Merge branch 'feature/38-sprecher-audio-snippets-s4-11' into 'develop'

extract speaker snippets mit main verknüpft.

See merge request proj-wise2526-video2document/video2document!60

main.js

@@ -198,6 +198,11 @@ electron.ipcMain.on("file_submit", async (event, args) => {
             })
         }
 
+        await mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: transcriptpath }).then(resp => {
+                        mainWindow.webContents.send("submitSpeaker", resp)
+                        console.log(resp)
+        })
+
         // 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 => {
@@ -210,7 +215,7 @@ electron.ipcMain.on("file_submit", async (event, args) => {
 // // speakerA: {source: "Pfad zur Audio File"},
 // // speakerB:.....
 // // }
-            mainWindow.webContents.send("speakers", {speakerA:"pfad1", speakerB:"pfad2"})
+//          mainWindow.webContents.send("speakers", {speakerA:"pfad1", speakerB:"pfad2"})
 //         }).catch(err => {
 //             mainWindow.webContents.send("error", err)
 //             return

package-lock.json

@@ -15,7 +15,7 @@
         "dotenv": "^17.2.3",
         "electron": "^39.1.1",
         "express": "^5.1.0",
-        "ffmpeg-static": "^5.2.0",
+        "ffmpeg-static": "^5.3.0",
         "fluent-ffmpeg": "^2.1.3",
         "html-to-docx": "^1.8.0",
         "mocha": "^11.7.5",
@@ -1773,9 +1773,9 @@
       }
     },
     "node_modules/ffmpeg-static": {
-      "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==",
+      "version": "5.3.0",
+      "resolved": "https://registry.npmjs.org/ffmpeg-static/-/ffmpeg-static-5.3.0.tgz",
+      "integrity": "sha512-H+K6sW6TiIX6VGend0KQwthe+kaceeH/luE8dIZyOP35ik7ahYojDuqlTV1bOrtEwl01sy2HFNGQfi5IDJvotg==",
       "hasInstallScript": true,
       "license": "GPL-3.0-or-later",
       "dependencies": {
@@ -1832,6 +1832,7 @@
       "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"

package.json

@@ -6,7 +6,7 @@
     "dotenv": "^17.2.3",
     "electron": "^39.1.1",
     "express": "^5.1.0",
-    "ffmpeg-static": "^5.2.0",
+    "ffmpeg-static": "^5.3.0",
     "fluent-ffmpeg": "^2.1.3",
     "html-to-docx": "^1.8.0",
     "mocha": "^11.7.5",

services/modules/audioSnippets/extract-speaker-snippets.js

@@ -0,0 +1,95 @@
+
+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");
+                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);
+                    return;
+                }
+
+                if (!Array.isArray(entries)) {
+                    console.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`);
+
+                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();
+                        })
+                        .run();
+                });
+
+            }
+            resolve(output)
+            console.log("\nAlle Speaker-Snippets erstellt\n");
+        })
+    }
+};

services/modules/utility/@startup.js

@@ -10,6 +10,7 @@ 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' });