Compare commits

..

11 Commits

Author SHA1 Message Date
MikeHughes-BIN b6276b005e Removed Parakeet again as it requires PyTorch which is too large for this project 2026-01-18 19:13:18 +01:00
MikeHughes-BIN 8f2024df14 Refactor HTML structure for improved readability and maintainability 2026-01-18 19:12:04 +01:00
MikeHughes-BIN 0f548b3012 Add function to send speaker packages and handle errors 2026-01-18 19:05:55 +01:00
Hughes, Mike 7fbf0c59d1 Merge branch 'feature/ui-test' into 'develop'
Feature/ui test

See merge request proj-wise2526-video2document/video2document!96
2026-01-18 18:02:35 +01:00
Hughes, Mike ef20a08d9f Merge branch 'fix/speaker-selection' into 'develop'
Speakers that have been renamed will stay in the selection as requested by Oliver

See merge request proj-wise2526-video2document/video2document!97
2026-01-18 18:00:53 +01:00
Hughes, Mike 6813b45c80 Merge branch 'develop' into 'feature/ui-test'
# Conflicts:
#   main.js
2026-01-18 17:38:36 +01:00
MikeHughes-BIN 773e8b471c Remove notification for successful file download in ipcMain handler 2026-01-18 17:37:47 +01:00
MikeHughes-BIN 013c9b5f2c Refactor file download handling to improve error management and user notifications 2026-01-18 17:32:29 +01:00
MikeHughes-BIN 18e791d56e Refactor code formatting and improve error handling in htmlDocumentConverter 2026-01-18 17:28:41 +01:00
MikeHughes-BIN 1ed386fcf4 Enhance file download handling and format validation in htmlDocumentConverter 2026-01-18 17:02:29 +01:00
MikeHughes-BIN c98d7761b2 Refactor UI elements for step selection and speaker management; improve styling and accessibility 2026-01-18 16:55:42 +01:00
8 changed files with 718 additions and 553 deletions
+329 -223
View File
@@ -1,234 +1,340 @@
<!DOCTYPE html> <!doctype html>
<html lang="de"> <html lang="de">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title id="title">Video to document</title>
<link rel="stylesheet" href="style.css" />
<link
rel="stylesheet"
href="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/themes/light.css"
/>
</head>
<head> <body>
<meta charset="UTF-8"> <div id="h1-wrapper">
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <section class="p-menu1">
<title id="title">Video to document</title> <nav id="navbar" class="navigation" role="navigation">
<link rel="stylesheet" href="style.css"> <input id="toggle1" type="checkbox" />
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/themes/light.css"> <label class="hamburger1" for="toggle1">
</head> <div class="top"></div>
<div class="meat"></div>
<div class="bottom"></div>
</label>
<body> <nav class="menu1">
<button id="customDocBtn" onclick="showCD()">
<div id="h1-wrapper"> Manage document types
<section class="p-menu1"> </button>
<nav id="navbar" class="navigation" role="navigation"> <a href="help_page.html" class="li1">Help</a>
<input id="toggle1" type="checkbox" /> </nav>
<label class="hamburger1" for="toggle1">
<div class="top"></div>
<div class="meat"></div>
<div class="bottom"></div>
</label>
<nav class="menu1">
<button id="customDocBtn" onclick="showCD()">Manage document types</button>
<a href="help_page.html" class="li1">Help</a>
</nav> </nav>
</nav> </section>
</section>
<h1 id="h1">Video to document</h1> <h1 id="h1">Video to document</h1>
<div class="gui-language"> <div class="gui-language">
<select name="language_option" id="language_option"></select> <select name="language_option" id="language_option"></select>
</div>
</div>
<div class="step-nav">
<div class="step-item active" data-step="1" id="step_nav1">1. Step</div>
<div class="step-item" data-step="2" id="step_nav2">2. Step</div>
<div class="step-item" data-step="3" id="step_nav3">3. Step</div>
<div class="step-item" data-step="4" id="step_nav4">4. Step</div>
<div class="step-item" data-step="5" id="step_nav5">5. Step</div>
<div class="step-item" data-step="6" id="step_nav6">6. Step</div>
</div>
<div id="middleContainerWrapper" class="middle-container-wrapper">
<button id="prevBtn" class="navBtn" disabled>&larr;</button>
<!-- Visible middle part-->
<div class="mitte" id="mitte">
<!--Costum document section-->
<div class="container" id="cdContainer" style="display:none;">
<h1 id="cd_h1">Manage document types</h1>
<label for="existingDocs" id="cd_existingDocs">Select existing documents (optional):</label>
<!--Drop Down-->
<select name="existingDocs" id="existingDocs">
<option value="newDoc" id="newDoc">-- Create new document --</option>
</select>
<div id="docNameWrapper">
<label for="docName" id="cd_docName">Document name:</label>
<input type="text" id="docName" placeholder="Enter the document name here">
</div>
<label for="prompt" id="cd_promt">Your prompt:</label>
<textarea id="prompt" placeholder="Type the prompt for your document here..."></textarea>
<div class="buttons">
<button id="goBackBtn">Return</button>
<button id="deleteBtn">Delete document</button>
<button id="generateBtn">Save document</button>
</div>
<div id="result"></div>
</div>
<!-- Here starts code from step 1-->
<div class="step" id="step1">
<h2 class="h2">Upload your video here:</h2>
<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>
</div>
<!-- Here starts code from step 2-->
<div class="step" id="step2" style="display:none;">
<h2 class="h2">Choose your preferences:</h2>
<div class="KI-wrapper">
<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>
<select name="output_type" id="output_type">
<option value="pdf">.pdf</option>
<option value="word">.docx</option>
<option value="txt">.txt</option>
</select>
</div>
<div class="language-wrapper">
<label id="labelLanguage">Select language:</label>
<select name="document_language_option" id="document_language_option">
</select>
</div>
</div>
<!-- Here starts code from step 3-->
<!-- Hover Effekt für Dokumentenvorschau, Fragezeichen hinter Text, drüber hoven zeigt Beispieldokument -->
<div class="step" id="step3" style="display:none;">
<div class="checkbox-group">
<h2 class="h2">Choose prefered document style:</h2>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormat" value="followup-report">
<label id="label_format" for="docFormat">Follow-up Report</label>
<div class="figure1">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover1" src="flags/germany-flag-png-large.jpg">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary1" value="agenda">
<label id="label_summary" for="docFormatSummary">Agenda</label>
<div class="figure2">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover2" src="flags/india-flag-png-large.png">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary2" value="result-protocol">
<label id="label_summary" for="docFormatSummary">Resultprotocol</label>
<div class="figure3">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover3" src="flags/united-kingdom-flag-png-large.jpg">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary3" value="sprint-planning">
<label id="label_summary" for="docFormatSummary">Sprint Planning Note</label>
<div class="figure4">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover4" src="flags/germany-flag-png-large.jpg">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatCustom" value="custom">
<select name="customDocumentTypes" id="customDocumentTypes">
</select>
</div>
</div>
</div>
<!-- Here starts code from step 4-->
<div class="step" id="step4" style="display:none;">
<h2 class="h2">Click to submit:</h2>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
<div class="testy" id="testy">
<div class="box2" id="box1">
</div>
<p id="box1_p1">---Starting---</p>
<div class="box2" id="box2">
</div>
<p id="box2_p2">---Transkribing---</p>
<div class="box2" id="box3">
</div>
<p id="box3_p3">---Document creation---</p>
<div class="box2" id="box4">
</div>
</div>
</div>
<!-- Here starts code from step 5-->
<div class="step" id="step5" style="display:none;">
<h2 class="h2">Change names of the speakers:</h2>
<div class="speakerView" id="speakerView">
<label id="labelSpeaker">Select Speaker:</label>
<select name="cur_speaker" id="cur_speaker">
</select>
</div>
<div class="speakerAudio" id="speakerAutio">
<label id="labelSpeakerAudio">Selected Speaker:</label>
<audio controls id="speakerAudioViewer">
Currently there is no audio file here.
</audio>
</div>
<div class="speakerWrite" id="speakerWrite">
<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>
</div>
<!-- Here starts code from step 6-->
<div class="step" id="step6" style="display:none;">
<h2 class="h2">Klick to download your document:</h2>
<button class="download-btn" id="downloadButton" onclick="fileDownload()">Download</button>
</div> </div>
</div> </div>
<button id="nextBtn" class="navBtn">&rarr;</button> <div class="step-nav">
<div class="step-item active" data-step="1" id="step_nav1">1. Step</div>
<div class="step-item" data-step="2" id="step_nav2">2. Step</div>
<div class="step-item" data-step="3" id="step_nav3">3. Step</div>
<div class="step-item" data-step="4" id="step_nav4">4. Step</div>
<div class="step-item" data-step="5" id="step_nav5">5. Step</div>
<div class="step-item" data-step="6" id="step_nav6">6. Step</div>
</div>
</div> <div id="middleContainerWrapper" class="middle-container-wrapper">
<script src="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/lc_select.min.js"></script> <button id="prevBtn" class="navBtn" disabled>&larr;</button>
<script src="languages.js"></script>
<script src="script.js"></script>
<script src="./renderer.js"></script>
</body>
</html> <!-- Visible middle part-->
<div class="mitte" id="mitte">
<!--Costum document section-->
<div class="container" id="cdContainer" style="display: none">
<h1 id="cd_h1">Manage document types</h1>
<label for="existingDocs" id="cd_existingDocs"
>Select existing documents (optional):</label
>
<!--Drop Down-->
<select name="existingDocs" id="existingDocs">
<option value="newDoc" id="newDoc">
-- Create new document --
</option>
</select>
<div id="docNameWrapper">
<label for="docName" id="cd_docName">Document name:</label>
<input
type="text"
id="docName"
placeholder="Enter the document name here"
/>
</div>
<label for="prompt" id="cd_promt">Your prompt:</label>
<textarea
id="prompt"
placeholder="Type the prompt for your document here..."
></textarea>
<div class="buttons">
<button id="goBackBtn">Return</button>
<button id="deleteBtn">Delete document</button>
<button id="generateBtn">Save document</button>
</div>
<div id="result"></div>
</div>
<!-- Here starts code from step 1-->
<div class="step" id="step1">
<h2 class="h2">Upload your video here:</h2>
<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>
</div>
<!-- Here starts code from step 2-->
<div class="step" id="step2" style="display: none">
<h2 class="h2">Choose your preferences:</h2>
<div class="step2-form">
<div class="KI-wrapper">
<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>
<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>
<select
name="document_language_option"
id="document_language_option"
></select>
</div>
</div>
</div>
<!-- Here starts code from step 3-->
<!-- Hover Effekt für Dokumentenvorschau, Fragezeichen hinter Text, drüber hoven zeigt Beispieldokument -->
<div class="step" id="step3" style="display: none">
<div class="checkbox-group">
<h2 class="h2">Choose prefered document style:</h2>
<div class="checkbox-container">
<input
type="checkbox"
name="docFormat"
id="docFormat"
value="followup-report"
/>
<label id="label_format" for="docFormat">Follow-up Report</label>
<div class="figure1">
<img
class="img-icon"
src="icons/question-mark-button-icon--free-clip-art-30.png"
/>
<img
class="img-hover1"
src="flags/germany-flag-png-large.jpg"
/>
</div>
</div>
<div class="checkbox-container">
<input
type="checkbox"
name="docFormat"
id="docFormatSummary1"
value="agenda"
/>
<label id="label_summary" for="docFormatSummary">Agenda</label>
<div class="figure2">
<img
class="img-icon"
src="icons/question-mark-button-icon--free-clip-art-30.png"
/>
<img class="img-hover2" src="flags/india-flag-png-large.png" />
</div>
</div>
<div class="checkbox-container">
<input
type="checkbox"
name="docFormat"
id="docFormatSummary2"
value="result-protocol"
/>
<label id="label_summary" for="docFormatSummary"
>Resultprotocol</label
>
<div class="figure3">
<img
class="img-icon"
src="icons/question-mark-button-icon--free-clip-art-30.png"
/>
<img
class="img-hover3"
src="flags/united-kingdom-flag-png-large.jpg"
/>
</div>
</div>
<div class="checkbox-container">
<input
type="checkbox"
name="docFormat"
id="docFormatSummary3"
value="sprint-planning"
/>
<label id="label_summary" for="docFormatSummary"
>Sprint Planning Note</label
>
<div class="figure4">
<img
class="img-icon"
src="icons/question-mark-button-icon--free-clip-art-30.png"
/>
<img
class="img-hover4"
src="flags/germany-flag-png-large.jpg"
/>
</div>
</div>
<div class="checkbox-container">
<input
type="checkbox"
name="docFormat"
id="docFormatCustom"
value="custom"
/>
<select
name="customDocumentTypes"
id="customDocumentTypes"
></select>
</div>
</div>
</div>
<!-- Here starts code from step 4-->
<div class="step" id="step4" style="display: none">
<h2 class="h2">Click to submit:</h2>
<button
class="submit-btn"
id="submitButton"
onclick="checkBoxes()"
disabled
>
Submit
</button>
<div class="testy" id="testy">
<div class="box2" id="box1"></div>
<p id="box1_p1">---Starting---</p>
<div class="box2" id="box2"></div>
<p id="box2_p2">---Transkribing---</p>
<div class="box2" id="box3"></div>
<p id="box3_p3">---Document creation---</p>
<div class="box2" id="box4"></div>
</div>
</div>
<!-- Here starts code from step 5-->
<div class="step" id="step5" style="display: none">
<h2 class="h2">Change names of the speakers:</h2>
<div class="speaker-container">
<table class="speaker-table">
<tbody>
<tr>
<td class="label-cell">
<label id="labelSpeaker" for="cur_speaker"
>Select Speaker:</label
>
</td>
<td class="input-cell">
<select name="cur_speaker" id="cur_speaker"></select>
</td>
</tr>
<tr>
<td class="label-cell">
<label id="labelSpeakerAudio">Speaker Audio:</label>
</td>
<td class="input-cell">
<audio controls id="speakerAudioViewer">
Currently there is no audio file here.
</audio>
</td>
</tr>
<tr>
<td class="label-cell">
<label id="labelSpeakerWriter" for="newSpeaker"
>New Name:</label
>
</td>
<td class="input-cell">
<input
type="text"
id="newSpeaker"
placeholder="Enter new speaker name"
/>
</td>
</tr>
</tbody>
</table>
<div class="speaker-button-group">
<button id="speakerLocker" onclick="rewriteSpeakerName()">
Rename Speaker
</button>
<button id="speakerResender" onclick="sendSpeakerPackages()">
Rewrite Document
</button>
</div>
</div>
</div>
<!-- Here starts code from step 6-->
<div class="step" id="step6" style="display: none">
<h2 class="h2">Click to download your document:</h2>
<button
class="download-btn"
id="downloadButton"
onclick="fileDownload()"
>
Download
</button>
</div>
</div>
<button id="nextBtn" class="navBtn">&rarr;</button>
</div>
<script src="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/lc_select.min.js"></script>
<script src="languages.js"></script>
<script src="script.js"></script>
<script src="./renderer.js"></script>
</body>
</html>
+22 -22
View File
@@ -1,7 +1,7 @@
var languageOptions = { var languageOptions = {
"eng":{ "eng":{
"flagPath": "flags/united-kingdom-flag-png-large.jpg", "flagPath": "flags/united-kingdom-flag-png-large.jpg",
"labelKI": "Select ki:", "labelKI": "Select AI:",
"labelTranscription": "Select transcription:", "labelTranscription": "Select transcription:",
"labelLanguage": "Select language:", "labelLanguage": "Select language:",
"title": "Video to document", "title": "Video to document",
@@ -9,7 +9,7 @@ var languageOptions = {
"p1": "Drag and drop video file", "p1": "Drag and drop video file",
"fileName": "No video chosen", "fileName": "No video chosen",
"manualUploadBtn": "Search video", "manualUploadBtn": "Search video",
"checkbox_group": "Choose prefered document style:", "checkbox_group": "Choose preferred document style:",
"label_format": "Meeting report", "label_format": "Meeting report",
"label_summary": "Summary with timestamps", "label_summary": "Summary with timestamps",
"submitButton": "Submit", "submitButton": "Submit",
@@ -27,7 +27,7 @@ var languageOptions = {
"speakerResender": "Rewrite document", "speakerResender": "Rewrite document",
"downloadButton": "Download", "downloadButton": "Download",
"box1_p1": "---Starting---", "box1_p1": "---Starting---",
"box2_p2": "---Transkribing---", "box2_p2": "---Transcribing---",
"box3_p3": "---Document creation---", "box3_p3": "---Document creation---",
"labelType": "Select document type:", "labelType": "Select document type:",
@@ -46,13 +46,13 @@ var languageOptions = {
}, },
"de":{ "de":{
"flagPath": "flags/germany-flag-png-large.jpg", "flagPath": "flags/germany-flag-png-large.jpg",
"labelKI": "Waehle KI:", "labelKI": "Wähle KI:",
"labelTranscription": "Waehle Transkription:", "labelTranscription": "Wähle Transkription:",
"labelLanguage": "Waehle Sprache:", "labelLanguage": "Wähle Sprache:",
"title": "Video zu Dokument", "title": "Video zu Dokument",
"h1": "Video zu Dokument", "h1": "Video zu Dokument",
"p1": "Video per Drag & Drop ablegen", "p1": "Video per Drag & Drop ablegen",
"fileName": "Kein Video ausgewaehlt", "fileName": "Kein Video ausgewählt",
"manualUploadBtn": "Video suchen", "manualUploadBtn": "Video suchen",
"checkbox_group": "Bevorzugte Dokumentvarianten:", "checkbox_group": "Bevorzugte Dokumentvarianten:",
"label_format": "Meeting Bericht", "label_format": "Meeting Bericht",
@@ -64,7 +64,7 @@ var languageOptions = {
"step_nav4": "Schritt 4", "step_nav4": "Schritt 4",
"step_nav5": "Schritt 5", "step_nav5": "Schritt 5",
"step_nav6": "Schritt 6", "step_nav6": "Schritt 6",
"h2": "Uploade dein Video hier:", "h2": "Lade dein Video hier hoch:",
"labelSpeaker": "Wähle Sprecher:", "labelSpeaker": "Wähle Sprecher:",
"labelSpeakerAudio": "Ausgewählter Sprecher:", "labelSpeakerAudio": "Ausgewählter Sprecher:",
"labelSpeakerWriter": "Schreib Namen:", "labelSpeakerWriter": "Schreib Namen:",
@@ -72,27 +72,27 @@ var languageOptions = {
"speakerResender": "Überschreibe Dokument", "speakerResender": "Überschreibe Dokument",
"downloadButton": "Download", "downloadButton": "Download",
"box1_p1": "---Startet---", "box1_p1": "---Startet---",
"box2_p2": "---Transkribing---", "box2_p2": "---Transkribierung---",
"box3_p3": "---Dokument kreieren---", "box3_p3": "---Dokument erstellen---",
"labelType": "Wähle Dokumenttype:", "labelType": "Wähle Dokumenttyp:",
"customDocBtn": "Dokumenttypen verwalten", "customDocBtn": "Dokumenttypen verwalten",
"cd_h1": "Dokumenttypen verwalten", "cd_h1": "Dokumenttypen verwalten",
"cd_existingDocs": "Vorhandene Dokumente auswählen (optional):", "cd_existingDocs": "Vorhandene Dokumente auswählen (optional):",
"cd_docName": "Dokument Name", "cd_docName": "Dokumentname",
"docName": "Geben Sie hier den Dokumentnamen ein", "docName": "Geben Sie hier den Dokumentnamen ein",
"cd_promt": "Ihr Prompt:", "cd_promt": "Ihr Prompt:",
"prompt": "Geben Sie hier die Eingabeaufforderung für Ihr Dokument ein...", "prompt": "Geben Sie hier die Eingabeaufforderung für Ihr Dokument ein...",
"goBackBtn": "Zurück", "goBackBtn": "Zurück",
"deleteBtn": "Lösche Dokument", "deleteBtn": "Lösche Dokument",
"generateBtn": "Speicher Dokument", "generateBtn": "Speichere Dokument",
"newDoc": "-- Neues Dokument erstellen --" "newDoc": "-- Neues Dokument erstellen --"
}, },
"in":{ "in":{
"flagPath": "flags/india-flag-png-large.png", "flagPath": "flags/india-flag-png-large.png",
"labelKI": "की का चयन करें:", "labelKI": "KI का चयन करें:",
"labelTranscription": "प्रतिलेखन चुनें:", "labelTranscription": "प्रतिलेखन चुनें:",
"labelLanguage": "भाषा चुने:", "labelLanguage": "भाषा चुने:",
"title": "दस्तावेज़ के लिए वीडियो", "title": "दस्तावेज़ के लिए वीडियो",
"h1": "दस्तावेज़ के लिए वीडियो", "h1": "दस्तावेज़ के लिए वीडियो",
"p1": "वीडियो फ़ाइल खींचें और छोड़ें", "p1": "वीडियो फ़ाइल खींचें और छोड़ें",
@@ -101,7 +101,7 @@ var languageOptions = {
"checkbox_group": "पसंदीदा दस्तावेज़ शैली चुनें:", "checkbox_group": "पसंदीदा दस्तावेज़ शैली चुनें:",
"label_format": "बैठक रिपोर्ट", "label_format": "बैठक रिपोर्ट",
"label_summary": "टाइमस्टैम्प के साथ सारांश", "label_summary": "टाइमस्टैम्प के साथ सारांश",
"submitButton": "जमा करना", "submitButton": "जमा करें",
"step_nav1": "स्टेप 1", "step_nav1": "स्टेप 1",
"step_nav2": "स्टेप 2", "step_nav2": "स्टेप 2",
"step_nav3": "स्टेप 3", "step_nav3": "स्टेप 3",
@@ -110,11 +110,11 @@ var languageOptions = {
"step_nav6": "स्टेप 6", "step_nav6": "स्टेप 6",
"h2": "अपना वीडियो यहां अपलोड करें:", "h2": "अपना वीडियो यहां अपलोड करें:",
"labelSpeaker": "स्पीकर चुनें:", "labelSpeaker": "स्पीकर चुनें:",
"labelSpeakerAudio": "चयनित वक्ता:", "labelSpeakerAudio": "चयनित स्पीकर:",
"labelSpeakerWriter": "नाम लिखें:", "labelSpeakerWriter": "नाम लिखें:",
"speakerLocker": "स्पीकर का नाम बदलें", "speakerLocker": "स्पीकर का नाम बदलें",
"speakerResender": "दस्तावेज़ पुनः लिखें", "speakerResender": "दस्तावेज़ फिर से लिखें",
"downloadButton": "डाउनलोड करना", "downloadButton": "डाउनलोड करें",
"box1_p1": "---प्रारंभ---", "box1_p1": "---प्रारंभ---",
"box2_p2": "---प्रतिलेखन---", "box2_p2": "---प्रतिलेखन---",
"box3_p3": "---दस्तावेज़ निर्माण---", "box3_p3": "---दस्तावेज़ निर्माण---",
@@ -127,10 +127,10 @@ var languageOptions = {
"docName": "यहां दस्तावेज़ का नाम दर्ज करें", "docName": "यहां दस्तावेज़ का नाम दर्ज करें",
"cd_promt": "आपका संकेत:", "cd_promt": "आपका संकेत:",
"prompt": "अपने दस्तावेज़ के लिए प्रॉम्प्ट यहां टाइप करें...", "prompt": "अपने दस्तावेज़ के लिए प्रॉम्प्ट यहां टाइप करें...",
"goBackBtn": "वापस करना", "goBackBtn": "वापस जाएं",
"deleteBtn": "दस्तावेज़ हटाए", "deleteBtn": "दस्तावेज़ हटाए",
"generateBtn": "दस्तावेज़ सहेजें", "generateBtn": "दस्तावेज़ सहेजें",
"newDoc": "-- नया दस्तावेज़ बनाए --" "newDoc": "-- नया दस्तावेज़ बनाए --"
} }
+11 -1
View File
@@ -499,4 +499,14 @@ function reloadDocuments() {
existingDocs.appendChild(option); existingDocs.appendChild(option);
}); });
}); });
} }
function sendSpeakerPackages() {
try {
window.submitSpeaker.speaker_submit(speakerAudios);
} catch (error) {
console.log(error);
}
}
window.sendSpeakerPackages = sendSpeakerPackages;
+127 -22
View File
@@ -11,12 +11,12 @@ body {
} }
#h1 { #h1 {
position: absolute; position: static;
left: 50%; transform: none;
top: 50%;
transform: translate(-50%, -50%);
margin: 0; margin: 0;
z-index: 20; z-index: 20;
flex: 1;
text-align: center;
} }
#h1-wrapper { #h1-wrapper {
@@ -30,6 +30,26 @@ body {
margin-bottom: 10px; margin-bottom: 10px;
display: flex; display: flex;
align-items: center; align-items: center;
justify-content: space-between;
padding: 0 20px;
box-sizing: border-box;
}
.gui-language {
position: absolute;
right: 20px;
top: 50%;
transform: translateY(-50%);
z-index: 100;
pointer-events: auto;
}
#language_option {
padding: 8px 12px;
border-radius: 4px;
border: 1px solid #ccc;
font-size: 14px;
cursor: pointer;
} }
.upload-container { .upload-container {
@@ -85,7 +105,6 @@ body {
#previewThumbnail { #previewThumbnail {
width: 150px; width: 150px;
height: 100px; height: 100px;
/*border: 1px dashed black;*/
} }
.custom-btn { .custom-btn {
@@ -108,8 +127,9 @@ body {
background-color: #0056b3; background-color: #0056b3;
} }
#step2 { .step h2 {
gap: 25px; width: 100%;
text-align: center;
} }
.KI-wrapper { .KI-wrapper {
@@ -356,7 +376,10 @@ input[type="file"] {
#ai_type, #ai_type,
#transkript_type, #transkript_type,
#language_option { #language_option {
padding: 3px; padding: 8px 12px;
border-radius: 4px;
border: 1px solid #ccc;
font-size: 14px;
} }
.labelDiv { .labelDiv {
@@ -404,7 +427,6 @@ input[type="file"] {
.step { .step {
margin-top: 40px; margin-top: 40px;
margin-bottom: 40px; margin-bottom: 40px;
;
display: flex; display: flex;
flex-direction: column; flex-direction: column;
min-height: 425px; min-height: 425px;
@@ -579,7 +601,27 @@ li {
transition: all 0.3s ease; transition: all 0.3s ease;
} }
#step2,
#step2 {
font-size: larger;
align-items: center;
}
.step2-form {
width: 100%;
max-width: 420px;
display: flex;
flex-direction: column;
gap: 24px; /* DAS ist dein Spacing */
}
.step2-row {
display: flex;
flex-direction: column;
gap: 6px;
}
#step3, #step3,
#step5 { #step5 {
font-size: larger; font-size: larger;
@@ -590,7 +632,7 @@ li {
} }
#step5 { #step5 {
align-items: flex-start; align-items: center;
} }
.button-group { .button-group {
@@ -614,27 +656,84 @@ li {
font-size: 14px; font-size: 14px;
} }
.h2 {
font-size: 25px;
}
.speaker-container {
width: 100%;
max-width: 700px;
margin-top: 30px;
}
.speaker-table {
width: 100%;
border-collapse: collapse;
background: white;
}
.speaker-table tbody tr {
display: flex;
align-items: center;
gap: 20px;
margin-bottom: 25px;
padding: 10px 0;
}
.label-cell {
flex: 0 0 150px;
text-align: left;
}
.label-cell label {
font-weight: 400;
display: block;
}
.input-cell {
flex: 1;
}
#cur_speaker,
#newSpeaker {
width: 100%;
padding: 10px;
border-radius: 6px;
border: 1px solid #ccc;
font-size: 14px;
box-sizing: border-box;
}
#speakerAudioViewer {
width: 100%;
height: 35px;
border-radius: 6px;
}
.speaker-button-group {
display: flex;
gap: 15px;
justify-content: center;
margin-top: 30px;
}
#speakerLocker, #speakerLocker,
#speakerResender { #speakerResender {
padding: 10px 20px; padding: 12px 25px;
margin: 20px auto;
background-color: #007BFF; background-color: #007BFF;
color: white; color: white;
border: none; border: none;
border-radius: 8px; border-radius: 8px;
cursor: pointer; cursor: pointer;
font-size: 14px; font-size: 14px;
font-weight: 500;
transition: background-color 0.2s;
} }
.h2 { #speakerLocker:hover,
font-size: 25px; #speakerResender:hover {
} background-color: #0056b3;
.speakerView,
.speakerAudio,
.speakerWrite {
margin-top: auto;
margin-bottom: auto;
} }
.container { .container {
@@ -702,4 +801,10 @@ button:hover {
margin-top: 20px; margin-top: 20px;
color: #333; color: #333;
word-break: break-word; word-break: break-word;
}
.container input,
.container textarea,
.container select {
width: 100%;
} }
+34 -4
View File
@@ -168,9 +168,39 @@ electron.ipcMain.on("file_submit", async (event, args) => {
throw new Error("Unknown document type: " + args.document.type); throw new Error("Unknown document type: " + args.document.type);
} }
console.log(args); electron.ipcMain.on("file_download", async (event) => {
let audiopath = ""; try {
let transcriptpath = ""; if (!globalFinalHtmlPath) {
throw new Error("No document generated yet");
}
const format = String(globalArgs?.document?.outputType || "")
.replace('.', '')
.toLowerCase();
if (!format) {
throw new Error("No output format selected");
}
const outputPath = await mapFunctions
.get("htmlDocumentConverter")
.convert({
inputPath: globalFinalHtmlPath,
format,
showDialog: true
});
event.sender.send("download_success", {
path: outputPath,
format
});
} catch (err) {
console.error("file_download failed:", err);
event.sender.send("error", err.message || String(err));
}
});
console.log("\n\n Running the Video to Audio Extractor"); console.log("\n\n Running the Video to Audio Extractor");
// This code handles the Video to Audio extraction module call // This code handles the Video to Audio extraction module call
@@ -365,4 +395,4 @@ electron.ipcMain.handle('delete-txt-file', (event, fileName) => {
} else { } else {
return false; return false;
} }
}); });
+195 -156
View File
@@ -1,35 +1,37 @@
const fs = require('fs'); const fs = require("fs");
const path = require('path'); const path = require("path");
const puppeteer = require('puppeteer'); const puppeteer = require("puppeteer");
const htmlToDocx = require('html-to-docx'); const htmlToDocx = require("html-to-docx");
const { execSync } = require('child_process'); const { execSync } = require("child_process");
const os = require('os'); const os = require("os");
const outputDir = path.join(__dirname, "../../../storage/documents"); const outputDir = path.join(__dirname, "../../../storage/documents");
if (!fs.existsSync(outputDir)) { if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true }); fs.mkdirSync(outputDir, { recursive: true });
} }
async function showSaveDialog(defaultName, format) { async function showSaveDialog(defaultName, format) {
const platform = os.platform(); const platform = os.platform();
if (platform === 'darwin') { if (platform === "darwin") {
// macOS // macOS
const applescript = ` const applescript = `
set defaultName to "${defaultName}.${format}" set defaultName to "${defaultName}.${format}"
set theFile to choose file name with prompt "Dokument speichern als:" default name defaultName set theFile to choose file name with prompt "Dokument speichern als:" default name defaultName
POSIX path of theFile POSIX path of theFile
`; `;
try { try {
const result = execSync(`osascript -e '${applescript}'`, { encoding: 'utf8' }); const result = execSync(`osascript -e '${applescript}'`, {
return result.trim(); encoding: "utf8",
} catch (err) { });
if (err.status === 1) return null; // User canceled return result.trim();
throw err; } catch (err) {
} if (err.status === 1) return null; // User canceled
} else if (platform === 'win32') { throw err;
}
} else if (platform === "win32") {
const safeName = decodeURIComponent(defaultName); const safeName = decodeURIComponent(defaultName);
const powershell = ` const powershell = `
@@ -43,155 +45,192 @@ async function showSaveDialog(defaultName, format) {
`; `;
try { try {
const result = execSync( const result = execSync(
`powershell -NoProfile -Command "${powershell.replace(/\r?\n/g, ' ')}"`, `powershell -NoProfile -Command "${powershell.replace(/\r?\n/g, " ")}"`,
{ encoding: 'utf8' } { encoding: "utf8" },
); );
return result.trim() || null; return result.trim() || null;
} catch (err) { } catch (err) {
if (err.status === 1) return null; // User cancelled if (err.status === 1) return null; // User cancelled
throw new Error("Save dialog failed: " + err.message); throw new Error("Save dialog failed: " + err.message);
} }
} else { } else {
// Linux - zenity oder kdialog // Linux - zenity oder kdialog
try { try {
const result = execSync( const result = execSync(
`zenity --file-selection --save --confirm-overwrite --filename="${defaultName}.${format}"`, `zenity --file-selection --save --confirm-overwrite --filename="${defaultName}.${format}"`,
{ encoding: 'utf8' } { encoding: "utf8" },
); );
return result.trim(); return result.trim();
} catch (err) { } catch (err) {
try { try {
const result = execSync( const result = execSync(
`kdialog --getsavefilename . "${defaultName}.${format}"`, `kdialog --getsavefilename . "${defaultName}.${format}"`,
{ encoding: 'utf8' } { encoding: "utf8" },
); );
return result.trim(); return result.trim();
} catch (err2) { } catch (err2) {
// Fallback // Fallback
return path.join(os.homedir(), 'Downloads', `${defaultName}.${format}`); return path.join(os.homedir(), "Downloads", `${defaultName}.${format}`);
} }
}
} }
}
} }
const module_exports = { const module_exports = {
name: "htmlDocumentConverter", name: "htmlDocumentConverter",
type: "converter", type: "converter",
displayname: "HTML Document Converter", displayname: "HTML Document Converter",
description: "Converts LLM-generated HTML to PDF, DOCX, TXT, or HTML", description: "Converts LLM-generated HTML to PDF, DOCX, TXT, or HTML",
/** /**
* Main conversion function * Main conversion function
* @param {Object} options * @param {Object} options
* @param {string} options.inputPath - Path to the HTML input * @param {string} options.inputPath - Path to the HTML input
* @param {string} options.format - 'pdf' | 'docx' | 'html' | 'txt' * @param {string} options.format - 'pdf' | 'docx' | 'html' | 'txt'
* @param {string} [options.outputName] - Optional output filename (without extension) * @param {string} [options.outputName] - Optional output filename (without extension)
* @param {boolean} [options.showDialog] - Show save dialog (default: false in module mode, true in CLI mode) * @param {boolean} [options.showDialog] - Show save dialog (default: false in module mode, true in CLI mode)
*/ */
async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) { async convert({ inputPath, format = "pdf", outputName, showDialog = false }) {
if (!fs.existsSync(inputPath)) { format = format.toLowerCase().replace(".", ""); // <-- FIX
throw new Error(`Input file not found: ${inputPath}`);
}
const ext = path.extname(inputPath).toLowerCase(); if (!["pdf", "docx", "html", "txt"].includes(format)) {
const baseName = outputName || path.basename(inputPath, ext); throw new Error(`Unsupported format: ${format}`);
let outputFile;
if (showDialog) {
// Zeige nativen Dialog
outputFile = await showSaveDialog(baseName, format);
if (!outputFile) {
console.log('Speichervorgang abgebrochen.');
return null;
}
} else {
// Nutze Standard-Ausgabeverzeichnis
outputFile = path.join(outputDir, `${baseName}.${format.toLowerCase()}`);
}
let htmlContent = fs.readFileSync(inputPath, 'utf8');
// Remove <think> tags if present
htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, '');
switch (format.toLowerCase()) {
case 'html':
fs.writeFileSync(outputFile, htmlContent, 'utf8');
break;
case 'pdf':
await this.htmlToPDF(htmlContent, outputFile);
break;
case 'docx':
await this.htmlToDOCX(htmlContent, outputFile);
break;
case 'txt':
fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), 'utf8');
break;
default:
throw new Error(`Unsupported format: ${format}`);
}
console.log(`Erfolgreich gespeichert: ${outputFile}`);
return outputFile;
},
// HTML → PDF
async htmlToPDF(html, outputPath) {
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox', '--disable-setuid-sandbox']
});
const page = await browser.newPage();
await page.setContent(html, { waitUntil: 'networkidle0' });
await page.pdf({
path: outputPath,
format: 'A4',
printBackground: true,
margin: { top: '20mm', right: '20mm', bottom: '20mm', left: '20mm' }
});
await browser.close();
},
// HTML → DOCX
async htmlToDOCX(html, outputPath) {
const buffer = await htmlToDocx(html);
fs.writeFileSync(outputPath, buffer);
},
// HTML → TXT (rudimentär)
htmlToTXT(html) {
return html.replace(/<[^>]*>/g, '').replace(/\s+\n/g, '\n').trim();
} }
if (!fs.existsSync(inputPath)) {
throw new Error(`Input file not found: ${inputPath}`);
}
const ext = path.extname(inputPath).toLowerCase();
const baseName = outputName || path.basename(inputPath, ext);
let outputFile;
if (showDialog) {
// Zeige nativen Dialog
outputFile = await showSaveDialog(baseName, format);
if (!outputFile) {
console.log("Speichervorgang abgebrochen.");
return null;
}
} else {
// Nutze Standard-Ausgabeverzeichnis
outputFile = path.join(outputDir, `${baseName}.${format.toLowerCase()}`);
}
let htmlContent = fs.readFileSync(inputPath, "utf8");
// Remove <think> tags if present
htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, "");
switch (format.toLowerCase()) {
case "html":
fs.writeFileSync(outputFile, htmlContent, "utf8");
break;
case "pdf":
await this.htmlToPDF(htmlContent, outputFile);
break;
case "docx":
await this.htmlToDOCX(htmlContent, outputFile);
break;
case "txt":
fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), "utf8");
break;
default:
throw new Error(`Unsupported format: ${format}`);
}
console.log(`Erfolgreich gespeichert: ${outputFile}`);
return outputFile;
},
// HTML → PDF
async htmlToPDF(html, outputPath) {
let browser;
try {
browser = await puppeteer.launch({
headless: true,
args: ["--no-sandbox", "--disable-setuid-sandbox"],
});
const page = await browser.newPage();
await page.setContent(html, { waitUntil: "networkidle0" });
await page.pdf({
path: outputPath,
format: "A4",
printBackground: true,
margin: {
top: "20mm",
right: "20mm",
bottom: "20mm",
left: "20mm",
},
});
} finally {
if (browser) {
await browser.close();
}
}
},
// HTML → DOCX
async htmlToDOCX(html, outputPath) {
try {
// htmltodocx library converts HTML string into a Word .docx buffer
// Usage from htmltodocx docs:
// await HTMLtoDOCX(htmlString, headerHTMLString, documentOptions, footerHTMLString) [oai_citation:0‡GitHub](https://github.com/privateOmega/html-to-docx?utm_source=chatgpt.com)
const buffer = await htmlToDocx(html, null, {
table: { row: { cantSplit: true } },
});
fs.writeFileSync(outputPath, buffer);
} catch (err) {
throw new Error(`DOCX conversion failed: ${err.message}`);
}
},
// HTML → TXT
htmlToTXT(html) {
// A decent plain text conversion: strip tags and collapse whitespace
// If you want more advanced extraction consider using a library like `html-to-text` or `strip-html` [oai_citation:1‡GitHub](https://github.com/html-to-text/node-html-to-text?utm_source=chatgpt.com)
return (
html
// Remove all tags
.replace(/<[^>]+>/g, "")
// Convert multiple whitespace into single spaces
.replace(/\s+/g, " ")
.trim()
);
},
}; };
module.exports = module_exports; module.exports = module_exports;
// CLI usage mit Dialog // CLI usage mit Dialog
if (require.main === module) { if (require.main === module) {
(async () => { (async () => {
const args = process.argv.slice(2); const args = process.argv.slice(2);
if (args.length < 1) { if (args.length < 1) {
console.log('Usage: node htmlDocumentConverter.js <input.html> [format]'); console.log("Usage: node htmlDocumentConverter.js <input.html> [format]");
console.log('Formats: pdf (default), docx, html, txt'); console.log("Formats: pdf (default), docx, html, txt");
console.log(''); console.log("");
console.log('Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.'); console.log(
process.exit(1); 'Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.',
} );
process.exit(1);
}
const inputPath = args[0]; const inputPath = args[0];
const format = args[1] || 'pdf'; const format = args[1] || "pdf";
try { try {
await module_exports.convert({ await module_exports.convert({
inputPath, inputPath,
format, format,
showDialog: true showDialog: true,
}); });
} catch (err) { } catch (err) {
console.error('Konvertierung fehlgeschlagen:', err.message); console.error("Konvertierung fehlgeschlagen:", err.message);
process.exit(1); process.exit(1);
} }
})(); })();
} }
@@ -1,54 +0,0 @@
// -----------------------------------------------------------
// Parakeet (Step 3A: spawn Python minimal integration)
// -----------------------------------------------------------
const fs = require("fs");
const path = require("path");
const { spawn } = require("child_process");
module.exports = {
name: "parakeet",
type: "transcription",
displayname: "NVIDIA Parakeet",
async function(audioFilePath) {
console.log("🦜 [Parakeet] Starting test integration (spawn only)...");
console.log("🦜 Input audio:", audioFilePath);
// Check audio exists
if (!fs.existsSync(audioFilePath)) {
throw new Error("Audio file does not exist: " + audioFilePath);
}
// Output path in storage/transcripts
const sessionId = path.basename(audioFilePath).replace(/\.[^.]+$/, "");
const outputDir = path.join(__dirname, "../../../storage/transcripts");
fs.mkdirSync(outputDir, { recursive: true });
const outputPath = path.join(outputDir, `${sessionId}.json`);
// -------------------------------------------------------
// SPAWN PYTHON SCRIPT (step 3A — dummy script)
// -------------------------------------------------------
return new Promise((resolve, reject) => {
const python310 = "C:\\Users\\smith\\AppData\\Local\\Programs\\Python\\Python310\\python.exe";
const py = spawn(python310, [
path.join(__dirname, "parakeet_transcribe.py"),
audioFilePath,
outputPath
]);
py.stdout.on("data", data => console.log("🦜 [Python]", data.toString().trim()));
py.stderr.on("data", data => console.error("🦜 [Python ERR]", data.toString().trim()));
py.on("close", code => {
if (code === 0) {
console.log("🦜 [Parakeet] Done (spawn test). Output:", outputPath);
resolve(outputPath);
} else {
reject(new Error("Python script failed with exit code " + code));
}
});
});
}
};
@@ -1,71 +0,0 @@
# -----------------------------------------------------------
# Parakeet Real Transcriber (NVIDIA NeMo + PyTorch GPU)
# -----------------------------------------------------------
import sys
import json
import soundfile as sf
import torch
from nemo.collections.asr.models import ASRModel
# Args:
# sys.argv[1] = input audio path
# sys.argv[2] = output JSON path
audio_path = sys.argv[1]
output_path = sys.argv[2]
print("🔥 Starting Parakeet model...")
device = "cuda" if torch.cuda.is_available() else "cpu"
print("🔥 Using device:", device)
# -----------------------------------------------------------
# Load Parakeet model (NVIDIA pretrained ASR)
# -----------------------------------------------------------
model = ASRModel.from_pretrained(model_name="nvidia/parakeet-ctc-0.6b")
model = model.to(device)
model.eval()
# -----------------------------------------------------------
# Load audio
# -----------------------------------------------------------
print("🎧 Loading audio:", audio_path)
audio, sr = sf.read(audio_path)
# model expects mono float32
if len(audio.shape) > 1:
audio = audio.mean(axis=1)
audio = audio.astype("float32")
# -----------------------------------------------------------
# Run inference
# -----------------------------------------------------------
print("🧠 Running inference...")
with torch.no_grad():
hyp = model.transcribe([audio])[0]
# Extract only the text
if hasattr(hyp, "text"):
transcript = hyp.text
else:
# fallback: convert to string (rare)
transcript = str(hyp)
print("📄 Transcript:", transcript)
# -----------------------------------------------------------
# Save JSON format compatible with V2D pipeline
# -----------------------------------------------------------
result = {
"id": output_path.split("/")[-1].replace(".json", ""),
"tool": "nemo_parakeet",
"status": "completed",
"text": transcript,
"words": [] # Parakeet XS doesnt return word timestamps
}
with open(output_path, "w", encoding="utf-8") as f:
json.dump(result, f, indent=2, ensure_ascii=False)
print("✔ JSON saved at:", output_path)