)</button>
<button id="fetch-whisper-base-en-q5_1" onclick="loadWhisper('base-en-q5_1')">base.en (Q5_1, 57 MB)</button>
<button id="fetch-whisper-small-en-q5_1" onclick="loadWhisper('small-en-q5_1')">small.en (Q5_1, 182 MB)</button>
<button id="fetch-whisper-medium-en-q5_0" onclick="loadWhisper('medium-en-q5_0')">medium.en (Q5_0, 515 MB)</button>
<button id="fetch-whisper-large-q5_0" onclick="loadWhisper('large-q5_0')">large (Q5_0, 1030 MB)</button>
<span id="fetch-whisper-progress"></span>
</div>
<br>
<div id="input">
<button id="bench" onclick="onBench()" disabled>Bench</button>
<button id="clear" onclick="clearCache()">Clear Cache</button>
</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/bench.wasm">Source Code</a> |
</span>
</div>
</div>
<script type="text/javascript" src="helpers.js"></script>
<script type='text/javascript'>
// the bench 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);
model_whisper = fname;
document.getElementById('model-whisper-status').innerHTML = 'loaded "' + model_whisper + '"!';
if (model_whisper != null) {
document.getElementById('bench').disabled = false;
}
}
function loadFile(event, fname) {
var file = event.target.files[0] || null;
if (file == null) {
return;
}
printTextarea("loadFile: loading model: " + file.name + ", size: " + file.size + " bytes");
printTextarea('loadFile: please wait ...');
var reader = new FileReader();
reader.onload = function(event) {
var buf = new Uint8Array(reader.result);
storeFS(fname, buf);
}
reader.readAsArrayBuffer(file);
document.getElementById('fetch-whisper-tiny-en').style.display = 'none';
document.getElementById('fetch-whisper-base-en').style.display = 'none';
document.getElementById('fetch-whisper-small-en').style.display = 'none';
document.getElementById('fetch-whisper-tiny-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-base-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-small-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-medium-en-q5_0').style.display = 'none';
document.getElementById('fetch-whisper-large-q5_0' ).style.display = 'none';
document.getElementById('whisper-file' ).style.display = 'none';
document.getElementById('model-whisper-status' ).innerHTML = 'loaded model: ' + file.name;
}
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',
'small.en': 'https://whisper.ggerganov.com/ggml-model-whisper-small.en.bin',
'tiny-en-q5_1': 'https://whisper.ggerganov.com/ggml-model-whisper-tiny.en-q5_1.bin',
'base-en-q5_1': 'https://whisper.ggerganov.com/ggml-model-whisper-base.en-q5_1.bin',
'small-en-q5_1': 'https://whisper.ggerganov.com/ggml-model-whisper-small.en-q5_1.bin',
'medium-en-q5_0':'https://whisper.ggerganov.com/ggml-model-whisper-medium.en-q5_0.bin',
'large-q5_0': 'https://whisper.ggerganov.com/ggml-model-whisper-large-q5_0.bin',
};
let sizes = {
'tiny.en': 75,
'base.en': 142,
'small.en': 466,
'tiny-en-q5_1': 31,
'base-en-q5_1': 57,
'small-en-q5_1': 182,
'medium-en-q5_0': 515,
'large-q5_0': 1030,
};
let url = urls[model];
let dst = 'whisper.bin';
let size_mb = sizes[model];
document.getElementById('fetch-whisper-tiny-en').style.display = 'none';
document.getElementById('fetch-whisper-base-en').style.display = 'none';
document.getElementById('fetch-whisper-small-en').style.display = 'none';
document.getElementById('fetch-whisper-tiny-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-base-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-small-en-q5_1' ).style.display = 'none';
document.getElementById('fetch-whisper-medium-en-q5_0').style.display = 'none';
document.getElementById('fetch-whisper-large-q5_0' ).style.display = 'none';
document.getElementById('whisper-file' ).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('fetch-whisper-small-en'); if (el) el.style.display = 'inline-block';
el = document.getElementById('fetch-whisper-tiny-en-q5_1' ); if (el) el.style.display = 'inline-block';
el = document.getElementById('fetch-whisper-base-en-q5_1' ); if (el) el.style.display = 'inline-block';
el = document.getElementById('fetch-whisper-small-en-q5_1' ); if (el) el.style.display = 'inline-block';
el = document.getElementById('fetch-whisper-medium-en-q5_0'); if (el) el.style.display = 'inline-block';
el = document.getElementById('fetch-whisper-large-q5_0' ); if (el) el.style.display = 'inline-block';
el = document.getElementById('whisper-file' ); 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);
}
//
// main
//
function onBench() {
if (instance) {
Module.free(instance);
}
instance = Module.init('whisper.bin');
if (instance) {
printTextarea("js: whisper initialized, instance: " + instance);
}
document.getElementById('bench').disabled = true;
if (!instance) {
printTextarea("js: failed to initialize whisper");
return;
}
}
</script>
<script type="text/javascript" src="bench.js"></script>
</body>
</html>