mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-08-14 13:39:16 +02:00
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
This commit is contained in:
Georgi Gerganov
GitHub
@ -31,9 +31,9 @@ endif()
|
||||
set_target_properties(${TARGET} PROPERTIES LINK_FLAGS " \
|
||||
--bind \
|
||||
-s USE_PTHREADS=1 \
|
||||
-s PTHREAD_POOL_SIZE=8 \
|
||||
-s INITIAL_MEMORY=1024MB \
|
||||
-s TOTAL_MEMORY=1024MB \
|
||||
-s PTHREAD_POOL_SIZE_STRICT=0 \
|
||||
-s INITIAL_MEMORY=2000MB \
|
||||
-s TOTAL_MEMORY=2000MB \
|
||||
-s FORCE_FILESYSTEM=1 \
|
||||
-s EXPORTED_RUNTIME_METHODS=\"['print', 'printErr', 'ccall', 'cwrap']\" \
|
||||
${EXTRA_FLAGS} \
|
||||
|
||||
@ -35,6 +35,15 @@
|
||||
|
||||
<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>
|
||||
@ -44,11 +53,18 @@
|
||||
|
||||
<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>
|
||||
<span id="fetch-whisper-progress"></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>
|
||||
@ -160,6 +176,14 @@
|
||||
|
||||
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;
|
||||
}
|
||||
@ -168,19 +192,42 @@
|
||||
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-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) {
|
||||
@ -190,9 +237,18 @@
|
||||
|
||||
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 = '';
|
||||
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);
|
||||
|
||||
Reference in New Issue
Block a user