Duplicate from radames/whisper.wasm

Co-authored-by: Radamés Ajna <radames@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,3 @@
+FROM nginxinc/nginx-unprivileged  
+COPY ./nginx.conf /etc/nginx/conf.d/default.conf
+COPY . /usr/share/nginx/html

README.md

@@ -0,0 +1,14 @@
+---
+title: Whisper.cpp WASM
+emoji: 📉
+colorFrom: red
+colorTo: green
+sdk: docker
+pinned: false
+app_port: 8080
+duplicated_from: radames/whisper.wasm
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Models on https://huggingface.co/datasets/ggerganov/whisper.cpp

ggml-tiny.en.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921e4cf8686fdd993dcd081a5da5b6c365bfde1162e72b08d75ac75289920b1f
+size 77704715

helpers.js

@@ -0,0 +1,182 @@
+// Common Javascript functions used by the examples
+
+function convertTypedArray(src, type) {
+    var buffer = new ArrayBuffer(src.byteLength);
+    var baseView = new src.constructor(buffer).set(src);
+    return new type(buffer);
+}
+
+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
+        }
+    };
+})();
+
+async function clearCache() {
+    if (confirm('Are you sure you want to clear the cache?\nAll the models will be downloaded again.')) {
+        indexedDB.deleteDatabase(dbName);
+    }
+}
+
+// fetch a remote file from remote URL using the Fetch API
+async function fetchRemote(url, cbProgress, cbPrint) {
+    cbPrint('fetchRemote: downloading with fetch()...');
+
+    const response = await fetch(
+        url,
+        {
+            method: 'GET',
+            headers: {
+                'Content-Type': 'application/octet-stream',
+            },
+        }
+    );
+
+    if (!response.ok) {
+        cbPrint('fetchRemote: 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) {
+            cbProgress(receivedLength/total);
+
+            var progressCur = Math.round((receivedLength / total) * 10);
+            if (progressCur != progressLast) {
+                cbPrint('fetchRemote: fetching ' + 10*progressCur + '% ...');
+                progressLast = progressCur;
+            }
+        }
+    }
+
+    var position = 0;
+    var chunksAll = new Uint8Array(receivedLength);
+
+    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
+function loadRemote(url, dst, size_mb, cbProgress, cbReady, cbCancel, cbPrint) {
+    // query the storage quota and print it
+    navigator.storage.estimate().then(function (estimate) {
+        cbPrint('loadRemote: storage quota: ' + estimate.quota + ' bytes');
+        cbPrint('loadRemote: storage usage: ' + estimate.usage + ' bytes');
+    });
+
+    // check if the data is already in the IndexedDB
+    var rq = indexedDB.open(dbName, dbVersion);
+
+    rq.onupgradeneeded = function (event) {
+        var db = event.target.result;
+        if (db.version == 1) {
+            var os = db.createObjectStore('models', { autoIncrement: false });
+            cbPrint('loadRemote: created IndexedDB ' + db.name + ' version ' + db.version);
+        } else {
+            // clear the database
+            var os = event.currentTarget.transaction.objectStore('models');
+            os.clear();
+            cbPrint('loadRemote: cleared IndexedDB ' + db.name + ' version ' + db.version);
+        }
+    };
+
+    rq.onsuccess = function (event) {
+        var db = event.target.result;
+        var tx = db.transaction(['models'], 'readonly');
+        var os = tx.objectStore('models');
+        var rq = os.get(url);
+
+        rq.onsuccess = function (event) {
+            if (rq.result) {
+                cbPrint('loadRemote: "' + url + '" is already in the IndexedDB');
+                cbReady(dst, rq.result);
+            } else {
+                // data is not in the IndexedDB
+                cbPrint('loadRemote: "' + 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.\n' +
+                    'The model data will be cached in the browser for future use.\n\n' +
+                    'Press OK to continue.')) {
+                    cbCancel();
+                    return;
+                }
+
+                fetchRemote(url, cbProgress, cbPrint).then(function (data) {
+                    if (data) {
+                        // store the data in the IndexedDB
+                        var rq = indexedDB.open(dbName, dbVersion);
+                        rq.onsuccess = function (event) {
+                            var db = event.target.result;
+                            var tx = db.transaction(['models'], 'readwrite');
+                            var os = tx.objectStore('models');
+                            var rq = os.put(data, url);
+
+                            rq.onsuccess = function (event) {
+                                cbPrint('loadRemote: "' + url + '" stored in the IndexedDB');
+                                cbReady(dst, data);
+                            };
+
+                            rq.onerror = function (event) {
+                                cbPrint('loadRemote: failed to store "' + url + '" in the IndexedDB');
+                                cbCancel();
+                            };
+                        };
+                    }
+                });
+            }
+        };
+
+        rq.onerror = function (event) {
+            cbPrint('loadRemote: failed to get data from the IndexedDB');
+            cbCancel();
+        };
+    };
+
+    rq.onerror = function (event) {
+        cbPrint('loadRemote: failed to open IndexedDB');
+        cbCancel();
+    };
+
+    rq.onblocked = function (event) {
+        cbPrint('loadRemote: failed to open IndexedDB: blocked');
+        cbCancel();
+    };
+
+    rq.onabort = function (event) {
+        cbPrint('loadRemote: failed to open IndexedDB: abort');
+
+    };
+}
+

index.html

@@ -0,0 +1,582 @@
+<!doctype html>
+<html lang="en-us">
+
+<head>
+    <title>whisper.cpp : WASM example</title>
+
+    <style>
+        body {
+            background-color: white;
+        }
+
+        #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">
+        <div id="warning" style="display: none; padding: 1rem;">
+            <b style="color: red ; font-size: large;">Warning: your browser does not support SharedArrayBuffer please
+                try open the page in a new tab.
+            </b> <a href="https://radames-whisper-wasm.hf.space"
+                target="_blank">https://radames-whisper-wasm.hf.space</a>
+        </div>
+        <b>Minimal <a target="_blank" href="https://github.com/ggerganov/whisper.cpp">whisper.cpp</a> example running
+            fully in the browser</b>
+
+        <br><br>
+
+        Usage instructions:<br>
+        <ul>
+            <li>Load a ggml model file (you can obtain one from <a target="_blank"
+                    href="https://ggml.ggerganov.com/">here</a>, recommended: <b>tiny</b> or <b>base</b>)</li>
+            <li>Select audio file to transcribe or record audio from the microphone (sample: <a target="_blank"
+                    href="https://whisper.ggerganov.com/jfk.wav">jfk.wav</a>)</li>
+            <li>Click on the "Transcribe" button to start the transcription</li>
+        </ul>
+
+        Note that the computation is quite heavy and may take a few seconds to complete.<br>
+        The transcription results will be displayed in the text area below.<br><br>
+        <b>Important: your browser must support WASM SIMD instructions for this to work.</b>
+
+        <br><br>
+        <hr>
+
+        <div id="model">
+            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-tiny" onclick="loadWhisper('tiny')">tiny (75 MB)</button>
+            <button id="fetch-whisper-base-en" onclick="loadWhisper('base.en')">base.en (142 MB)</button>
+            <button id="fetch-whisper-base" onclick="loadWhisper('base')">base (142 MB)</button>
+            <span id="fetch-whisper-progress"></span>
+
+            <input type="file" id="whisper-file" name="file" onchange="loadFile(event, 'whisper.bin')" />
+        </div>
+
+        <br>
+
+        <!-- radio button to select between file upload or microphone -->
+        <div id="input">
+            Input:
+            <input type="radio" id="file" name="input" value="file" checked="checked" onchange="changeInput('file')" />
+            File
+            <input type="radio" id="mic" name="input" value="mic" onchange="changeInput('mic')" /> Microphone
+        </div>
+
+        <br>
+
+        <div id="input_file">
+            Audio file:
+            <input type="file" id="file" name="file" onchange="loadAudio(event)" />
+        </div>
+
+        <div id="input_mic" style="display: none;">
+            Microphone:
+            <button id="start" onclick="startRecording()">Start</button>
+            <button id="stop" onclick="stopRecording()" disabled>Stop</button>
+
+            <!-- progress bar to show recording progress -->
+            <br><br>
+            <div id="progress" style="display: none;">
+                <div id="progress-bar" style="width: 0%; height: 10px; background-color: #4CAF50;"></div>
+                <div id="progress-text">0%</div>
+            </div>
+        </div>
+
+        <audio controls="controls" id="audio" loop hidden>
+            Your browser does not support the &lt;audio&gt; tag.
+            <source id="source" src="" type="audio/wav" />
+        </audio>
+
+        <hr><br>
+
+        <table>
+            <tr>
+                <td>
+                    Language:
+                    <select id="language" name="language">
+                        <option value="en">English</option>
+                        <option value="ar">Arabic</option>
+                        <option value="hy">Armenian</option>
+                        <option value="az">Azerbaijani</option>
+                        <option value="eu">Basque</option>
+                        <option value="be">Belarusian</option>
+                        <option value="bn">Bengali</option>
+                        <option value="bg">Bulgarian</option>
+                        <option value="ca">Catalan</option>
+                        <option value="zh">Chinese</option>
+                        <option value="hr">Croatian</option>
+                        <option value="cs">Czech</option>
+                        <option value="da">Danish</option>
+                        <option value="nl">Dutch</option>
+                        <option value="en">English</option>
+                        <option value="et">Estonian</option>
+                        <option value="tl">Filipino</option>
+                        <option value="fi">Finnish</option>
+                        <option value="fr">French</option>
+                        <option value="gl">Galician</option>
+                        <option value="ka">Georgian</option>
+                        <option value="de">German</option>
+                        <option value="el">Greek</option>
+                        <option value="gu">Gujarati</option>
+                        <option value="iw">Hebrew</option>
+                        <option value="hi">Hindi</option>
+                        <option value="hu">Hungarian</option>
+                        <option value="is">Icelandic</option>
+                        <option value="id">Indonesian</option>
+                        <option value="ga">Irish</option>
+                        <option value="it">Italian</option>
+                        <option value="ja">Japanese</option>
+                        <option value="kn">Kannada</option>
+                        <option value="ko">Korean</option>
+                        <option value="la">Latin</option>
+                        <option value="lv">Latvian</option>
+                        <option value="lt">Lithuanian</option>
+                        <option value="mk">Macedonian</option>
+                        <option value="ms">Malay</option>
+                        <option value="mt">Maltese</option>
+                        <option value="no">Norwegian</option>
+                        <option value="fa">Persian</option>
+                        <option value="pl">Polish</option>
+                        <option value="pt">Portuguese</option>
+                        <option value="ro">Romanian</option>
+                        <option value="ru">Russian</option>
+                        <option value="sr">Serbian</option>
+                        <option value="sk">Slovak</option>
+                        <option value="sl">Slovenian</option>
+                        <option value="es">Spanish</option>
+                        <option value="sw">Swahili</option>
+                        <option value="sv">Swedish</option>
+                        <option value="ta">Tamil</option>
+                        <option value="te">Telugu</option>
+                        <option value="th">Thai</option>
+                        <option value="tr">Turkish</option>
+                        <option value="uk">Ukrainian</option>
+                        <option value="ur">Urdu</option>
+                        <option value="vi">Vietnamese</option>
+                        <option value="cy">Welsh</option>
+                        <option value="yi">Yiddish</option>
+                    </select>
+                </td>
+                <td>
+                    <button onclick="onProcess(false);">Transcribe</button>
+                </td>
+                <td>
+                    <button onclick="onProcess(true);">Translate</button>
+                </td>
+            </tr>
+        </table>
+
+        <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">Mon Jan 16 11:57:35 2023</span> |
+                Commit hash: <a class="nav-link" target="_blank"
+                    href="https://github.com/ggerganov/whisper.cpp/commit/49b529ba">49b529ba</a> |
+                Commit subject: <span class="nav-link">whisper.android : add support for loading directly from asset in
+                    C (#415)</span> |
+                <a class="nav-link" target="_blank"
+                    href="https://github.com/ggerganov/whisper.cpp/tree/master/examples/whisper.wasm">Source Code</a> |
+            </span>
+        </div>
+    </div>
+
+    <script type="text/javascript" src="helpers.js"></script>
+    <script type='text/javascript'>
+        document.addEventListener("DOMContentLoaded", () => {
+            //check is shared array buffer is supported
+            if (!window.SharedArrayBuffer) {
+                document.querySelector("#warning").style.display = "block";
+            }
+        })
+        // 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';
+                document.getElementById('progress').style.display = 'none';
+            } else {
+                document.getElementById('input_file').style.display = 'none';
+                document.getElementById('input_mic').style.display = 'block';
+                document.getElementById('progress').style.display = 'block';
+            }
+        }
+
+        var Module = {
+            print: printTextarea,
+            printErr: printTextarea,
+            setStatus: function (text) {
+                printTextarea('js: ' + text);
+            },
+            monitorRunDependencies: function (left) {
+            }
+        };
+
+        // web audio context
+        var context = null;
+
+        // audio data
+        var audio = null;
+
+        // the whisper instance
+        var instance = null;
+        var model_whisper = '';
+
+        // helper function
+        function convertTypedArray(src, type) {
+            var buffer = new ArrayBuffer(src.byteLength);
+            var baseView = new src.constructor(buffer).set(src);
+            return new type(buffer);
+        }
+
+        //
+        // load model
+        //
+
+        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);
+
+            model_whisper = fname;
+
+            document.getElementById('model-whisper-status').innerHTML = 'loaded "' + model_whisper + '"!';
+
+            printTextarea('storeFS: stored model: ' + fname + ' size: ' + buf.length);
+        }
+
+        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-tiny').style.display = 'none';
+            document.getElementById('fetch-whisper-base').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': 'models/ggml-tiny.en.bin',
+                'tiny': 'models/ggml-tiny.bin',
+                'base.en': 'models/ggml-base.en.bin',
+                'base': 'models/ggml-base.bin',
+            };
+
+            let sizes = {
+                'tiny.en': 75,
+                'tiny': 75,
+                'base.en': 142,
+                'base': 142,
+            };
+
+            let url = urls[model];
+            let dst = 'whisper.bin';
+            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('fetch-whisper-tiny').style.display = 'none';
+            document.getElementById('fetch-whisper-base').style.display = 'none';
+            document.getElementById('whisper-file').style.display = 'none';
+            document.getElementById('model-whisper-status').innerHTML = 'loading model: ' + 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-tiny'); if (el) el.style.display = 'inline-block';
+                el = document.getElementById('fetch-whisper-base'); 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);
+        }
+
+        //
+        // audio file
+        //
+
+        const kMaxAudio_s = 120;
+        const kSampleRate = 16000;
+
+        window.AudioContext = window.AudioContext || window.webkitAudioContext;
+        window.OfflineAudioContext = window.OfflineAudioContext || window.webkitOfflineAudioContext;
+
+        function loadAudio(event) {
+            if (!context) {
+                context = new AudioContext({
+                    sampleRate: kSampleRate,
+                    channelCount: 1,
+                    echoCancellation: false,
+                    autoGainControl: true,
+                    noiseSuppression: true,
+                });
+            }
+
+            var file = event.target.files[0] || null;
+            if (file == null) {
+                return;
+            }
+
+            printTextarea('js: loading audio: ' + file.name + ', size: ' + file.size + ' bytes');
+            printTextarea('js: please wait ...');
+
+            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 loaded, size: ' + audio.length);
+
+                        // truncate to first 30 seconds
+                        if (audio.length > kMaxAudio_s * kSampleRate) {
+                            audio = audio.slice(0, kMaxAudio_s * kSampleRate);
+                            printTextarea('js: truncated audio to first ' + kMaxAudio_s + ' seconds');
+                        }
+
+                        setAudio(audio);
+                    });
+                }, function (e) {
+                    printTextarea('js: error decoding audio: ' + e);
+                    audio = null;
+                    setAudio(audio);
+                });
+            }
+            reader.readAsArrayBuffer(file);
+        }
+
+        //
+        // microphone
+        //
+
+        var mediaRecorder = null;
+        var doRecording = false;
+        var startTime = 0;
+
+        function stopRecording() {
+            doRecording = false;
+        }
+
+        // record up to kMaxAudio_s seconds of audio from the microphone
+        // check if doRecording is false every 1000 ms and stop recording if so
+        // update progress information
+        function startRecording() {
+            if (!context) {
+                context = new AudioContext({
+                    sampleRate: kSampleRate,
+                    channelCount: 1,
+                    echoCancellation: false,
+                    autoGainControl: true,
+                    noiseSuppression: true,
+                });
+            }
+
+            document.getElementById('start').disabled = true;
+            document.getElementById('stop').disabled = false;
+
+            document.getElementById('progress-bar').style.width = '0%';
+            document.getElementById('progress-text').innerHTML = '0%';
+
+            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);
+                    };
+                    mediaRecorder.onstop = function (e) {
+                        var blob = new Blob(chunks, { 'type': 'audio/ogg; codecs=opus' });
+                        chunks = [];
+
+                        document.getElementById('start').disabled = false;
+                        document.getElementById('stop').disabled = true;
+
+                        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);
+
+                                    // truncate to first 30 seconds
+                                    if (audio.length > kMaxAudio_s * kSampleRate) {
+                                        audio = audio.slice(0, kMaxAudio_s * kSampleRate);
+                                        printTextarea('js: truncated audio to first ' + kMaxAudio_s + ' seconds');
+                                    }
+                                    setAudio(audio);
+                                });
+                            }, function (e) {
+                                printTextarea('js: error decoding audio: ' + e);
+                                audio = null;
+                                setAudio(audio);
+                            });
+                        }
+
+                        reader.readAsArrayBuffer(blob);
+                    };
+                    mediaRecorder.start();
+                })
+                .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('progress-bar').style.width = (100 * (Date.now() - startTime) / 1000 / kMaxAudio_s) + '%';
+                document.getElementById('progress-text').innerHTML = (100 * (Date.now() - startTime) / 1000 / kMaxAudio_s).toFixed(0) + '%';
+            }, 1000);
+
+            printTextarea('js: recording ...');
+
+            setTimeout(function () {
+                if (doRecording) {
+                    printTextarea('js: recording stopped after ' + kMaxAudio_s + ' seconds');
+                    stopRecording();
+                }
+            }, kMaxAudio_s * 1000);
+        }
+
+        //
+        // transcribe
+        //
+
+        function onProcess(translate) {
+            if (!instance) {
+                instance = Module.init('whisper.bin');
+
+                if (instance) {
+                    printTextarea("js: whisper initialized, instance: " + instance);
+                    document.getElementById('model').innerHTML = 'Model loaded: ' + model_whisper;
+                }
+            }
+
+            if (!instance) {
+                printTextarea("js: failed to initialize whisper");
+                return;
+            }
+
+            if (!audio) {
+                printTextarea("js: no audio data");
+                return;
+            }
+
+            if (instance) {
+                printTextarea('');
+                printTextarea('js: processing - this might take a while ...');
+                printTextarea('');
+
+                setTimeout(function () {
+                    var ret = Module.full_default(instance, audio, document.getElementById('language').value, translate);
+                    console.log('js: full_default returned: ' + ret);
+                    if (ret) {
+                        printTextarea("js: whisper returned: " + ret);
+                    }
+                }, 100);
+            }
+        }
+    </script>
+    <script type="text/javascript" src="main.js"></script>
+</body>
+
+</html>

libmain.worker.js

@@ -0,0 +1 @@
+"use strict";var Module={};var ENVIRONMENT_IS_NODE=typeof process=="object"&&typeof process.versions=="object"&&typeof process.versions.node=="string";if(ENVIRONMENT_IS_NODE){var nodeWorkerThreads=require("worker_threads");var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",data=>onmessage({data:data}));var fs=require("fs");Object.assign(global,{self:global,require:require,Module:Module,location:{href:__filename},Worker:nodeWorkerThreads.Worker,importScripts:function(f){(0,eval)(fs.readFileSync(f,"utf8")+"//# sourceURL="+f)},postMessage:function(msg){parentPort.postMessage(msg)},performance:global.performance||{now:function(){return Date.now()}}})}var initializedJS=false;var pendingNotifiedProxyingQueues=[];function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");if(ENVIRONMENT_IS_NODE){fs.writeSync(2,text+"\n");return}console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:Module["_pthread_self"]()})}var err=threadPrintErr;self.alert=threadAlert;Module["instantiateWasm"]=(info,receiveInstance)=>{var instance=new WebAssembly.Instance(Module["wasmModule"],info);receiveInstance(instance);Module["wasmModule"]=null;return instance.exports};self.onunhandledrejection=e=>{throw e.reason??e};function handleMessage(e){try{if(e.data.cmd==="load"){let messageQueue=[];self.onmessage=e=>messageQueue.push(e);self.startWorker=instance=>{postMessage({"cmd":"loaded"});for(let msg of messageQueue){handleMessage(msg)}self.onmessage=handleMessage};Module["wasmModule"]=e.data.wasmModule;for(const handler of e.data.handlers){Module[handler]=function(){postMessage({cmd:"callHandler",handler:handler,args:[...arguments]})}}Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob=="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}}else if(e.data.cmd==="run"){Module["__emscripten_thread_init"](e.data.pthread_ptr,0,0,1);Module["establishStackSpace"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].threadInitTLS();if(!initializedJS){Module["__embind_initialize_bindings"]();pendingNotifiedProxyingQueues.forEach(queue=>{Module["executeNotifiedProxyingQueue"](queue)});pendingNotifiedProxyingQueues=[];initializedJS=true}try{Module["invokeEntryPoint"](e.data.start_routine,e.data.arg)}catch(ex){if(ex!="unwind"){if(ex instanceof Module["ExitStatus"]){if(Module["keepRuntimeAlive"]()){}else{Module["__emscripten_thread_exit"](ex.status)}}else{throw ex}}}}else if(e.data.cmd==="cancel"){if(Module["_pthread_self"]()){Module["__emscripten_thread_exit"](-1)}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processProxyingQueue"){if(initializedJS){Module["executeNotifiedProxyingQueue"](e.data.queue)}else{pendingNotifiedProxyingQueues.push(e.data.queue)}}else if(e.data.cmd){err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){if(Module["__emscripten_thread_crashed"]){Module["__emscripten_thread_crashed"]()}throw ex}}self.onmessage=handleMessage;

libwhisper.worker.js

@@ -0,0 +1 @@
+"use strict";var Module={};var ENVIRONMENT_IS_NODE=typeof process=="object"&&typeof process.versions=="object"&&typeof process.versions.node=="string";if(ENVIRONMENT_IS_NODE){var nodeWorkerThreads=require("worker_threads");var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",data=>onmessage({data:data}));var fs=require("fs");Object.assign(global,{self:global,require:require,Module:Module,location:{href:__filename},Worker:nodeWorkerThreads.Worker,importScripts:function(f){(0,eval)(fs.readFileSync(f,"utf8")+"//# sourceURL="+f)},postMessage:function(msg){parentPort.postMessage(msg)},performance:global.performance||{now:function(){return Date.now()}}})}var initializedJS=false;var pendingNotifiedProxyingQueues=[];function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");if(ENVIRONMENT_IS_NODE){fs.writeSync(2,text+"\n");return}console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:Module["_pthread_self"]()})}var err=threadPrintErr;self.alert=threadAlert;Module["instantiateWasm"]=(info,receiveInstance)=>{var instance=new WebAssembly.Instance(Module["wasmModule"],info);receiveInstance(instance);Module["wasmModule"]=null;return instance.exports};self.onunhandledrejection=e=>{throw e.reason??e};function handleMessage(e){try{if(e.data.cmd==="load"){let messageQueue=[];self.onmessage=e=>messageQueue.push(e);self.startWorker=instance=>{Module=instance;postMessage({"cmd":"loaded"});for(let msg of messageQueue){handleMessage(msg)}self.onmessage=handleMessage};Module["wasmModule"]=e.data.wasmModule;for(const handler of e.data.handlers){Module[handler]=function(){postMessage({cmd:"callHandler",handler:handler,args:[...arguments]})}}Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob=="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}whisper_factory(Module)}else if(e.data.cmd==="run"){Module["__emscripten_thread_init"](e.data.pthread_ptr,0,0,1);Module["establishStackSpace"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].threadInitTLS();if(!initializedJS){Module["__embind_initialize_bindings"]();pendingNotifiedProxyingQueues.forEach(queue=>{Module["executeNotifiedProxyingQueue"](queue)});pendingNotifiedProxyingQueues=[];initializedJS=true}try{Module["invokeEntryPoint"](e.data.start_routine,e.data.arg)}catch(ex){if(ex!="unwind"){if(ex instanceof Module["ExitStatus"]){if(Module["keepRuntimeAlive"]()){}else{Module["__emscripten_thread_exit"](ex.status)}}else{throw ex}}}}else if(e.data.cmd==="cancel"){if(Module["_pthread_self"]()){Module["__emscripten_thread_exit"](-1)}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processProxyingQueue"){if(initializedJS){Module["executeNotifiedProxyingQueue"](e.data.queue)}else{pendingNotifiedProxyingQueues.push(e.data.queue)}}else if(e.data.cmd){err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){if(Module["__emscripten_thread_crashed"]){Module["__emscripten_thread_crashed"]()}throw ex}}self.onmessage=handleMessage;

models/.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

models/README.md

@@ -0,0 +1,24 @@
+---
+license: mit
+---
+
+# OpenAI's Whisper models converted to ggml format
+
+[Available models](https://huggingface.co/datasets/ggerganov/whisper.cpp/tree/main)
+
+| Model     | Disk   | Mem     | SHA                                        |
+| ---       | ---    | ---     | ---                                        |
+| tiny      |  75 MB | ~390 MB | `bd577a113a864445d4c299885e0cb97d4ba92b5f` |
+| tiny.en   |  75 MB | ~390 MB | `c78c86eb1a8faa21b369bcd33207cc90d64ae9df` |
+| base      | 142 MB | ~500 MB | `465707469ff3a37a2b9b8d8f89f2f99de7299dac` |
+| base.en   | 142 MB | ~500 MB | `137c40403d78fd54d454da0f9bd998f78703390c` |
+| small     | 466 MB | ~1.0 GB | `55356645c2b361a969dfd0ef2c5a50d530afd8d5` |
+| small.en  | 466 MB | ~1.0 GB | `db8a495a91d927739e50b3fc1cc4c6b8f6c2d022` |
+| medium    | 1.5 GB | ~2.6 GB | `fd9727b6e1217c2f614f9b698455c4ffd82463b4` |
+| medium.en | 1.5 GB | ~2.6 GB | `8c30f0e44ce9560643ebd10bbe50cd20eafd3723` |
+| large-v1  | 2.9 GB | ~4.7 GB | `b1caaf735c4cc1429223d5a74f0f4d0b9b59a299` |
+| large     | 2.9 GB | ~4.7 GB | `0f4c8e34f21cf1a914c59d8b3ce882345ad349d6` |
+
+For more information, visit:
+
+https://github.com/ggerganov/whisper.cpp/tree/master/models

models/ggml-base.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ed5bc3dd14eea856493d334349b405782ddcaf0028d4b5df4088345fba2efe
+size 147951465

models/ggml-base.en.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03779c86df3323075f5e796cb2ce5029f00ec8869eee3fdfb897afe36c6d002
+size 147964211

models/ggml-tiny.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be07e048e1e599ad46341c8d2a135645097a538221678b7acdd1b1919c6e1b21
+size 77691713

models/ggml-tiny.en.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921e4cf8686fdd993dcd081a5da5b6c365bfde1162e72b08d75ac75289920b1f
+size 77704715

nginx.conf

@@ -0,0 +1,19 @@
+server {
+    listen       8080;
+    listen  [::]:8080;
+    server_name  localhost;
+
+    #access_log  /var/log/nginx/host.access.log  main;
+
+    location / {
+        root   /usr/share/nginx/html;
+        index  index.html index.htm;
+
+        add_header 'Cross-Origin-Embedder-Policy' 'require-corp';
+        add_header 'Cross-Origin-Opener-Policy' 'same-origin';	 
+        add_header 'Cross-Origin-Resource-Policy' 'cross-origin';
+
+    }
+    #error_page  404              /404.html;
+
+  }

style.css

@@ -0,0 +1,28 @@
+body {
+	padding: 2rem;
+	font-family: -apple-system, BlinkMacSystemFont, "Arial", sans-serif;
+}
+
+h1 {
+	font-size: 16px;
+	margin-top: 0;
+}
+
+p {
+	color: rgb(107, 114, 128);
+	font-size: 15px;
+	margin-bottom: 10px;
+	margin-top: 5px;
+}
+
+.card {
+	max-width: 620px;
+	margin: 0 auto;
+	padding: 16px;
+	border: 1px solid lightgray;
+	border-radius: 16px;
+}
+
+.card p:last-child {
+	margin-bottom: 0;
+}