You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
565 lines
22 KiB
565 lines
22 KiB
<!doctype html>
|
|
<html lang="en-us">
|
|
<head>
|
|
<title>talk : GPT-2 meets Whisper in 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>talk : GPT-2 meets Whisper in WebAssembly</b>
|
|
|
|
<br><br>
|
|
|
|
WIP IN PROGRESS
|
|
|
|
<br><br><hr>
|
|
|
|
<div id="model-whisper">
|
|
Whisper Model:
|
|
<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="model-gpt-2">
|
|
GPT-2 Model:
|
|
<button id="fetch-gpt-2-small" onclick="loadGPT2('small')">small 117M (240 MB)</button>
|
|
<!--<button id="fetch-gpt-2-medium" onclick="loadGPT2('medium')">medium 345M (720 MB)</button>-->
|
|
<span id="fetch-gpt-2-progress"></span>
|
|
|
|
<!--
|
|
<input type="file" id="file" name="file" onchange="loadFile(event, 'gpt-2.bin')" />
|
|
-->
|
|
</div>
|
|
|
|
<br>
|
|
|
|
<div id="input_mic">
|
|
<button id="start" onclick="onStart()">Start</button>
|
|
<button id="stop" onclick="onStop()" disabled>Stop</button>
|
|
<button id="speak" onclick="speakTest()">Speak</button>
|
|
<button id="speak" onclick="clearCache()">Clear Cache</button>
|
|
</div>
|
|
|
|
<audio controls="controls" id="audio" loop hidden>
|
|
Your browser does not support the <audio> tag.
|
|
<source id="source" src="" type="audio/wav" />
|
|
</audio>
|
|
|
|
<hr><br>
|
|
|
|
<br>
|
|
|
|
<!-- textarea with height filling the rest of the page -->
|
|
<textarea id="output" rows="20"></textarea>
|
|
|
|
<br><br>
|
|
|
|
<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/talk">Source Code</a> |
|
|
</span>
|
|
</div>
|
|
</div>
|
|
|
|
<script type='text/javascript'>
|
|
// TODO: convert audio buffer to WAV
|
|
function setAudio(audio) {
|
|
//if (audio) {
|
|
// // convert to 16-bit PCM
|
|
// var blob = new Blob([audio], { type: 'audio/wav' });
|
|
// var url = URL.createObjectURL(blob);
|
|
// document.getElementById('source').src = url;
|
|
// document.getElementById('audio').hidden = false;
|
|
// document.getElementById('audio').loop = false;
|
|
// document.getElementById('audio').load();
|
|
//} else {
|
|
// document.getElementById('audio').hidden = true;
|
|
//}
|
|
}
|
|
|
|
function changeInput(input) {
|
|
if (input == 'file') {
|
|
document.getElementById('input_file').style.display = 'block';
|
|
document.getElementById('input_mic').style.display = 'none';
|
|
} else {
|
|
document.getElementById('input_file').style.display = 'none';
|
|
document.getElementById('input_mic').style.display = 'block';
|
|
}
|
|
}
|
|
|
|
var printTextarea = (function() {
|
|
var element = document.getElementById('output');
|
|
if (element) element.alue = ''; // clear browser cache
|
|
return function(text) {
|
|
if (arguments.length > 1) text = Array.prototype.slice.call(arguments).join(' ');
|
|
console.log(text);
|
|
if (element) {
|
|
element.value += text + "\n";
|
|
element.scrollTop = element.scrollHeight; // focus on bottom
|
|
}
|
|
};
|
|
})();
|
|
|
|
var Module = {
|
|
print: printTextarea,
|
|
printErr: printTextarea,
|
|
setStatus: function(text) {
|
|
printTextarea('js: ' + text);
|
|
},
|
|
monitorRunDependencies: function(left) {
|
|
}
|
|
};
|
|
|
|
const kMaxAudio_s = 10;
|
|
const kRestartRecording_s = 15;
|
|
const kSampleRate = 16000;
|
|
|
|
window.AudioContext = window.AudioContext || window.webkitAudioContext;
|
|
window.OfflineAudioContext = window.OfflineAudioContext || window.webkitOfflineAudioContext;
|
|
|
|
// web audio context
|
|
var context = null;
|
|
|
|
// audio data
|
|
var audio = null;
|
|
var audio0 = null;
|
|
|
|
// the talk instance
|
|
var instance = null;
|
|
|
|
// speech synthesis
|
|
const synth = window.speechSynthesis;
|
|
|
|
// helper function
|
|
function convertTypedArray(src, type) {
|
|
var buffer = new ArrayBuffer(src.byteLength);
|
|
var baseView = new src.constructor(buffer).set(src);
|
|
return new type(buffer);
|
|
}
|
|
|
|
//
|
|
// fetch models
|
|
//
|
|
|
|
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('js: stored model: ' + fname + ' size: ' + buf.length);
|
|
}
|
|
|
|
let dbVersion = 1
|
|
let dbName = 'talk.ggerganov.com';
|
|
let indexedDB = window.indexedDB || window.mozIndexedDB || window.webkitIndexedDB || window.msIndexedDB
|
|
|
|
// fetch a remote file from remote URL using the Fetch API
|
|
async function fetchRemote(url, elProgress) {
|
|
printTextarea('js: downloading with fetch()...');
|
|
|
|
const response = await fetch(
|
|
url,
|
|
{
|
|
method: 'GET',
|
|
headers: {
|
|
'Content-Type': 'application/octet-stream',
|
|
},
|
|
}
|
|
);
|
|
|
|
if (!response.ok) {
|
|
printTextarea('js: failed to fetch ' + url);
|
|
return;
|
|
}
|
|
|
|
const contentLength = response.headers.get('content-length');
|
|
const total = parseInt(contentLength, 10);
|
|
const reader = response.body.getReader();
|
|
|
|
var chunks = [];
|
|
var receivedLength = 0;
|
|
var progressLast = -1;
|
|
|
|
while (true) {
|
|
const { done, value } = await reader.read();
|
|
|
|
if (done) {
|
|
break;
|
|
}
|
|
|
|
chunks.push(value);
|
|
receivedLength += value.length;
|
|
|
|
if (contentLength) {
|
|
// update progress bar element with the new percentage
|
|
var progressCur = Math.round((receivedLength / total) * 10);
|
|
if (progressCur != progressLast) {
|
|
elProgress.innerHTML = 10*progressCur + '%';
|
|
printTextarea('js: fetching ' + 10*progressCur + '% ...');
|
|
progressLast = progressCur;
|
|
}
|
|
}
|
|
}
|
|
|
|
var chunksAll = new Uint8Array(receivedLength);
|
|
var position = 0;
|
|
for (var chunk of chunks) {
|
|
chunksAll.set(chunk, position);
|
|
position += chunk.length;
|
|
}
|
|
|
|
return chunksAll;
|
|
}
|
|
|
|
// load remote data
|
|
// - check if the data is already in the IndexedDB
|
|
// - if not, fetch it from the remote URL and store it in the IndexedDB
|
|
// - store it in WASM memory
|
|
function loadRemote(url, dst, elProgress) {
|
|
// query the storage quota and print it
|
|
navigator.storage.estimate().then(function (estimate) {
|
|
printTextarea('js: storage quota: ' + estimate.quota + ' bytes');
|
|
printTextarea('js: storage usage: ' + estimate.usage + ' bytes');
|
|
});
|
|
|
|
// check if the data is already in the IndexedDB
|
|
var request = indexedDB.open(dbName, dbVersion);
|
|
|
|
request.onupgradeneeded = function (event) {
|
|
var db = event.target.result;
|
|
if (db.version == 1) {
|
|
var objectStore = db.createObjectStore('models', { autoIncrement: false });
|
|
printTextarea('js: created IndexedDB ' + db.name + ' version ' + db.version);
|
|
} else {
|
|
// clear the database
|
|
var objectStore = event.currentTarget.transaction.objectStore('models');
|
|
objectStore.clear();
|
|
printTextarea('js: cleared IndexedDB ' + db.name + ' version ' + db.version);
|
|
}
|
|
};
|
|
|
|
request.onsuccess = function (event) {
|
|
var db = event.target.result;
|
|
var transaction = db.transaction(['models'], 'readonly');
|
|
var objectStore = transaction.objectStore('models');
|
|
var request = objectStore.get(url);
|
|
|
|
request.onsuccess = function (event) {
|
|
if (request.result) {
|
|
printTextarea('js: "' + url + '" is already in the IndexedDB');
|
|
storeFS(dst, request.result);
|
|
} else {
|
|
// data is not in the IndexedDB
|
|
printTextarea('js: "' + url + '" is not in the IndexedDB');
|
|
|
|
fetchRemote(url, elProgress).then(function (data) {
|
|
if (data) {
|
|
// store the data in the IndexedDB
|
|
var request = indexedDB.open(dbName, dbVersion);
|
|
request.onsuccess = function (event) {
|
|
var db = event.target.result;
|
|
var transaction = db.transaction(['models'], 'readwrite');
|
|
var objectStore = transaction.objectStore('models');
|
|
var request = objectStore.put(data, url);
|
|
|
|
request.onsuccess = function (event) {
|
|
printTextarea('js: "' + url + '" stored in the IndexedDB');
|
|
storeFS(dst, data);
|
|
};
|
|
|
|
request.onerror = function (event) {
|
|
printTextarea('js: failed to store "' + url + '" in the IndexedDB');
|
|
};
|
|
};
|
|
}
|
|
});
|
|
}
|
|
};
|
|
|
|
request.onerror = function (event) {
|
|
printTextarea('js: failed to get data from the IndexedDB');
|
|
};
|
|
};
|
|
|
|
request.onerror = function (event) {
|
|
printTextarea('js: failed to open IndexedDB');
|
|
};
|
|
|
|
request.onblocked = function (event) {
|
|
printTextarea('js: failed to open IndexedDB: blocked');
|
|
};
|
|
|
|
request.onabort = function (event) {
|
|
printTextarea('js: failed to open IndexedDB: abort');
|
|
};
|
|
}
|
|
|
|
function loadWhisper(model) {
|
|
let urls = {
|
|
'tiny.en': 'https://talk.ggerganov.com/ggml-model-whisper-tiny.en.bin',
|
|
'base.en': 'https://talk.ggerganov.com/ggml-model-whisper-base.en.bin',
|
|
};
|
|
|
|
let url = urls[model];
|
|
let dst = 'whisper.bin';
|
|
let el = document.getElementById('fetch-whisper-progress');
|
|
|
|
loadRemote(url, dst, el);
|
|
}
|
|
|
|
function loadGPT2(model) {
|
|
let urls = {
|
|
'small': 'https://talk.ggerganov.com/ggml-model-gpt-2-117M.bin',
|
|
'medium': 'https://talk.ggerganov.com/ggml-model-gpt-2-345M.bin',
|
|
};
|
|
|
|
let url = urls[model];
|
|
let dst = 'gpt-2.bin';
|
|
let el = document.getElementById('fetch-gpt-2-progress');
|
|
|
|
loadRemote(url, dst, el);
|
|
}
|
|
|
|
//
|
|
// microphone
|
|
//
|
|
|
|
var mediaRecorder = null;
|
|
var doRecording = false;
|
|
var startTime = 0;
|
|
|
|
function stopRecording() {
|
|
doRecording = false;
|
|
audio0 = null;
|
|
audio = null;
|
|
}
|
|
|
|
function startRecording() {
|
|
if (!context) {
|
|
context = new AudioContext({sampleRate: 16000});
|
|
}
|
|
|
|
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);
|
|
|
|
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);
|
|
}
|
|
|
|
setAudio(audio);
|
|
});
|
|
}, function(e) {
|
|
printTextarea('js: error decoding audio: ' + e);
|
|
audio = null;
|
|
setAudio(audio);
|
|
});
|
|
}
|
|
|
|
reader.readAsArrayBuffer(blob);
|
|
};
|
|
|
|
mediaRecorder.onstop = function(e) {
|
|
if (doRecording) {
|
|
setTimeout(function() {
|
|
startRecording();
|
|
});
|
|
}
|
|
};
|
|
|
|
mediaRecorder.start(250);
|
|
})
|
|
.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();
|
|
});
|
|
}
|
|
}
|
|
}, 250);
|
|
}
|
|
|
|
//
|
|
// speak
|
|
//
|
|
|
|
var voice = null;
|
|
|
|
function onSpeak(text) {
|
|
var voices = synth.getVoices();
|
|
var msg = new SpeechSynthesisUtterance(text);
|
|
|
|
if (voice == null) {
|
|
//voice = voices[Math.floor(Math.random() * 2)];
|
|
voice = voices[0];
|
|
}
|
|
|
|
msg.voice = voice;
|
|
synth.speak(msg);
|
|
|
|
if (doRecording) {
|
|
printTextarea('js: speaking');
|
|
stopRecording();
|
|
var interval = setInterval(function() {
|
|
if (!synth.speaking) {
|
|
printTextarea('js: done speaking');
|
|
clearInterval(interval);
|
|
startRecording();
|
|
}
|
|
}, 100);
|
|
}
|
|
}
|
|
|
|
async function clearCache() {
|
|
if (confirm('Are you sure you want to clear the cache?\nAll the models will be downloaded again.')) {
|
|
const dbs = await window.indexedDB.databases();
|
|
dbs.forEach(db => { window.indexedDB.deleteDatabase(db.name) });
|
|
}
|
|
}
|
|
|
|
//
|
|
// main
|
|
//
|
|
|
|
var intervalSpeak = null;
|
|
|
|
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();
|
|
|
|
intervalSpeak = setInterval(function() {
|
|
var textToSpeak = Module.get_text_to_speak();
|
|
|
|
if (textToSpeak != null && textToSpeak.length > 1) {
|
|
onSpeak(textToSpeak);
|
|
}
|
|
}, 100);
|
|
}
|
|
|
|
function onStop() {
|
|
stopRecording();
|
|
|
|
if (instance) {
|
|
Module.free(instance);
|
|
instance = null;
|
|
|
|
printTextarea("js: talk instance freed");
|
|
}
|
|
}
|
|
|
|
</script>
|
|
<script type="text/javascript" src="talk.js"></script>
|
|
</body>
|
|
</html>
|