Compare commits

..

2 Commits

23 changed files with 148 additions and 14094 deletions
BIN
View File
Binary file not shown.
+8 -25
View File
@@ -9,22 +9,9 @@
<body>
<div class="mitte" id="mitte">
<div class="labelDiv" id="labelDiv">
<label id="labelKI">Select ki:</label>
<label id="labelTranscription">Select transcription:</label>
<label id="labelLanguage">Select language:</label>
<img id="labelLanguageFlag" src="flags/united-kingdom-flag-png-large.jpg" width="20" height="10" >
</div>
<div class="dropdownMenus" id="dropdownMenus">
<div class="flagsBtns" id="flagsBtns">
<select name="ai_type" id="ai_type">
</select>
<select name="transkript_type" id="transkript_type">
</select>
<select name="output_type" id="output_type">
<option value="flac">flac</option>
<option value="mp3">mp3</option>
<option value="wav">wav</option>
</select>
<select name="language_option" id="language_option">
</select>
</div>
@@ -33,32 +20,28 @@
<div class="upload-container" id="uploadContainer">
<p id="p1">Drag and drop video file</p>
<video id="previewThumbnail" autoplay="false">
</video>
<div class="file-name" id="fileName">No video chosen</div>
<div id="thumbnailContainer">
<img id="thumbnailImage" style="display:none;">
</div>
<button class="custom-btn" id="manualUploadBtn">Search video</button>
<input type="file" id="videoUpload" accept="video/*">
</div>
<button class="custom-btn" id="manualUploadBtn">Search video</button>
<input type="file" id="videoUpload" accept="video/*">
<div class="checkbox-group">
<label id="checkbox_group" for="checkbox-group">Choose prefered document style:</label>
<div class="checkbox-container">
<input type="checkbox" name ="docFormat" id="docFormat" value="Meeting report">
<input type="checkbox" name ="docFormat" id="docFormat">
<label id="label_format" for="docFormat">Meeting report</label>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary" value="Summary with timestamps">
<input type="checkbox" name="docFormat" id="docFormatSummary">
<label id="label_summary" for="docFormatSummary">Summary with timestamps</label>
</div>
</div>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()">Submit</button>
<div class="progressbar" id="progressbar">
<div class="progressbar">
<div class="progress_fill"></div>
<span class="progress_text">0%</span>
</div>
-12
View File
@@ -1,9 +1,5 @@
var languageOptions = {
"eng":{
"flagPath": "flags/united-kingdom-flag-png-large.jpg",
"labelKI": "Select ki:",
"labelTranscription": "Select transcription:",
"labelLanguage": "Select language:",
"title": "Video to document",
"h1": "Video to document",
"p1": "Drag and drop video file",
@@ -15,10 +11,6 @@ var languageOptions = {
"submitButton": "Submit"
},
"de":{
"flagPath": "flags/germany-flag-png-large.jpg",
"labelKI": "Waehle KI:",
"labelTranscription": "Waehle Transkription:",
"labelLanguage": "Waehle Sprache:",
"title": "Video zu Dokument",
"h1": "Video zu Dokument",
"p1": "Video per Drag & Drop ablegen",
@@ -30,10 +22,6 @@ var languageOptions = {
"submitButton": "Absenden"
},
"in":{
"flagPath": "flags/india-flag-png-large.png",
"labelKI": "की का चयन करें:",
"labelTranscription": "प्रतिलेखन चुनें:",
"labelLanguage": "भाषा चुने:",
"title": "दस्तावेज़ के लिए वीडियो",
"h1": "दस्तावेज़ के लिए वीडियो",
"p1": "वीडियो फ़ाइल खींचें और छोड़ें",
+3 -15
View File
@@ -4,24 +4,12 @@ try {
contextBridge.exposeInMainWorld("explorer", {
onFileDrop: (file) => webUtils.getPathForFile(file)
})
contextBridge.exposeInMainWorld("submit", {
submit: (meeting_specifications) => {ipcRenderer.send("file_submit", meeting_specifications)}
contextBridge.exposeInMainWorld("extractor", {
extract: (file) => ipcRenderer.send("extract", file)
})
contextBridge.exposeInMainWorld("electronAPI", {
getFilePath: (file) => {return webUtils.getPathForFile(file)}
})
contextBridge.exposeInMainWorld("onStartup", {
getModuleNames: () => ipcRenderer.invoke('get-module-names')
})
ipcRenderer.on("progress", (event, resp) => {
alert(`Finished step ${resp.curstep} of ${resp.totalsteps}`)
})
ipcRenderer.on("error", (event, err) => {alert(err)})
} catch (error) {
console.log("Error in preload.js");
}
}
+10 -56
View File
@@ -16,72 +16,26 @@ uploadContainer.addEventListener("drop", (e) => {
e.preventDefault()
const files = e.dataTransfer.files
const filePath = window.explorer.onFileDrop(files[0])
const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
var pathToLower = filePath.toLowerCase();
if(testEndings.some(e => pathToLower.endsWith(e))){
document.getElementById("progressbar").style.visibility = "visible";
var holdy = filePath + "";
if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
console.log(filePath)
const files1 = e.dataTransfer.files;
handleFiles(files1);
}else{
alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
}
} catch (error) {
console.log("Error in renderer.js with the listerner for the drop function");
}
})
window.addEventListener('load', async (e) => {
try {
console.log("test");
loadLanguageOptions();
const value = await window.onStartup.getModuleNames();
loadAiOptions(value.ai_modules);
loadTranscriptionOptions(value.transcription_modules);
} catch (error) {
}
window.addEventListener('load', (e) => {
console.log("test");
loadLanguageOptions();
});
language_option.addEventListener('change', (e)=>{
try {
const select = document.getElementById('language_option');
changeLanguage(select.value);
} catch (error) {
}
const select = document.getElementById('language_option');
console.log(select.value);
changeLanguage(select.value);
});
videoUpload.addEventListener("change", () => {
try {
activateSubmitBtn(videoUpload.files.length > 0);
} catch (error) {
console.log(error);
}
});
//listener for the file explorer search when something got selected
videoUpload.addEventListener('change', () => {
try {
handleFiles(videoUpload.files);
} catch (error) {
console.log("Error in manualBtn EventListener change");
console.log(error);
}
});
//listener for the file explorer search
manualUploadBtn.addEventListener('click', () => {
try {
videoUpload.click();
} catch (error) {
console.log("Error in manualBtn EventListener click");
console.log(error);
}
});
+33 -117
View File
@@ -1,84 +1,45 @@
//listener for the file explorer search
manualUploadBtn.addEventListener('click', () => {
try {
videoUpload.click();
} catch (error) {
console.log("Error in manualBtn EventListener click");
}
});
//function to check if one checkbox is at least klicked
function checkBoxes() {
try {
const checkboxes = document.querySelectorAll('input[name="docFormat"]');
let isChecked = false;
var checkedCounter = 0;
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
isChecked = true;
checkedCounter++;
}
});
if (isChecked) {
if(isChecked){
//Code to submit the video
var selectedCheckboxes = {};
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
selectedCheckboxes[checkbox.nextElementSibling.textContent] = "";
}
});
const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
var pathToLower = pathTest.toLowerCase();
if(testEndings.some(e => pathToLower.endsWith(e))){
document.getElementById("progressbar").style.visibility = "visible";
//assembly of the json for the main
const selectedStyles = [checkedCounter];
var iter = 0;
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
console.log(checkbox.value);
selectedStyles[iter] = {iter: checkbox.value};
iter++;
}
});
console.log(selectedCheckboxes);
const outputType = document.getElementById("output_type");
const transcriptionType = document.getElementById("transkript_type");
const aiType = document.getElementById("ai_type");
const sendingPackage = {
"video": {
"module":"extraction-video-to-audio",
"inputVideoPath": pathTest,
"outputType": outputType.value
},
"transcription": {
"module": transcriptionType.value
},
"document": {
"module":aiType.value,
"styles": selectedStyles
}
};
window.submit.submit(sendingPackage)
}else{
alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
if(pathTest.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
window.extractor.extract({inputVideoPath: pathTest, outputType:"wav"})
}
} else {
//language only english at the moment
alert('Please select at least one document type.');
}
} catch (error) {
console.log("Error in script.js checkBoxes function");
console.log(error);
console.log(error)
}
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
}
//language changing feature
function changeLanguage(language) {
try {
document.getElementById('labelLanguageFlag').src = languageOptions[language].flagPath;
document.getElementById('labelKI').textContent = languageOptions[language].labelKI;
document.getElementById('labelTranscription').textContent = languageOptions[language].labelTranscription;
document.getElementById('labelLanguage').textContent = languageOptions[language].labelLanguage;
document.getElementById('title').textContent = languageOptions[language].title;
document.getElementById('h1').textContent = languageOptions[language].h1;
document.getElementById('p1').textContent = languageOptions[language].p1;
@@ -88,43 +49,46 @@ function changeLanguage(language) {
document.getElementById('label_format').textContent = languageOptions[language].label_format;
document.getElementById('label_summary').textContent = languageOptions[language].label_summary;
document.getElementById('submitButton').textContent = languageOptions[language].submitButton;
} catch (error) {
console.log("Error in script.js changeLanguage function");
console.log(error);
}
}
//listener for the file explorer search when something got selected
videoUpload.addEventListener('change', () => {
try {
handleFiles(videoUpload.files);
} catch (error) {
console.log("Error in manualBtn EventListener change");
}
});
//function to display the file path in the drop down box
function handleFiles(files) {
try {
if (files.length > 0) {
const file = files[0];
if (file.type.startsWith('video/')) {
const filePath = window.explorer.onFileDrop(files[0])
videoUpload.files = files;
fileName.textContent = `Chosen video: ${file.name}`;
generateThumbnail(filePath);
activateSubmitBtn(true);
}
}
} catch (error) {
console.log("Error in script.js handleFiles function");
console.log(error);
}
}
//function to regulate the progress on the progressbar
function updateProgressBar(bar, value) {
function updateProgressBar(bar, value){
try {
value = Math.round(value);
bar.querySelector(".progress_fill").style.width = `${value}%`;
bar.querySelector(".progress_text").textContent = `${value}%`;
} catch (error) {
console.log("Error in scripts.js updateProgressBar function");
console.log(error);
}
}
@@ -133,13 +97,12 @@ function updateProgressBar(bar, value) {
function loadAiOptions(options){
try {
var menu = document.getElementById('ai_type');
var object_holdy;
var choice ;
object_holdy = options
for(i = 0; i < options.length; i++){
choice = document.createElement('option');
choice.textContent = object_holdy[i].displayname;
choice.value = object_holdy[i].name;
var opty = options[i];
var namey = "option" + i;
var choice = document.createElement(namey);
choice.textContent = "t";
choice.value = i;
menu.appendChild(choice);
}
} catch (error) {
@@ -148,25 +111,6 @@ function loadAiOptions(options){
}
}
//function to load transcription options to the drop down list
function loadTranscriptionOptions(options){
try {
var menu = document.getElementById('transkript_type');
var object_holdy;
var choice ;
object_holdy = options
for(i = 0; i < options.length; i++){
choice = document.createElement('option');
choice.textContent = object_holdy[i].displayname;
choice.value = object_holdy[i].name;
menu.appendChild(choice);
}
} catch (error) {
console.log("Error in script.js function loadTranscriptionOptions");
console.log(error);
}
}
//function to load language options to the drop down list
function loadLanguageOptions(){
try {
@@ -185,32 +129,4 @@ function loadLanguageOptions(){
console.log("Error in script.js loadLanguageOptions function");
console.log(error);
}
}
function activateSubmitBtn(hasFile){
try {
submitButton.disabled = !hasFile;
} catch (error) {
console.log(error);
}
}
function deaktivateProgressbar(){
try {
document.getElementById("progressbar").style.visibility = "hidden";
} catch (error) {
console.log(error);
}
}
//Video thumbnail generation
function generateThumbnail(path){
const videoElement = document.getElementById("previewThumbnail");
while (videoElement.firstChild) videoElement.removeChild(videoElement.firstChild);
videoElement.src = path;
videoElement.type = "video/mov";
videoElement.load();
videoElement.style.maxWidth = 40;
videoElement.style.maxHeight = 40;
videoElement.autoplay = false;
}
}
+33 -74
View File
@@ -5,71 +5,46 @@ body {
justify-content: center;
align-items: center;
height: 100vh;
background-color: #f2f3f4;
background-color: #555;
gap: 15px;
margin: 0;
}
.upload-container {
background: white;
padding: 40px;
border-radius: 12px;
box-shadow: 0 4px 10px rgba(0,0,0,0.1);
text-align: center;
width: 350px;
height: 200px;
width: 400px;
transition: border 0.3s, background-color 0.3s;
border: 2px dashed #7378c9;
border: 2px dashed #ccc;
}
.upload-container.dragover {
border-color: #007BFF;
background-color: #eaf0ff;
}
.upload-container p {
margin: 0 0 15px 0;
font-size: 16px;
color: #555;
}
.file-name {
margin-top: 10px;
font-size: 14px;
color: #333;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
#thumbnailContainer {
width: 100%;
display: flex;
justify-content: center;
margin-bottom: 15px;
}
#thumbnailImage {
width: 200px;
height: auto;
border-radius: 10px;
box-shadow: 0px 4px 10px rgba(0,0,0,0.1);
object-fit: cover;
}
#previewThumbnail {
width: 150px;
height: 100px;
/*border: 1px dashed black;*/
}
.custom-btn {
padding: 10px 20px;
margin-top: 10px;
background-color: #007BFF;
color: white;
border: none;
@@ -77,27 +52,27 @@ body {
cursor: pointer;
font-size: 14px;
}
.custom-btn:hover {
background-color: #0056b3;
}
.submit-btn:hover {
background-color: #0056b3;
}
input[type="file"] {
display: none;
}
.checkbox-container{
margin-top: 8px;
display: flex;
align-items: center;
gap: 5px;
}
.checkbox-group {
margin-top: 15px;
margin-bottom: 15px;
@@ -106,11 +81,9 @@ gap: 5px;
gap: 10px;
align-items: flex-start;
}
.submit-btn {
padding: 10px 20px;
margin-top: 10px;
margin-bottom: 10px;
background-color: #007BFF;
color: white;
border: none;
@@ -118,33 +91,24 @@ gap: 5px;
cursor: pointer;
font-size: 14px;
}
.submit-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
pointer-events: none;
}
.mitte {
background-color: #FDFCFA;
background-color: #f2f3f4;
display: flex;
width: 700px;
flex-direction: column;
align-items: center;
padding: 5% 50px;
margin-top: 20px;
gap: 10px;
border: 0px;
border: 1px;
border-color: black;
border-style: solid;
border-radius: 6px;
box-shadow: 0px 4px 10px rgba(0,0,0,0.1);
}
h1 {
align-content: center;
}
.progressbar{
position: relative;
width: 210px;
@@ -152,16 +116,15 @@ h1 {
background: rgb(42, 46, 78);
border-radius: 5px;
overflow: hidden;
visibility: hidden;
}
.progress_fill{
width: 0%;
height: 100%;
background: green;
transition: all 0.2s;
}
.progress_text{
position: absolute;
top: 50%;
@@ -170,19 +133,15 @@ h1 {
color: white;
}
.dropdownMenus {
.flagsBtns {
display: flex;
justify-content: flex-end;
margin-top: 1px;
gap: 150px;
padding: 2px 10px 2px 10px;
}
#ai_type, #transkript_type, #language_option {
padding: 3px;
}
.labelDiv {
gap: 200px;
.de_Btn, .eng_Btn, .in_Btn {
padding: 8px 16px;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
}
+13 -169
View File
@@ -35,8 +35,6 @@ console.log("-------------------------------------------------------------------
// --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //
const rl = readline.createInterface({
@@ -60,176 +58,22 @@ rl.on("line", data =>{
let mainWindow;
function createWindow() {
mainWindow = new electron.BrowserWindow({
width: 800,
height: 800,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow = new electron.BrowserWindow({
width: 800,
height: 600,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow.loadFile('./electron/main/index.html');
mainWindow.loadFile('./electron/main/index.html');
}
electron.app.whenReady().then(createWindow);
// electron.ipcMain.on("extract", (event, args) => {
// mapFunctions.get("extraction-video-to-audio").function(args)
// })
// setTimeout(() => {
// mainWindow.webContents.send("fuck", "worked uwu")
// }, 5000);
electron.ipcMain.handle('get-module-names', async () => {
let module_array = {
"ai_modules":[],
"transcription_modules":[]
}
mapFunctions.forEach(e => {
switch(e.type){
case "llm":
module_array.ai_modules.push({"name": e.name, "displayname": e.displayname})
break;
case "transcription":
module_array.transcription_modules.push({"name": e.name, "displayname": e.displayname})
break;
}
})
// console.log(module_array);
return module_array
});
// electron.ipcMain.on("get_modules", async (event, args) => {
// let module_array = {
// "ai_modules":[],
// "transcription_modules":[]
// }
// mapFunctions.forEach(e => {
// switch(e.type){
// case "llm":
// module_array.ai_modules.push({"name": e.name, "displayname": e.displayname})
// break;
// case "transcription":
// module_array.transcription_modules.push({"name": e.name, "displayname": e.displayname})
// break;
// }
// })
// console.log(module_array);
// mainWindow.webContents.send("modules", module_array)
// })
electron.ipcMain.on("file_submit", async (event, args) => {
try {
let curstep = 0
let totalsteps = 3 + args.document.styles.length
if(args.document.styles.length == 0)
throw new Error("At least one Document Style needed");
console.log(args);
let audiopath = ""
let transcriptpath = ""
console.log("\n\n Running the Video to Audio Extractor");
// This code handles the Video to Audio extraction module call
await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: args.video.outputType}).then(resp => {
console.log(resp);
audiopath = resp
curstep++
mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
console.log("\n\n Running the Audio to Transcription module");
// TODO implement transcription module
// This code handles the Audio to Text transcription module call
await mapFunctions.get("module-handler").function(args.transcription.module, audiopath).then(resp => {
console.log(resp);
transcriptpath = resp
curstep++
mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
console.log("\n\n Running the Transcription Summarizer module");
// This code summarises the transcript, so that it can be used by an llm
// await mapFunctions.get("summarize-transcription").function('A:\\programing\\@projects\\video2document\\storage\\transcripts\\IMG_2978.json').then(resp => {
await mapFunctions.get("summarize-transcription2").function(transcriptpath).then(resp => {
console.log(resp);
transcriptpath = resp
curstep++
mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
console.log("\n\n Running the LLM module");
// TODO implement documentation module
// This code handles the Text to Document processing module call
for (let i = 0; i < args.document.styles.length; i++) {
await mapFunctions.get("module-handler").function(args.document.module, {prompt: args.document.styles[i].prompt, transcript: transcriptpath}).then(resp => {
console.log(resp);
transcriptpath = resp
curstep++
mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
}
} catch (error) {
console.log(error);
}
})
let q =
{
video: {
module: "String", // The name of the module, idk if we ever implement other extraction modules, the default one is extraction-video-to-audio
inputVideoPath: "String", // See script.js on line 27 for an example of what this should look like
outputType: "String" // The file format to be used for the audio output file, such as wav, mp3, flac and so on
},
transcription:{
module: "String" // The module name of the transcription model you want to use
},
document:{
module: "String", // The module name of the AI model you want to use to create the document
styles: [ // An array of all the document styles/prompts you want to have the document be processed with
{
prompt: "String",
}
]
}
}
let q1 = {
"ai_modules": [
{name:"abc", displayname:"ABC"},
{name:"qeg", displayname:"aqghegahu"}
],
"transcription_modules": [
{name:"abc", displayname:"ABC"},
{name:"qeg", displayname:"aqghegahu"}
]
}
electron.ipcMain.on("extract", (event, args) => {
mapFunctions.get("extraction-video-to-audio").function(args)
})
+1 -812
View File
File diff suppressed because it is too large Load Diff
-2
View File
@@ -1,8 +1,6 @@
{
"dependencies": {
"@google/genai": "^1.30.0",
"@types/axios": "^0.9.36",
"axios": "^1.13.2",
"cli-progress": "^3.12.0",
"dotenv": "^17.2.3",
"electron": "^39.1.1",
-5
View File
@@ -16,8 +16,3 @@ cliProgress = require('cli-progress');
// { app, BrowserWindow, ipcMain, dialog } = require('electron');
electron = require('electron');
genai = require("@google/genai");
axios = require("axios")
console.log(require('dotenv').config({path: __dirname + '/.env'}));
@@ -1,3 +1,4 @@
// Ensure ffmpeg binary is available
if (!ffmpegPath) {
throw new Error('FFmpeg binary not found!');
@@ -31,11 +32,11 @@ module.exports = {
hideCursor: true
});
try {
return new Promise((resolve, reject) => {
// if (meta.url === `file://${process.argv[1]}`) {
this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
.then((resp) => resolve(resp))
.then(() => console.log('Audio extraction successful.'))
.catch((err) => console.error(err));
})
// }
} catch (error) {
console.log(parameter.outputType);
@@ -74,7 +75,7 @@ module.exports = {
progressBar.update(100, { timemark: 'done' });
progressBar.stop();
console.log(`Extraction completed: ${outputAudioPath}`);
resolve(outputAudioPath);
resolve();
})
.on('error', (err) => {
progressBar.stop();
@@ -88,4 +89,5 @@ module.exports = {
}
});
}
}
@@ -1,148 +0,0 @@
// Prepare output directory (always storage/transcriptionSummaries under project root)
const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
//Speaker, ALL-Sentences, Start, End
module.exports = {
name: "summarize-transcription", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type: "summarizer", // value used to differentiate each module to order them in the UI
displayname: "Summarizer", // The displayname used within the UI
async function(args) {
return new Promise(async (resolve, reject) => {
let inputJson = args.json;
//JSON Path
if (args.jsonPath) {
try {
const raw = fs.readFileSync(args.jsonPath, "utf-8");
inputJson = JSON.parse(raw);
} catch (e) {
console.error("Failed to load JSON from file:", e);
return { error: "Could not read JSON from file path." };
}
}
// JSON parsen
if (typeof args === "string") {
try {
await new Promise((res) => {
fs.readFile(args, 'utf8', function (err, data) {
if (err) throw err;
inputJson = JSON.parse(data);
res()
});
})
} catch (e) {
console.log("Invalid JSON in summarize-transcription");
console.log(e)
return { error: "Invalid JSON" };
}
}
const words = inputJson.words;
if (!Array.isArray(words)) {
return { error: "No words Array found" };
}
const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
const result = [];
let currentSentence = "";
let currentSpeaker = null;
let startTime = null;
let endTime = null;
for (const w of words) {
if (!currentSpeaker) currentSpeaker = w.speaker;
if (startTime === null) startTime = w.start;
endTime = w.end;
//speaker changing
if (currentSpeaker !== w.speaker && currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = w.start;
}
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending
if (ENDINGS.includes(lastChar) && !isAbbreviation) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = null;
endTime = null;
currentSpeaker = null;
}
}
// safe last sentence
if (currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
}
// Output as Text
const output = result.map(r =>
`Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
);
// Output on cosole
//console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
try {
const jsonPath = path.join(outputDir, "transcription_result.json");
fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
const txtPath = path.join(outputDir, "transcription_result.txt");
fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
resolve(jsonPath);
} catch (err) {
console.error("Error saving Summary:", err);
reject(err);
}
})
}
}
@@ -1,143 +0,0 @@
// Prepare output directory (always storage/transcriptionSummaries under project root)
const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
function getSessionId(inputPath) {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch {
return path.basename(inputPath, path.extname(inputPath));
}
}
//Speaker, Sentence, Start, End
module.exports = {
name: "summarize-transcription2", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type: "summarizer", // value used to differentiate each module to order them in the UI
displayname: "Summarizer", // The displayname used within the UI
async function(args) {
return new Promise(async (resolve, reject) => {
let inputJson = args.json;
//JSON Path
if (args.jsonPath) {
try {
const raw = fs.readFileSync(args.jsonPath, "utf-8");
inputJson = JSON.parse(raw);
} catch (e) {
console.error("Failed to load JSON from file:", e);
return { error: "Could not read JSON from file path." };
}
}
// JSON parsen
if (typeof args === "string") {
try {
await new Promise((res) => {
fs.readFile(args, 'utf8', function (err, data) {
if (err) throw err;
inputJson = JSON.parse(data);
res()
});
})
} catch (e) {
console.log("Invalid JSON in summarize-transcription");
console.log(e)
return { error: "Invalid JSON" };
}
}
const words = inputJson.words;
if (!Array.isArray(words)) {
return { error: "No words Array found" };
}
const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
const result = [];
let currentSentence = "";
let currentSpeaker = null;
let startTime = null;
let endTime = null;
for (const w of words) {
if (!currentSpeaker) currentSpeaker = w.speaker;
if (startTime === null) startTime = w.start;
endTime = w.end;
//speaker changing
if (currentSpeaker !== w.speaker && currentSentence) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
currentSentence = "";
startTime = w.start;
}
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending
if (ENDINGS.includes(lastChar) && !isAbbreviation) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
currentSentence = "";
startTime = null;
endTime = null;
currentSpeaker = null;
}
}
// safe last sentence
if (currentSentence) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
// Output as Text
const output = result.map(r =>
`Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
);
// Output on cosole
//console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
try {
let filename = getSessionId(args);
const jsonPath = path.join(outputDir, `${filename}-${new Date().getTime()}.json`);
fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
const txtPath = path.join(outputDir, `${filename}-${new Date().getTime()}.txt`);
fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
resolve(jsonPath);
} catch (err) {
console.error("Error saving Summary:", err);
reject(err);
}
})
}
}
+1 -1
View File
@@ -1,6 +1,6 @@
module.exports = {
name:"chatgpt", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type:"llm", // value used to differentiate each module to order them in the UI
type:"document", // value used to differentiate each module to order them in the UI
displayname:"ChatGPT", // The displayname used within the UI
async function(parameter){
// TODO add code to actually send the transcript to ChatGPT and get a response back
+33 -12
View File
@@ -4,9 +4,10 @@ if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
}
const ai = new genai.GoogleGenAI({
apiKey: process.env.GOOGLE_API_KEY // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
});
// Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
const GEMINI_API_KEY = process.env.GOOGLE_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; //URL for the REST call, used model and action
module.exports = {
name: "llm-gemini",
@@ -31,19 +32,39 @@ module.exports = {
createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
try {
const transcript = await fs.promises.readFile(transcriptPath, "utf-8");
const documentType = await fs.promises.readFile(documentTypePath, "utf-8");
const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`;
const response = await ai.models.generateContent({
model: "gemini-2.5-flash", // Specify the Gemini model to use
contents: promptText // Input prompt for content generation
// --- REST CALL ---
const response = await fetch(`${GEMINI_URL}?key=${GEMINI_API_KEY}`, { //safe model response in variable
method: "POST",
headers: {
"Content-Type": "application/json"
},
body: JSON.stringify({
contents: [
{
parts: [
{ text: promptText } // Input prompt for content generation
]
}
]
})
});
const output = response.text || ""; // Get generated text from response or default to empty string (if null)
if (!response.ok) { //ok is true when a responce was successfull
const text = await response.text();
throw new Error(`Gemini API error (${response.status}): ${text}`);
}
const outPath = path.join(outputDir, "test.md"); // Output file path & name TO BE DONE to make dynamic out of input transcript name
const data = await response.json();
// Get generated text from response or default to empty string (if null)
const output = data?.candidates?.[0]?.content?.parts?.[0]?.text || "";
let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file
console.log(inputTranscriptName);
const outPath = path.join(outputDir, `${inputTranscriptName}.md`); // Output file path & name to make naming dynamic. Pulled from input transcript name
fs.writeFileSync(outPath, output, "utf8"); // Write output to file
console.log("Generated document written to:", outPath);
@@ -1,123 +1,8 @@
const API_KEY = process.env.ASSEMBLYAI_API_KEY;
const BASE_URL = 'https://api.assemblyai.com/v2';
//---------------------------------------------------Upload audio---------------------------------------------------
async function uploadAudio(audioPath) {
const audioData = fs.readFileSync(audioPath);
const response = await axios.post(`${BASE_URL}/upload`, audioData, {
headers: {
authorization: API_KEY,
'content-type': 'application/octet-stream'
}
});
return response.data.upload_url;
}
////---------------------------------------------------Extract session id---------------------------------------------------
function getSessionId(inputPath) {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch {
return path.basename(inputPath, path.extname(inputPath));
}
}
//---------------------------------------------------Create transcript---------------------------------------------------
async function createTranscript(audioUrl) {
const response = await axios.post(
`${BASE_URL}/transcript`,
{
audio_url: audioUrl,
speaker_labels: true,
language_detection: true
},
{
headers: {
authorization: API_KEY,
'content-type': 'application/json'
}
}
);
return response.data.id;
}
//---------------------------------------------------Poll transcript---------------------------------------------------
async function pollTranscript(transcriptId) {
while (true) {
const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
headers: { authorization: API_KEY }
});
const status = response.data.status;
if (status === 'completed') return response.data;
if (status === 'error') throw new Error(`Transcription failed: ${response.data.error}`);
await new Promise(res => setTimeout(res, 3000));
}
}
//---------------------------------------------------Save transcript---------------------------------------------------
function saveTranscript(transcript, sessionId) {
const outputDir = path.join(__dirname, '../../../storage/transcripts');
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
const outputPath = path.join(outputDir, `${sessionId}.json`);
fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
console.log(`Transcript saved: ${outputPath}`);
return outputPath;
}
//---------------------------------------------------Modul---------------------------------------------------
module.exports = {
name: 'assembly',
type: 'transcription',
displayname: 'AssemblyAI',
async function(audioFileName) {
return new Promise(async (resolve, reject) => {
try {
// audioFileName ist nur "datei.mp3"
const audioPath = audioFileName;
let audioUrl;
if (/^https?:\/\//i.test(audioFileName)) {
audioUrl = audioFileName;
} else {
if (!fs.existsSync(audioPath)) {
throw new Error(`Audio file not found: ${audioPath}`);
}
audioUrl = await uploadAudio(audioPath);
}
const transcriptId = await createTranscript(audioUrl);
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioFileName);
resolve(saveTranscript(transcript, sessionId));
} catch (error) {
console.error('Transcription error:', error.message);
reject(error);
}
})
}
};
name:"assembly", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type:"transcription", // value used to differentiate each module to order them in the UI
displayname:"Assembly", // The displayname used within the UI
async function(parameter){
// TODO add code to actually process the audio file
}
}
-10
View File
@@ -6,18 +6,8 @@ module.exports = {
// We are now calling the example function from the example folder
mapFunctions.get("example").function("Startup")
// let transcript = await mapFunctions.get("assembly").function('../../storage/audio/IMG_2978.wav');
// let summary = await mapFunctions.get("summarize-transcription").function({jsonPath:'/Users/santa/Proj25/video2document/storage/transcripts/IMG_2978.json'});
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"wav"})
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"flac"})
// mapFunctions.get("ipc-handler").function("extraction-video-to-audio", {inputVideoPath:"./a.mp4", outputType:"flac"})
}
}
@@ -1,16 +0,0 @@
module.exports = {
name:"module-handler", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
async function(module,parameter){
return new Promise(async (resolve, reject) => {
if(mapFunctions.get(module) == undefined){
reject("requested modules not found")
return
}
mapFunctions.get(module).function(parameter).then((result) => {
resolve(result)
}).catch((err) => {
reject(err)
});
})
}
}
@@ -1,7 +1,6 @@
// services/pipeline/jobs/transcribeLatest.ts
import path from 'path';
import fs from 'fs';
// @ts-ignore: module has no type declarations or cannot be resolved in current TS config
import assembly from '../../modules/transcription/assembly';
/**
-18
View File
@@ -1,18 +0,0 @@
require('dotenv').config();
const path = require('path');
const assemblyModule = require('../../services/modules/transcription-remote/assembly.js');
// Audio-Datei oder URL aus Kommandozeile, Standard: test.wav
const audioPath = process.argv[2] || './storage/audio/IMG_2978.wav';
(async () => {
try {
const transcript = await assemblyModule.run(audioPath);
console.log('Transcription succesful');
console.log('Transcript ID:', transcript?.id);
console.log('Speaker labels:', transcript?.utterances?.length || 0);
} catch (error) {
console.error('Error in Transcription:', error?.message || error);
}
})();
File diff suppressed because it is too large Load Diff
@@ -1,12 +0,0 @@
const fs = require('fs');
const transSummarizer = require("../../services/modules/jsonTools/transcriptionSummarizer.js");
// JSON-Datei laden
const inputJson = JSON.parse(fs.readFileSync("./testFile.json", "utf8"));
// Übergabe an den Summarizer
transSummarizer.function({
json: inputJson
});