ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-17 22:38:07 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

wasm : refactor wasm example + reuse fetch mechanism

Browse Source
This commit is contained in:
Georgi Gerganov
2022-11-24 23:13:26 +02:00
parent ff36415a86
commit e4805d9601
7 changed files with 264 additions and 379 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/talk.wasm/CMakeLists.txt
View File

@ -45,3 +45,4 @@ set_target_properties(${TARGET} PROPERTIES LINK_FLAGS " \
set(TARGET talk.wasm)
configure_file(${CMAKE_CURRENT_SOURCE_DIR}/index-tmpl.html ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/${TARGET}/index.html @ONLY)
configure_file(${CMAKE_CURRENT_SOURCE_DIR}/../helpers.js ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/${TARGET}/helpers.js @ONLY)

5
examples/talk.wasm/README.md
View File

@ -61,9 +61,8 @@ emcmake cmake ..
make -j
# copy the produced page to your HTTP path
cp bin/talk.wasm/index.html /path/to/html/
cp bin/talk.wasm/talk.js /path/to/html/
cp bin/libtalk.worker.js /path/to/html/
cp bin/talk.wasm/* /path/to/html/
cp bin/libtalk.worker.js /path/to/html/
```
## Feedback

6
examples/talk.wasm/emscripten.cpp
View File

@ -62,7 +62,7 @@ void talk_main(size_t index) {
wparams.print_special_tokens = false;
wparams.max_tokens = 32;
wparams.audio_ctx = 768;
wparams.audio_ctx = 768; // partial encoder context for better performance
wparams.language = "en";
@ -133,7 +133,7 @@ void talk_main(size_t index) {
}
}
talk_set_status("processing ...");
talk_set_status("processing audio (whisper)...");
t_last = t_now;
@ -192,7 +192,7 @@ void talk_main(size_t index) {
text_heard = std::regex_replace(text_heard, std::regex("^\\s+"), "");
text_heard = std::regex_replace(text_heard, std::regex("\\s+$"), "");
talk_set_status("'" + text_heard + "' - thinking how to respond ...");
talk_set_status("'" + text_heard + "' - thinking how to respond (gpt-2) ...");
const std::vector<gpt_vocab::id> tokens = gpt2_tokenize(g_gpt2, text_heard.c_str());

226
examples/talk.wasm/index-tmpl.html
View File

@ -51,7 +51,7 @@
<br><br>
<div id="model-whisper">
<span id="model-whisper-status">Whisper model:</span>
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>
@ -64,7 +64,7 @@
<br>
<div id="model-gpt-2">
<span id="model-gpt-2-status">GPT-2 model:</span>
GPT-2 model: <span id="model-gpt-2-status"></span>
<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>
@ -158,20 +158,8 @@
</div>
</div>
<script type="text/javascript" src="helpers.js"></script>
<script type='text/javascript'>
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
}
};
})();
const kRestartRecording_s = 15;
const kSampleRate = 16000;
@ -218,6 +206,7 @@
if (voices.length == 0) {
el.innerHTML = '<option value="0">No voices available</option>';
} else {
// populate voice list
var n = 0;
voices.forEach(function(voice, i) {
if (!voice.lang.startsWith('en')) return;
@ -245,17 +234,14 @@
}
};
// 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
//
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
@ -267,176 +253,21 @@
Module.FS_createDataFile("/", fname, buf, true, true);
printTextarea('js: stored model: ' + fname + ' size: ' + buf.length);
printTextarea('storeFS: stored model: ' + fname + ' size: ' + buf.length);
if (fname == 'whisper.bin') {
document.getElementById('model-whisper').innerHTML = 'Whisper model: loaded "' + model_whisper + '"!';
document.getElementById('model-whisper-status').innerHTML = 'loaded "' + model_whisper + '"!';
} else if (fname == 'gpt-2.bin') {
document.getElementById('model-gpt-2').innerHTML = 'GPT-2 model: loaded "' + model_gpt_2 + '"!';
document.getElementById('model-gpt-2-status').innerHTML = 'loaded "' + model_gpt_2 + '"!';
}
if (model_whisper != null && model_gpt_2 != null) {
document.getElementById('start').disabled = false;
document.getElementById('stop').disabled = false;
document.getElementById('stop' ).disabled = false;
document.getElementById('voice').disabled = false;
}
}
let dbVersion = 1
let dbName = 'whisper.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
elProgress.innerHTML = Math.round((receivedLength / total) * 100) + '%';
var progressCur = Math.round((receivedLength / total) * 10);
if (progressCur != progressLast) {
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, size_mb) {
// 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');
// alert and ask the user to confirm
if (!confirm('You are about to download ' + size_mb + ' MB of data.\nThe model data will be cached in the browser for future use.\n\nPress OK to continue.')) {
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-gpt-2-small') ; if (el) el.style.display = 'inline-block';
return;
}
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://whisper.ggerganov.com/ggml-model-whisper-tiny.en.bin',
@ -450,16 +281,27 @@
let url = urls[model];
let dst = 'whisper.bin';
let el = document.getElementById('fetch-whisper-progress');
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 = 'Whisper model: loading "' + model + '" ... ';
document.getElementById('model-whisper-status').innerHTML = 'loading "' + model + '" ... ';
loadRemote(url, dst, el, size_mb);
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);
}
function loadGPT2(model) {
@ -475,15 +317,25 @@
let url = urls[model];
let dst = 'gpt-2.bin';
let el = document.getElementById('fetch-gpt-2-progress');
let size_mb = sizes[model];
model_gpt_2 = model;
document.getElementById('fetch-gpt-2-small').style.display = 'none';
document.getElementById('model-gpt-2-status').innerHTML = 'GPT-2 model: loading "' + model + '" ... ';
document.getElementById('model-gpt-2-status').innerHTML = 'loading "' + model + '" ... ';
loadRemote(url, dst, el, size_mb);
cbProgress = function(p) {
let el = document.getElementById('fetch-gpt-2-progress');
el.innerHTML = Math.round(100*p) + '%';
};
cbCancel = function() {
var el;
el = document.getElementById('fetch-gpt-2-small') ; if (el) el.style.display = 'inline-block';
el = document.getElementById('model-gpt-2-status'); if (el) el.innerHTML = '';
};
loadRemote(url, dst, size_mb, cbProgress, storeFS, cbCancel, printTextarea);
}
//