Compare commits

..

2 Commits

Author SHA1 Message Date
Hughes, Mike 431039d002 Merge branch 'develop' into 'feature/meeting_document_types'
# Conflicts:
#   electron/main/script.js
#   main.js
2025-12-16 15:40:27 +01:00
MikeHughes-BIN 597f4bfca5 Meeting Report Types connected from Backend to frontend 2025-12-16 15:26:15 +01:00
23 changed files with 192 additions and 561 deletions
-1
View File
@@ -24,5 +24,4 @@ job-test:
- npm install
- echo "ASSEMBLYAI_API_KEY=$apikey_assembly" > .env
- echo "GOOGLE_API_KEY=$apikey_gemini" >> .env
- echo "SAIA_API_KEY=$apikey_saia" >> .env
- npm test
+81 -44
View File
@@ -1,56 +1,93 @@
# Video2Document
## Getting started
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
## Add your files
- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
- [ ] [Add files using the command line](https://docs.gitlab.com/topics/git/add_files/#add-files-to-a-git-repository) or push an existing Git repository with the following command:
```
cd existing_repo
git remote add origin https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git
git branch -M main
git push -uf origin main
```
## Integrate with your tools
- [ ] [Set up project integrations](https://gitlab.rlp.net/proj-wise2526-video2document/video2document/-/settings/integrations)
## Collaborate with your team
- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
- [ ] [Set auto-merge](https://docs.gitlab.com/user/project/merge_requests/auto_merge/)
## Test and Deploy
Use the built-in continuous integration in GitLab.
- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/)
- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
***
# Editing this README
When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
## Suggestions for a good README
Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
## Name
Choose a self-explaining name for your project.
## Description
Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
## Badges
On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
## Visuals
Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
## Installation
Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
Follow the steps below to install Video2Document (v2d):
## Usage
Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
### 1. Install Node.js
## Support
Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
Download and install Node.js from [https://nodejs.org/en](https://nodejs.org/en)
## Roadmap
If you have ideas for releases in the future, it is a good idea to list them in the README.
### 2. Clone the Repository
## Contributing
State if you are open to contributions and what your requirements are for accepting them.
Clone the repository using Git:
For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
```bash
git clone https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git
```
You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
Alternatively, you can download the ZIP file and extract it manually.
## Authors and acknowledgment
Show your appreciation to those who have contributed to the project.
### 3. Start the Program
## License
For open source projects, say how it is licensed.
The start scripts automatically install dependencies and launch the program. Choose the appropriate method for your operating system:
**Windows:**
```bash
start.bat
```
**Linux:**
```bash
./start.sh
```
**macOS:**
```bash
./start.sh
```
#### Alternative: Manual Installation and Start
If the start scripts don't work, you can manually install dependencies and start the program:
```bash
cd video2document
npm install
npm start
```
### 5. Install FFmpeg
Make sure that **ffmpeg** is installed on your system, as it may be required for video processing.
---
**Installation complete!** You're now ready to use Video2Document.
## Project status
If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
-161
View File
@@ -1,161 +0,0 @@
<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Custom Document</title>
<style>
body {
font-family: Arial, sans-serif;
background: #f0f2f5;
margin: 0;
padding: 0;
display: flex;
justify-content: center;
align-items: center;
min-height: 100vh;
}
.container {
background: white;
padding: 30px;
margin-top: 50px;
border-radius: 12px;
box-shadow: 0 4px 20px rgba(0,0,0,0.1);
width: 90%;
max-width: 600px;
}
h1 {
text-align: center;
color: #333;
}
label {
font-weight: bold;
margin-top: 15px;
display: block;
color: #555;
}
input[type="text"], textarea, select {
width: 100%;
padding: 10px;
margin-top: 5px;
border-radius: 6px;
border: 1px solid #ccc;
font-size: 14px;
}
textarea {
height: 120px;
resize: vertical;
}
.buttons {
display: flex;
justify-content: space-between;
margin-top: 25px;
}
button {
padding: 10px 20px;
font-size: 14px;
border: none;
border-radius: 6px;
cursor: pointer;
transition: 0.2s;
background-color: #007BFF;
color: white;
}
button:hover {
background-color: #0056b3;
}
@media (max-width: 500px) {
.buttons {
flex-direction: column;
}
.buttons button {
width: 100%;
margin-top: 10px;
}
}
#result {
margin-top: 20px;
color: #333;
word-break: break-word;
}
</style>
</head>
<body>
<div class="container">
<h1>Custom Document Generator</h1>
<label for="docName">Dokumentname:</label>
<input type="text" id="docName" placeholder="Gib hier den Dokumentnamen ein">
<label for="existingDocs">Vorhandene Dokumente auswählen (optional):</label>
<select id="existingDocs">
<option value="">-- Neues Dokument erstellen --</option>
<option value="meeting_report_001">Meeting Report 001</option>
<option value="summary_01">Summary 01</option>
<option value="project_plan_A">Project Plan A</option>
</select>
<label for="prompt">Dein Prompt:</label>
<textarea id="prompt" placeholder="Schreibe hier den Prompt für dein Dokument..."></textarea>
<div class="buttons">
<a href="index.html">
<button id="goBackBtn">Abbrechen</button>
</a>
<button id="generateBtn">Dokument speichern</button>
</div>
<div id="result"></div>
</div>
<script>
const goBackBtn = document.getElementById("goBackBtn");
const generateBtn = document.getElementById("generateBtn");
const existingDocs = document.getElementById("existingDocs");
const docNameInput = document.getElementById("docName");
const promptInput = document.getElementById("prompt");
const resultDiv = document.getElementById("result");
// Zurück zur Haupt-GUI
goBackBtn.addEventListener("click", () => {
window.electronAPI.goBackToMain();
});
// Generiere Dokument
generateBtn.addEventListener("click", () => {
const prompt = promptInput.value.trim();
let docName = docNameInput.value.trim();
const selectedExisting = existingDocs.value;
if (!prompt) {
alert("Bitte gib einen Prompt ein!");
return;
}
// Wenn ein vorhandenes Dokument ausgewählt wurde, hängt der Prompt daran
if (selectedExisting) {
docName = selectedExisting; // prompt wird an vorhandenes Dokument angehängt
} else if (!docName) {
alert("Bitte gib einen Dokumentnamen ein, wenn du ein neues Dokument erstellen möchtest!");
return;
}
// Demo-Ausgabe im Result-Div
resultDiv.innerHTML = `<strong>Dokumentname:</strong> ${docName}<br><strong>Prompt:</strong> ${prompt}`;
// Hier kannst du den Prompt an dein LLM oder Module-Handler senden
// z.B. window.submit.submit({documentName: docName, prompt: prompt})
});
</script>
</body>
</html>
+16 -22
View File
@@ -19,8 +19,8 @@
</label>
<nav class="menu1">
<a href="custom_document.html" class="li1">Custom document</a>
<a href="" class="li1">Help</a>
<li class="li1">Help</li>
<li class="li1">Language</li>
</nav>
</nav>
</section>
@@ -57,34 +57,29 @@
</div>
<div class="step" id="step2" style="display:none;">
<div class="KI-wrapper">
<div class="labelDiv" id="labelDiv">
<label id="labelKI">Select ki:</label>
<select name="ai_type" id="ai_type"></select>
</div>
<div class="transcript-wrap">
<label id="labelTranscription">Select transcription:</label>
<select name="transkript_type" id="transkript_type"></select>
</div>
<div class="type-wrapper">
<label id="labelType">Select type:</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">
<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="pdf">.pdf</option>
<option value="word">.word</option>
<option value="txt">.txt</option>
</select>
</div>
<div class="language-wrapper">
<label id="labelLanguage">Select language:</label>
<img id="labelLanguageFlag" src="flags/united-kingdom-flag-png-large.jpg" width="20" height="10" >
<select name="language_option" id="language_option">
</select>
</div>
</div>
</div>
<div class="step" id="step3" style="display:none;">
<div class="step" id="step3" style="display:none;">
<div class="checkbox-group">
<label id="checkbox-label" for="checkbox-group">Choose prefered document style:</label>
<div class="checkbox-container">
@@ -134,6 +129,7 @@
<div class="speakerView" id="speakerView">
<label id="labelSpeaker">Select Speaker:</label>
<select name="cur_speaker" id="cur_speaker">
<options>Stefan</options>
</select>
</div>
<div class="speakerAudio" id="speakerAutio">
@@ -146,10 +142,8 @@
<label id="labelSpeakerWriter">Write name:</label>
<input type="text" id="newSpeaker">
</div>
<div class="speakerButton-group">
<button id="speakerLocker" onclick="rewriteSpeakerName()">Rename Speaker</button>
<button id="speakerResender" onclick="sendSpeakerPackages()">Rewrite document</button>
</div>
<button id="speakerLocker" onclick="rewriteSpeakerName()">Rename Speaker</button>
<button id="speakerResender" onclick="sendSpeakerPackages()">Rewrite document</button>
</div>
<div class="step" id="step6" style="display:none;">
+1 -1
View File
@@ -23,7 +23,7 @@ try {
speakerAudios: (callback) => ipcRenderer.on('speakerAudios', callback)
})
contextBridge.exposeInMainWorld("submitSpeaker", {
speaker_submit: (speaker_names) => {ipcRenderer.send("speaker_submit", speaker_names)}
submitSpeaker: (speaker_names) => {ipcRenderer.send("speaker_submit", speaker_names)}
})
contextBridge.exposeInMainWorld("download", {
+4 -4
View File
@@ -19,6 +19,7 @@ uploadContainer.addEventListener("drop", (e) => {
const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
var pathToLower = filePath.toLowerCase();
if(testEndings.some(e => pathToLower.endsWith(e))){
document.getElementById("progressbar").style.visibility = "visible";
const files1 = e.dataTransfer.files;
handleFiles(files1);
}else{
@@ -27,7 +28,6 @@ uploadContainer.addEventListener("drop", (e) => {
} catch (error) {
console.log("Error in renderer.js with the listerner for the drop function");
console.log(error);
}
})
@@ -169,15 +169,15 @@ docFormatCustom.addEventListener("change", (e) =>{
//Speaker change listener
cur_speaker.addEventListener("change", (e) =>{
try {
document.getElementById("speakerAudioViewer").src = speakerAudios[document.getElementById("cur_speaker").value].src;
document.getElementById("speakerAudioViewer").src = valy[e.target.value].source;
} catch (error) {
}
});
window.audios.speakerAudios((event, arg) => {
loadSpeakerOptions(arg);
setSpeakerAudiosValue(arg);
setSpeakerAudiosValue(arg);
loadSpeakerOptions(arg);
});
window.electron.progress((event, arg) => {
+29 -24
View File
@@ -27,12 +27,22 @@ function checkBoxes() {
if(testEndings.some(e => pathToLower.endsWith(e))){
//assembly of the json for the main
var typeCheckbox;
if(document.getElementById("docFormat").checked) typeCheckbox = document.getElementById("docFormat").value;
if(document.getElementById("docFormatSummary1").checked) typeCheckbox = document.getElementById("docFormatSummary1").value;
if(document.getElementById("docFormatSummary2").checked) typeCheckbox = document.getElementById("docFormatSummary2").value;
if(document.getElementById("docFormatSummary3").checked) typeCheckbox = document.getElementById("docFormatSummary3").value;
if(document.getElementById("docFormatCustom").checked) typeCheckbox = document.getElementById("docFormatCustom").value;
/*
const selectedStyles = [checkedCounter];
var iter = 0;
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
console.log(checkbox.value);
selectedStyles[iter] = {iter: checkbox.value};
iter++;
}
});
*/
function getSelectedDocumentType() {
const checked = document.querySelector('input[name="docFormat"]:checked');
return checked ? checked.value : null;
}
document.getElementById("testy").style.visibility = "visible"
document.getElementById("box1").style.backgroundColor = "red";
@@ -53,8 +63,8 @@ function checkBoxes() {
},
"document": {
"module":aiType.value,
"type": typeCheckbox,
"outputType": outputType.value
"type": getSelectedDocumentType()
//"styles": selectedStyles
}
};
window.submit.submit(sendingPackage)
@@ -211,21 +221,16 @@ function loadLanguageOptions(){
//function to load speaker options to the drop down list
function loadSpeakerOptions(options){
try {
var menu = document.getElementById('cur_speaker');
var l = document.getElementById('cur_speaker').options.length -1;
for(i = l; i >= 0; i--){
menu.remove(i);
}
var menu = document.getElementById('speaker_option');
var object_holdy;
var choice;
object_holdy = Object.keys(options);
for(i = 0; i < object_holdy.length; i++){
object_holdy = options.keys();
for(i = 0; i < options.length; i++){
choice = document.createElement('option');
choice.textContent = options[object_holdy[i]].name;
choice.value = object_holdy[i];
choice.value = options[object_holdy[i]].name;
menu.appendChild(choice);
}
document.getElementById("speakerAudioViewer").src = options.speakerA.src;
} catch (error) {
console.log("Error in script.js loadSpeakerOptions function");
console.log(error);
@@ -286,7 +291,7 @@ function showStep(stepNumber) {
return;
}
steps.forEach(step => step.style.display = "none");
document.getElementById("step" + stepNumber).style.display = "flex";
document.getElementById("step" + stepNumber).style.display = "block";
stepButtons.forEach(btn => btn.classList.remove("active"));
document.querySelector(`.step-item[data-step="${stepNumber}"]`).classList.add("active");
@@ -307,7 +312,7 @@ function setSpeakerAudiosValue(valy){
try {
speakerAudios = valy;
speakerRewriten = valy;
document.getElementById("speakerAudioViewer").src = valy.speakerA.src;
document.getElementById("speakerAudioViewer").src = valy.speakerA.source;
} catch (error) {
}
@@ -315,17 +320,17 @@ function setSpeakerAudiosValue(valy){
function rewriteSpeakerName(){
try {
var tempy = document.getElementById("cur_speaker").value;
speakerAudios[tempy].name = document.getElementById("newSpeaker").value;
loadSpeakerOptions(speakerAudios);
var tempy = document.getElementById("cur_speaker").textContent;
speakerAudios[tempy].name = document.getElementById("newSpeaker").textContent;
document.getElementById("cur_speaker").textContent = document.getElementById("newSpeaker").textContent;
} catch (error) {
console.log("\n\n\n" + error + "\n\n\n")
}
}
function sendSpeakerPackages(){
try {
window.submitSpeaker.speaker_submit(speakerAudios);
window.sendSpeakerPackages(speakerAudios);
} catch (error) {
}
+11 -45
View File
@@ -17,6 +17,7 @@ body {
transform: translate(-50%, -50%);
margin: 0;
z-index: 20;
}
#h1-wrapper {
@@ -107,14 +108,6 @@ body {
.submit-btn:hover {
background-color: #0056b3;
}
#step2 {
gap: 30px;
}
.KI-wrapper {
margin-top: 40px;
}
input[type="file"] {
display: none;
@@ -183,10 +176,11 @@ input[type="file"] {
.submit-btn {
display: flex;
align-items: center;
justify-content: center;
padding: 10px 20px;
margin: 130px auto 10px auto;
margin-left: 80px;
margin-top: 30px;
margin-bottom: 10px;
background-color: #007BFF;
color: white;
border: none;
@@ -300,6 +294,7 @@ input[type="file"] {
margin-top: 70px;
display: flex;
flex-direction: column;
justify-content: center;
min-height: 400px;
}
@@ -425,6 +420,7 @@ li {
border-radius: 5px;
background-color: #1C3B69;
margin: 0;
display: -ms-grid;
display: grid;
grid-template-rows: 1fr repeat(4, 0.5fr);
grid-row-gap: 25px;
@@ -440,21 +436,19 @@ li {
-webkit-transition: all 0.3s ease;
}
.menu1 a:first-child {
.menu1 li:first-child {
margin-top: 30px;
}
.menu1 a:last-child {
.menu1 li:last-child {
margin-bottom: 30px;
}
.li1 {
color: #fff;
width: 100%;
margin: 0;
padding: 10px 0px;
padding: 10px 0;
font: 700 20px 'Oswald', sans-serif;
text-decoration: none;
}
.li1:hover {
@@ -469,29 +463,12 @@ li {
font-size: larger;
}
#step4 {
align-items: center;
}
#step5 {
align-items: flex-start;
}
.button-group {
display: flex;
gap: 12px;
justify-content: center;
margin-top: 10px;
}
.download-btn {
display: flex;
align-items: center;
justify-content: center;
padding: 10px 20px;
margin-left: auto;
margin-right: 0px;
margin-top: 130px;
margin-left: 80px;
margin-top: 30px;
margin-bottom: 10px;
background-color: #007BFF;
color: white;
@@ -499,15 +476,4 @@ li {
border-radius: 8px;
cursor: pointer;
font-size: 14px;
}
#speakerLocker, #speakerResender{
padding: 10px 20px;
margin: 20px auto;
background-color: #007BFF;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
font-size: 14px;
}
+23 -13
View File
@@ -194,26 +194,39 @@ electron.ipcMain.on("file_submit", async (event, args) => {
console.log("\n\n Running the LLM module");
// TODO implement documentation module
// This code handles the Text to Document processing module call
console.log(`\n\n Running the LLM for Document Style ${args.document.type}`);
await mapFunctions.get("module-handler").function(args.document.module, { inputTranscriptPath: transcriptpath, documentTypePath: "./storage/documentType/" + templateFile, language: "en" }).then(resp => {
console.log(resp);
globalFinalHtmlPath = resp
transcriptpath = resp
curstep++
mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
mainWindow.webContents.send("progress", { curstep: curstep, totalsteps: totalsteps })
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
// TODO actually implement this functionality
// Module to get the first few lines for each speaker to send to the frontend
// await mapFunctions.get("speaker-getter-idfk").function(transcriptpath).then(resp => {
// console.log(resp);
// transcriptpath = resp
// curstep++
// mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
// // {
// // speakerA: {source: "Pfad zur Audio File"},
// // speakerB:.....
// // }
mainWindow.webContents.send("speakers", {speakerA:"pfad1", speakerB:"pfad2"})
// }).catch(err => {
// mainWindow.webContents.send("error", err)
// return
// })
await mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: transcriptpath }).then(resp => {
mainWindow.webContents.send("speakerAudios", resp)
}).catch(err => {
mainWindow.webContents.send("error", err)
return
})
} catch (error) {
console.log(error);
}
@@ -223,9 +236,6 @@ electron.ipcMain.on("file_download", async() => {
await mapFunctions.get("htmlDocumentConverter").convert({inputPath:globalFinalHtmlPath, format: globalArgs.document.outputType, showDialog: true});
})
electron.ipcMain.on("speaker_submit", async() => {
console.log("\n\n\nJa also hier kam was an \n\n\n");
})
let q =
{
@@ -257,4 +267,4 @@ let q1 = {
{name:"abc", displayname:"ABC"},
{name:"qeg", displayname:"aqghegahu"}
]
}
}
+8 -6
View File
@@ -15,7 +15,7 @@
"dotenv": "^17.2.3",
"electron": "^39.1.1",
"express": "^5.1.0",
"ffmpeg-static": "^5.3.0",
"ffmpeg-static": "^5.2.0",
"fluent-ffmpeg": "^2.1.3",
"html-to-docx": "^1.8.0",
"mocha": "^11.7.5",
@@ -450,6 +450,7 @@
"resolved": "https://registry.npmjs.org/@types/node/-/node-24.9.2.tgz",
"integrity": "sha512-uWN8YqxXxqFMX2RqGOrumsKeti4LlmIMIyV0lgut4jx7KQBcBiW6vkDtIBvHnHIquwNfJhk8v2OtmO8zXWHfPA==",
"license": "MIT",
"peer": true,
"dependencies": {
"undici-types": "~7.16.0"
}
@@ -1305,7 +1306,8 @@
"version": "0.0.1534754",
"resolved": "https://registry.npmjs.org/devtools-protocol/-/devtools-protocol-0.0.1534754.tgz",
"integrity": "sha512-26T91cV5dbOYnXdJi5qQHoTtUoNEqwkHcAyu/IKtjIAxiEqPMrDiRkDOPWVsGfNZGmlQVHQbZRSjD8sxagWVsQ==",
"license": "BSD-3-Clause"
"license": "BSD-3-Clause",
"peer": true
},
"node_modules/diff": {
"version": "4.0.2",
@@ -1771,9 +1773,9 @@
}
},
"node_modules/ffmpeg-static": {
"version": "5.3.0",
"resolved": "https://registry.npmjs.org/ffmpeg-static/-/ffmpeg-static-5.3.0.tgz",
"integrity": "sha512-H+K6sW6TiIX6VGend0KQwthe+kaceeH/luE8dIZyOP35ik7ahYojDuqlTV1bOrtEwl01sy2HFNGQfi5IDJvotg==",
"version": "5.2.0",
"resolved": "https://registry.npmjs.org/ffmpeg-static/-/ffmpeg-static-5.2.0.tgz",
"integrity": "sha512-WrM7kLW+do9HLr+H6tk7LzQ7kPqbAgLjdzNE32+u3Ff11gXt9Kkkd2nusGFrlWMIe+XaA97t+I8JS7sZIrvRgA==",
"hasInstallScript": true,
"license": "GPL-3.0-or-later",
"dependencies": {
@@ -1830,7 +1832,6 @@
"resolved": "https://registry.npmjs.org/fluent-ffmpeg/-/fluent-ffmpeg-2.1.3.tgz",
"integrity": "sha512-Be3narBNt2s6bsaqP6Jzq91heDgOEaDCJAXcE3qcma/EJBSy5FB4cvO31XBInuAuKBx8Kptf8dkhjK0IOru39Q==",
"deprecated": "Package no longer supported. Contact Support at https://www.npmjs.com/support for more info.",
"license": "MIT",
"dependencies": {
"async": "^0.2.9",
"which": "^1.1.1"
@@ -4204,6 +4205,7 @@
"integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
"devOptional": true,
"license": "Apache-2.0",
"peer": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
+1 -1
View File
@@ -6,7 +6,7 @@
"dotenv": "^17.2.3",
"electron": "^39.1.1",
"express": "^5.1.0",
"ffmpeg-static": "^5.3.0",
"ffmpeg-static": "^5.2.0",
"fluent-ffmpeg": "^2.1.3",
"html-to-docx": "^1.8.0",
"mocha": "^11.7.5",
@@ -1,102 +0,0 @@
const ffmpeg = require("fluent-ffmpeg");
const ffmpegPath = require("ffmpeg-static");
ffmpeg.setFfmpegPath(ffmpegPath);
module.exports = {
name: "extract-speaker-snippets",
type: "audio",
displayname: "Extract Speaker Snippets",
async function(parameter) {
return new Promise(async (resolve, reject) => {
let output = {}
// console.log("Extract Speaker Snippets\n");
// Pfade
const AUDIO_PATH = parameter.audioPath; // Gesamt-Audio
const JSON_PATH = parameter.jsonPath; // json summary
const OUTPUT_DIR = path.join(__dirname, "/../../../storage/audio/speakerSnippets");
if (!AUDIO_PATH || !JSON_PATH) {
// console.error("no audioPath or jsonPath available");
reject(new Error("no audioPath or jsonPath available"));
return;
}
// Output-Ordner
if (!fs.existsSync(OUTPUT_DIR)) {
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
}
// JSON laden
let entries;
try {
entries = JSON.parse(fs.readFileSync(JSON_PATH, "utf8"));
} catch (err) {
// console.error("JSON reading failed", err);
reject(new Error(err));
return;
}
if (!Array.isArray(entries)) {
// console.error("JSON is not an Array");
reject(new Error("JSON is not an Array"));
return;
}
// Pro Speaker genau EINEN Satz merken
const speakerMap = {};
for (const item of entries) {
if (!speakerMap[item.speaker]) {
speakerMap[item.speaker] = item;
}
}
// FFmpeg pro Speaker ausführen (sequenziell)
for (const speaker of Object.keys(speakerMap)) {
const data = speakerMap[speaker];
// ms → Sekunden
const startSec = data.start / 1000;
const durationSec = (data.end - data.start) / 1000;
if (durationSec <= 0) {
// console.log(`invalid times for Speaker ${speaker}`);
continue;
}
const outFile = path.join(OUTPUT_DIR, `speaker_${speaker}.wav`);
try {
await new Promise((res, rej) => {
ffmpeg(AUDIO_PATH)
.setStartTime(startSec)
.setDuration(durationSec)
.output(outFile)
.on("end", () => {
output[`speaker${speaker}`] = {src: outFile, name: `speaker${speaker}`}
// console.log(`Snippet erstellt: speaker_${speaker}.wav`);
res();
})
.on("error", (err) => {
// console.error(`FFmpeg Fehler (${speaker})`, err.message);
rej(err);
return
})
.run();
});
} catch (error) {
reject(error)
return
}
}
resolve(output)
// console.log("\nAlle Speaker-Snippets erstellt\n");
})
}
};
+2 -3
View File
@@ -1,5 +1,5 @@
// const fs = require('fs');
// const path = require('path');
const fs = require('fs');
const path = require('path');
const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory
@@ -43,7 +43,6 @@ const module_exports = {
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
// return
// --- REST CALL ---
const response = await fetch(SAIA_URL, { //safe model response in variable
method: "POST",
-1
View File
@@ -10,7 +10,6 @@ module.exports = {
// 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'});
// let snippets = await mapFunctions.get("extract-speaker-snippets").function({audioPath:'/Users/santa/Proj25/video2document/storage/audio/KittyKat.wav', jsonPath1: '/Users/santa/Proj25/video2document/storage/transcriptionSummaries/KittyKat-1765806474958.json' });
-23
View File
@@ -1,23 +0,0 @@
@echo off
cd /d %~dp0
:: Prüfen ob Node.js installiert ist
where node >nul 2>nul
if %errorlevel% neq 0 (
echo Node.js ist nicht installiert.
pause
exit /b 1
)
echo Node.js gefunden:
node -v
npm install
if %errorlevel% neq 0 (
echo npm install fehlgeschlagen.
pause
exit /b 1
)
npm start
pause
-15
View File
@@ -1,15 +0,0 @@
#!/bin/bash
# Prüfen ob Node.js installiert ist
if ! command -v node >/dev/null 2>&1; then
echo "Node.js ist nicht installiert."
exit 1
fi
echo "Node.js gefunden: $(node -v)"
# Abhängigkeiten installieren
npm install || exit 1
# Projekt starten
npm start
-1
View File
@@ -21,6 +21,5 @@ STIL:
- Klar, kompakt
- Business-orientiert
- Keine Sprecher- oder Zeitangaben
- Namen aus dem Transkript speakerA, speakerB etc. sollen weiterhin bestehen bleiben wie sie sind und nicht im Dokument ersetzt werden
TRANSKRIPT:
-1
View File
@@ -10,7 +10,6 @@ WICHTIG:
- Nutze das Transkript als Wissensquelle
- Struktur, Tonalität und Detailgrad anpassen
- Inhalte logisch zusammenführen
- Namen aus dem Transkript speakerA, speakerB etc. sollen weiterhin bestehen bleiben wie sie sind und nicht im Dokument ersetzt werden
FORMAT:
- Passe Struktur und Stil an den Nutzerwunsch an
-1
View File
@@ -11,7 +11,6 @@ ANFORDERUNGEN:
- Keine Zeitstempel oder Sprecher-Namen zitieren
- Leite Entscheidungen und Aufgaben logisch ab, wenn sie implizit sind
- Markiere offene Punkte klar
- Namen aus dem Transkript speakerA, speakerB etc. sollen weiterhin bestehen bleiben wie sie sind und nicht im Dokument ersetzt werden
STRUKTUR DES DOKUMENTS:
1. Titel & Metadaten
-2
View File
@@ -21,7 +21,5 @@ REGELN:
- Keine Meinungen oder Spekulationen
- Keine Zeit- oder Sprecherangaben
- Sachlich, formal
- Namen aus dem Transkript speakerA, speakerB etc. sollen weiterhin bestehen bleiben wie sie sind und nicht im Dokument ersetzt werden
TRANSKRIPT:
@@ -30,6 +30,5 @@ STIL:
- Agile-konform
- Klar & umsetzungsorientiert
- Bullet Points bevorzugen
- Namen aus dem Transkript speakerA, speakerB etc. sollen weiterhin bestehen bleiben wie sie sind und nicht im Dokument ersetzt werden
TRANSKRIPT:
+16 -89
View File
@@ -21,7 +21,6 @@ let audiopath
let transcriptPath
let summarizePath
let llmpath
let speakers
describe("Unit Tests", function() {
@@ -35,7 +34,7 @@ describe("Unit Tests", function() {
// console.log(resp);
done()
}).catch(err => {
done(err);
throw err;
})
})
it('Extract .mp4 to .flac', function (done) {
@@ -44,7 +43,7 @@ describe("Unit Tests", function() {
// console.log(resp);
done()
}).catch(err => {
done(err);
throw err;
})
})
it('Extracting to a nonexistant format', function (done) {
@@ -87,7 +86,7 @@ describe("Unit Tests", function() {
transcriptPath = resp
done()
}).catch(err => {
done(err)
throw err
})
})
@@ -112,7 +111,7 @@ describe("Unit Tests", function() {
mapFunctions.get("summarize-transcription").function(transcriptPath).then(resp => {
done()
}).catch(err => {
done(err)
throw err
})
})
@@ -129,7 +128,7 @@ describe("Unit Tests", function() {
summarizePath = resp
done()
}).catch(err => {
done(err)
throw err
})
})
@@ -146,92 +145,20 @@ describe("Unit Tests", function() {
this.slow(30000)
this.timeout(120000)
it("ChatGPT", function (done){
mapFunctions.get("llm-saia_openai_gpt").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
// it("ChatGPT", function (done){
// mapFunctions.get("chatgpt").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/meetingReport.json", language: "en"}).then(resp => {
// done()
// }).catch(err => {
// throw err
// })
// })
it("Gemini", function (done){
mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/meetingReport.json", language: "en"}).then(resp => {
llmpath = resp
done()
}).catch(err => {
done(err)
})
})
it("Gemini", function (done){
mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
done()
}).catch(err => {
if(err.includes("(503)")){done()} // Error 503 is gemini overload, so an Error that they can at any time throw at us which would crash the pipeline, so we just ignore it and we just imagine that the test passed
else{
console.log(err);
done(err)
}
})
})
it("Qwen3", function (done){
mapFunctions.get("qwen3-235b-a22b").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
done()
}).catch(err => {
done(err)
})
})
it("ChatGPT (Nonexistant Type File)", function (done){
mapFunctions.get("llm-saia_openai_gpt").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Gemini (Nonexistant Type File)", function (done){
mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Qwen3 (Nonexistant Type File)", function (done){
mapFunctions.get("qwen3-235b-a22b").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
})
describe("Audio Snippet", function() {
this.slow(1000)
this.timeout(5000)
// transcriptPath = "A:\\programing\\@projects\\video2document\\storage\\transcriptionSummaries\\testvideo-1765900665001.json"
// audiopath = "A:\\programing\\@projects\\video2document\\storage\\audio\\testvideo.mp3"
it("Audio Snipper Generator", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: summarizePath }).then(resp => {
speakers = resp
done()
}).catch(err => {
done(err)
})
})
it("Audio Snipper Generator (Nonexistant Transcript File)", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: "a" }).then(resp => {
speakers = resp
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Audio Snipper Generator (Nonexistant Audio File)", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: "a", jsonPath: summarizePath }).then(resp => {
speakers = resp
done("Didnt crash")
}).catch(err => {
done()
throw err
})
})
})