mirror of
https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git
synced 2026-06-15 18:01:52 +02:00
Merge branch 'fix/language' into 'develop'
Fix/language See merge request proj-wise2526-video2document/video2document!99
This commit is contained in:
Hughes, Mike
+166
-81
@@ -1,16 +1,17 @@
|
|||||||
<!DOCTYPE html>
|
<!doctype html>
|
||||||
<html lang="de">
|
<html lang="de">
|
||||||
|
<head>
|
||||||
<head>
|
<meta charset="UTF-8" />
|
||||||
<meta charset="UTF-8">
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
||||||
<title id="title">Video to document</title>
|
<title id="title">Video to document</title>
|
||||||
<link rel="stylesheet" href="style.css">
|
<link rel="stylesheet" href="style.css" />
|
||||||
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/themes/light.css">
|
<link
|
||||||
</head>
|
rel="stylesheet"
|
||||||
|
href="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/themes/light.css"
|
||||||
<body>
|
/>
|
||||||
|
</head>
|
||||||
|
|
||||||
|
<body>
|
||||||
<div id="h1-wrapper">
|
<div id="h1-wrapper">
|
||||||
<section class="p-menu1">
|
<section class="p-menu1">
|
||||||
<nav id="navbar" class="navigation" role="navigation">
|
<nav id="navbar" class="navigation" role="navigation">
|
||||||
@@ -22,7 +23,9 @@
|
|||||||
</label>
|
</label>
|
||||||
|
|
||||||
<nav class="menu1">
|
<nav class="menu1">
|
||||||
<button id="customDocBtn" onclick="showCD()">Manage document types</button>
|
<button id="customDocBtn" onclick="showCD()">
|
||||||
|
Manage document types
|
||||||
|
</button>
|
||||||
<a href="help_page.html" class="li1">Help</a>
|
<a href="help_page.html" class="li1">Help</a>
|
||||||
</nav>
|
</nav>
|
||||||
</nav>
|
</nav>
|
||||||
@@ -33,7 +36,6 @@
|
|||||||
<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>
|
</div>
|
||||||
|
|
||||||
<div class="step-nav">
|
<div class="step-nav">
|
||||||
@@ -50,24 +52,34 @@
|
|||||||
|
|
||||||
<!-- Visible middle part-->
|
<!-- Visible middle part-->
|
||||||
<div class="mitte" id="mitte">
|
<div class="mitte" id="mitte">
|
||||||
|
|
||||||
<!--Costum document section-->
|
<!--Costum document section-->
|
||||||
<div class="container" id="cdContainer" style="display:none;">
|
<div class="container" id="cdContainer" style="display: none">
|
||||||
<h1 id="cd_h1">Manage document types</h1>
|
<h1 id="cd_h1">Manage document types</h1>
|
||||||
|
|
||||||
<label for="existingDocs" id="cd_existingDocs">Select existing documents (optional):</label>
|
<label for="existingDocs" id="cd_existingDocs"
|
||||||
|
>Select existing documents (optional):</label
|
||||||
|
>
|
||||||
<!--Drop Down-->
|
<!--Drop Down-->
|
||||||
<select name="existingDocs" id="existingDocs">
|
<select name="existingDocs" id="existingDocs">
|
||||||
<option value="newDoc" id="newDoc">-- Create new document --</option>
|
<option value="newDoc" id="newDoc">
|
||||||
|
-- Create new document --
|
||||||
|
</option>
|
||||||
</select>
|
</select>
|
||||||
|
|
||||||
<div id="docNameWrapper">
|
<div id="docNameWrapper">
|
||||||
<label for="docName" id="cd_docName">Document name:</label>
|
<label for="docName" id="cd_docName">Document name:</label>
|
||||||
<input type="text" id="docName" placeholder="Enter the document name here">
|
<input
|
||||||
|
type="text"
|
||||||
|
id="docName"
|
||||||
|
placeholder="Enter the document name here"
|
||||||
|
/>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<label for="prompt" id="cd_promt">Your prompt:</label>
|
<label for="prompt" id="cd_promt">Your prompt:</label>
|
||||||
<textarea id="prompt" placeholder="Type the prompt for your document here..."></textarea>
|
<textarea
|
||||||
|
id="prompt"
|
||||||
|
placeholder="Type the prompt for your document here..."
|
||||||
|
></textarea>
|
||||||
|
|
||||||
<div class="buttons">
|
<div class="buttons">
|
||||||
<button id="goBackBtn">Return</button>
|
<button id="goBackBtn">Return</button>
|
||||||
@@ -83,118 +95,175 @@
|
|||||||
<h2 class="h2">Upload your video here:</h2>
|
<h2 class="h2">Upload your video here:</h2>
|
||||||
<div class="upload-container" id="uploadContainer">
|
<div class="upload-container" id="uploadContainer">
|
||||||
<p id="p1">Drag and drop video file</p>
|
<p id="p1">Drag and drop video file</p>
|
||||||
<video id="previewThumbnail" autoplay="false">
|
<video id="previewThumbnail" autoplay="false"></video>
|
||||||
</video>
|
|
||||||
<div class="file-name" id="fileName">No video chosen</div>
|
<div class="file-name" id="fileName">No video chosen</div>
|
||||||
<div id="thumbnailContainer">
|
<div id="thumbnailContainer">
|
||||||
<img id="thumbnailImage" style="display:none;">
|
<img id="thumbnailImage" style="display: none" />
|
||||||
</div>
|
</div>
|
||||||
<button class="custom-btn" id="manualUploadBtn">Search video</button>
|
<button class="custom-btn" id="manualUploadBtn">
|
||||||
<input type="file" id="videoUpload" accept="video/*">
|
Search video
|
||||||
|
</button>
|
||||||
|
<input type="file" id="videoUpload" accept="video/*" />
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<!-- Here starts code from step 2-->
|
<!-- Here starts code from step 2-->
|
||||||
<div class="step" id="step2" style="display:none;">
|
<div class="step" id="step2" style="display: none">
|
||||||
<h2 class="h2">Choose your preferences:</h2>
|
<h2 class="h2">Choose your preferences:</h2>
|
||||||
|
|
||||||
<div class="step2-form">
|
<div class="step2-form">
|
||||||
|
<div class="KI-wrapper">
|
||||||
<div class="step2-row">
|
<label id="labelKI">Select ki:</label>
|
||||||
<label>Select ki:</label>
|
<select name="ai_type" id="ai_type"></select>
|
||||||
<select id="ai_type"></select>
|
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div class="step2-row">
|
<div class="transcript-wrap">
|
||||||
<label>Select transcription:</label>
|
<label id="labelTranscription">Select transcription:</label>
|
||||||
<select id="transkript_type"></select>
|
<select name="transkript_type" id="transkript_type"></select>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div class="step2-row">
|
<div class="type-wrapper">
|
||||||
<label>Select type:</label>
|
<label id="labelType">Select type:</label>
|
||||||
<select id="output_type">
|
<select name="output_type" id="output_type">
|
||||||
<option>.pdf</option>
|
<option value="pdf">.pdf</option>
|
||||||
<option>.docx</option>
|
<option value="word">.word</option>
|
||||||
<option>.txt</option>
|
<option value="txt">.txt</option>
|
||||||
</select>
|
</select>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div class="step2-row">
|
<div class="language-wrapper">
|
||||||
<label>Select language:</label>
|
<label id="labelLanguage">Select language:</label>
|
||||||
<select id="document_language_option"></select>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
|
<select
|
||||||
|
name="document_language_option"
|
||||||
|
id="document_language_option"
|
||||||
|
></select>
|
||||||
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<!-- Here starts code from step 3-->
|
<!-- Here starts code from step 3-->
|
||||||
|
|
||||||
<!-- Hover Effekt für Dokumentenvorschau, Fragezeichen hinter Text, drüber hoven zeigt Beispieldokument -->
|
<!-- Hover Effekt für Dokumentenvorschau, Fragezeichen hinter Text, drüber hoven zeigt Beispieldokument -->
|
||||||
<div class="step" id="step3" style="display:none;">
|
<div class="step" id="step3" style="display: none">
|
||||||
<div class="checkbox-group">
|
<div class="checkbox-group">
|
||||||
<h2 class="h2">Choose prefered document style:</h2>
|
<h2 class="h2">Choose prefered document style:</h2>
|
||||||
<div class="checkbox-container">
|
<div class="checkbox-container">
|
||||||
<input type="checkbox" name="docFormat" id="docFormat" value="followup-report">
|
<input
|
||||||
|
type="checkbox"
|
||||||
|
name="docFormat"
|
||||||
|
id="docFormat"
|
||||||
|
value="followup-report"
|
||||||
|
/>
|
||||||
<label id="label_format" for="docFormat">Follow-up Report</label>
|
<label id="label_format" for="docFormat">Follow-up Report</label>
|
||||||
<div class="figure1">
|
<div class="figure1">
|
||||||
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
|
<img
|
||||||
<img class="img-hover1" src="flags/germany-flag-png-large.jpg">
|
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>
|
</div>
|
||||||
<div class="checkbox-container">
|
<div class="checkbox-container">
|
||||||
<input type="checkbox" name="docFormat" id="docFormatSummary1" value="agenda">
|
<input
|
||||||
|
type="checkbox"
|
||||||
|
name="docFormat"
|
||||||
|
id="docFormatSummary1"
|
||||||
|
value="agenda"
|
||||||
|
/>
|
||||||
<label id="label_summary" for="docFormatSummary">Agenda</label>
|
<label id="label_summary" for="docFormatSummary">Agenda</label>
|
||||||
<div class="figure2">
|
<div class="figure2">
|
||||||
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
|
<img
|
||||||
<img class="img-hover2" src="flags/india-flag-png-large.png">
|
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>
|
</div>
|
||||||
<div class="checkbox-container">
|
<div class="checkbox-container">
|
||||||
<input type="checkbox" name="docFormat" id="docFormatSummary2" value="result-protocol">
|
<input
|
||||||
<label id="label_summary" for="docFormatSummary">Resultprotocol</label>
|
type="checkbox"
|
||||||
|
name="docFormat"
|
||||||
|
id="docFormatSummary2"
|
||||||
|
value="result-protocol"
|
||||||
|
/>
|
||||||
|
<label id="label_summary" for="docFormatSummary"
|
||||||
|
>Resultprotocol</label
|
||||||
|
>
|
||||||
<div class="figure3">
|
<div class="figure3">
|
||||||
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
|
<img
|
||||||
<img class="img-hover3" src="flags/united-kingdom-flag-png-large.jpg">
|
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>
|
</div>
|
||||||
<div class="checkbox-container">
|
<div class="checkbox-container">
|
||||||
<input type="checkbox" name="docFormat" id="docFormatSummary3" value="sprint-planning">
|
<input
|
||||||
<label id="label_summary" for="docFormatSummary">Sprint Planning Note</label>
|
type="checkbox"
|
||||||
|
name="docFormat"
|
||||||
|
id="docFormatSummary3"
|
||||||
|
value="sprint-planning"
|
||||||
|
/>
|
||||||
|
<label id="label_summary" for="docFormatSummary"
|
||||||
|
>Sprint Planning Note</label
|
||||||
|
>
|
||||||
<div class="figure4">
|
<div class="figure4">
|
||||||
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
|
<img
|
||||||
<img class="img-hover4" src="flags/germany-flag-png-large.jpg">
|
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>
|
</div>
|
||||||
<div class="checkbox-container">
|
<div class="checkbox-container">
|
||||||
<input type="checkbox" name="docFormat" id="docFormatCustom" value="custom">
|
<input
|
||||||
<select name="customDocumentTypes" id="customDocumentTypes">
|
type="checkbox"
|
||||||
</select>
|
name="docFormat"
|
||||||
|
id="docFormatCustom"
|
||||||
|
value="custom"
|
||||||
|
/>
|
||||||
|
<select
|
||||||
|
name="customDocumentTypes"
|
||||||
|
id="customDocumentTypes"
|
||||||
|
></select>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<!-- Here starts code from step 4-->
|
<!-- Here starts code from step 4-->
|
||||||
<div class="step" id="step4" style="display:none;">
|
<div class="step" id="step4" style="display: none">
|
||||||
<h2 class="h2">Click to submit:</h2>
|
<h2 class="h2">Click to submit:</h2>
|
||||||
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
|
<button
|
||||||
|
class="submit-btn"
|
||||||
|
id="submitButton"
|
||||||
|
onclick="checkBoxes()"
|
||||||
|
disabled
|
||||||
|
>
|
||||||
|
Submit
|
||||||
|
</button>
|
||||||
|
|
||||||
<div class="testy" id="testy">
|
<div class="testy" id="testy">
|
||||||
<div class="box2" id="box1">
|
<div class="box2" id="box1"></div>
|
||||||
</div>
|
|
||||||
<p id="box1_p1">---Starting---</p>
|
<p id="box1_p1">---Starting---</p>
|
||||||
<div class="box2" id="box2">
|
<div class="box2" id="box2"></div>
|
||||||
</div>
|
|
||||||
<p id="box2_p2">---Transkribing---</p>
|
<p id="box2_p2">---Transkribing---</p>
|
||||||
<div class="box2" id="box3">
|
<div class="box2" id="box3"></div>
|
||||||
</div>
|
|
||||||
<p id="box3_p3">---Document creation---</p>
|
<p id="box3_p3">---Document creation---</p>
|
||||||
<div class="box2" id="box4">
|
<div class="box2" id="box4"></div>
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<!-- Here starts code from step 5-->
|
<!-- Here starts code from step 5-->
|
||||||
<div class="step" id="step5" style="display:none;">
|
<div class="step" id="step5" style="display: none">
|
||||||
<h2 class="h2">Change names of the speakers:</h2>
|
<h2 class="h2">Change names of the speakers:</h2>
|
||||||
|
|
||||||
<div class="speaker-container">
|
<div class="speaker-container">
|
||||||
@@ -202,7 +271,9 @@
|
|||||||
<tbody>
|
<tbody>
|
||||||
<tr>
|
<tr>
|
||||||
<td class="label-cell">
|
<td class="label-cell">
|
||||||
<label id="labelSpeaker" for="cur_speaker">Select Speaker:</label>
|
<label id="labelSpeaker" for="cur_speaker"
|
||||||
|
>Select Speaker:</label
|
||||||
|
>
|
||||||
</td>
|
</td>
|
||||||
<td class="input-cell">
|
<td class="input-cell">
|
||||||
<select name="cur_speaker" id="cur_speaker"></select>
|
<select name="cur_speaker" id="cur_speaker"></select>
|
||||||
@@ -220,36 +291,50 @@
|
|||||||
</tr>
|
</tr>
|
||||||
<tr>
|
<tr>
|
||||||
<td class="label-cell">
|
<td class="label-cell">
|
||||||
<label id="labelSpeakerWriter" for="newSpeaker">New Name:</label>
|
<label id="labelSpeakerWriter" for="newSpeaker"
|
||||||
|
>New Name:</label
|
||||||
|
>
|
||||||
</td>
|
</td>
|
||||||
<td class="input-cell">
|
<td class="input-cell">
|
||||||
<input type="text" id="newSpeaker" placeholder="Enter new speaker name">
|
<input
|
||||||
|
type="text"
|
||||||
|
id="newSpeaker"
|
||||||
|
placeholder="Enter new speaker name"
|
||||||
|
/>
|
||||||
</td>
|
</td>
|
||||||
</tr>
|
</tr>
|
||||||
</tbody>
|
</tbody>
|
||||||
</table>
|
</table>
|
||||||
|
|
||||||
<div class="speaker-button-group">
|
<div class="speaker-button-group">
|
||||||
<button id="speakerLocker" onclick="rewriteSpeakerName()">Rename Speaker</button>
|
<button id="speakerLocker" onclick="rewriteSpeakerName()">
|
||||||
<button id="speakerResender" onclick="sendSpeakerPackages()">Rewrite Document</button>
|
Rename Speaker
|
||||||
|
</button>
|
||||||
|
<button id="speakerResender" onclick="sendSpeakerPackages()">
|
||||||
|
Rewrite Document
|
||||||
|
</button>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<!-- Here starts code from step 6-->
|
<!-- Here starts code from step 6-->
|
||||||
<div class="step" id="step6" style="display:none;">
|
<div class="step" id="step6" style="display: none">
|
||||||
<h2 class="h2">Click to download your document:</h2>
|
<h2 class="h2">Click to download your document:</h2>
|
||||||
<button class="download-btn" id="downloadButton" onclick="fileDownload()">Download</button>
|
<button
|
||||||
|
class="download-btn"
|
||||||
|
id="downloadButton"
|
||||||
|
onclick="fileDownload()"
|
||||||
|
>
|
||||||
|
Download
|
||||||
|
</button>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<button id="nextBtn" class="navBtn">→</button>
|
<button id="nextBtn" class="navBtn">→</button>
|
||||||
|
|
||||||
</div>
|
</div>
|
||||||
<script src="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/lc_select.min.js"></script>
|
<script src="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/lc_select.min.js"></script>
|
||||||
<script src="languages.js"></script>
|
<script src="languages.js"></script>
|
||||||
<script src="script.js"></script>
|
<script src="script.js"></script>
|
||||||
<script src="./renderer.js"></script>
|
<script src="./renderer.js"></script>
|
||||||
</body>
|
</body>
|
||||||
|
|
||||||
</html>
|
</html>
|
||||||
@@ -500,3 +500,13 @@ function reloadDocuments() {
|
|||||||
});
|
});
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
|
function sendSpeakerPackages() {
|
||||||
|
try {
|
||||||
|
window.submitSpeaker.speaker_submit(speakerAudios);
|
||||||
|
} catch (error) {
|
||||||
|
console.log(error);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
window.sendSpeakerPackages = sendSpeakerPackages;
|
||||||
@@ -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 doesn’t 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)
|
|
||||||
Reference in New Issue
Block a user