emily/video2document
1
0
Fork 0
mirror of https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git synced 2026-06-15 18:01:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

worked on fixing the code

Browse Source
This commit is contained in:
santa
2025-11-24 16:40:12 +01:00
parent af13907fdc
commit a5a60635fc
4 changed files with 140 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main.js
+5 -3
View File
@@ -139,7 +139,7 @@ electron.ipcMain.on("file_submit", async (event, args) => {
let audiopath = "" let audiopath = ""
let transcriptpath = "" let transcriptpath = ""
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
await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: args.video.outputType}).then(resp => { await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: args.video.outputType}).then(resp => {
console.log(resp); console.log(resp);
@@ -164,11 +164,13 @@ electron.ipcMain.on("file_submit", async (event, args) => {
mainWindow.webContents.send("error", err) mainWindow.webContents.send("error", err)
return return
}) })
*/
console.log("\n\n Running the Transcription Summarizer module"); console.log("\n\n Running the Transcription Summarizer module");
// This code summarises the transcript, so that it can be used by an llm // This code summarises the transcript, so that it can be used by an llm
await mapFunctions.get("summarize-transcription").function(transcriptpath).then(resp => { // await mapFunctions.get("summarize-transcription").function(transcriptpath).then(resp => {
await mapFunctions.get("summarize-transcription").function('/Users/santa/Proj25/video2document/storage/transcripts/IMG_2978.json').then(resp => {
console.log(resp); console.log(resp);
transcriptpath = resp transcriptpath = resp
curstep++ curstep++
package-lock.json
Generated
+2
View File
@@ -299,6 +299,7 @@
"resolved": "https://registry.npmjs.org/@types/node/-/node-24.9.2.tgz", "resolved": "https://registry.npmjs.org/@types/node/-/node-24.9.2.tgz",
"integrity": "sha512-uWN8YqxXxqFMX2RqGOrumsKeti4LlmIMIyV0lgut4jx7KQBcBiW6vkDtIBvHnHIquwNfJhk8v2OtmO8zXWHfPA==", "integrity": "sha512-uWN8YqxXxqFMX2RqGOrumsKeti4LlmIMIyV0lgut4jx7KQBcBiW6vkDtIBvHnHIquwNfJhk8v2OtmO8zXWHfPA==",
"license": "MIT", "license": "MIT",
"peer": true,
"dependencies": { "dependencies": {
"undici-types": "~7.16.0" "undici-types": "~7.16.0"
} }
@@ -2534,6 +2535,7 @@
"integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==", "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
"dev": true, "dev": true,
"license": "Apache-2.0", "license": "Apache-2.0",
"peer": true,
"bin": { "bin": {
"tsc": "bin/tsc", "tsc": "bin/tsc",
"tsserver": "bin/tsserver" "tsserver": "bin/tsserver"
services/modules/jsonTools/transcriptionSummarizer.js
+106 -99
View File
@@ -1,5 +1,3 @@
const fs = require("fs");
const path = require("path");
// Prepare output directory (always storage/transcriptionSummaries under project root) // Prepare output directory (always storage/transcriptionSummaries under project root)
const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`; const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
@@ -14,49 +12,98 @@ module.exports = {
type: "summarizer", // value used to differentiate each module to order them in the UI type: "summarizer", // value used to differentiate each module to order them in the UI
displayname: "Summarizer", // The displayname used within the UI displayname: "Summarizer", // The displayname used within the UI
async function(args) { async function(args) {
let inputJson = args.json; return new Promise(async (resolve, reject) => {
let inputJson = args.json;
//JSON Path //JSON Path
if (args.jsonPath) { if (args.jsonPath) {
try { try {
const raw = fs.readFileSync(args.jsonPath, "utf-8"); const raw = fs.readFileSync(args.jsonPath, "utf-8");
inputJson = JSON.parse(raw); inputJson = JSON.parse(raw);
} catch (e) { } catch (e) {
console.error("Failed to load JSON from file:", e); console.error("Failed to load JSON from file:", e);
return { error: "Could not read JSON from file path." }; return { error: "Could not read JSON from file path." };
}
} }
} // JSON parsen
// JSON parsen if (typeof args === "string") {
if (typeof inputJson === "string") { try {
try { await fs.readFile(args, 'utf8', function (err, data) {
inputJson = JSON.parse(inputJson); if (err) throw err;
} catch (e) { inputJson = JSON.parse(data);
console.log("Invalid JSON in summarize-transcription"); });
return { error: "Invalid JSON" }; } catch (e) {
console.log("Invalid JSON in summarize-transcription");
console.log(e)
return { error: "Invalid JSON" };
}
} }
}
const words = inputJson.words; const words = inputJson.words;
if (!Array.isArray(words)) { if (!Array.isArray(words)) {
return { error: "No words Array found" }; return { error: "No words Array found" };
} }
const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ? const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
const result = []; const result = [];
let currentSentence = ""; let currentSentence = "";
let currentSpeaker = null; let currentSpeaker = null;
let startTime = null; let startTime = null;
let endTime = null; let endTime = null;
for (const w of words) { for (const w of words) {
if (!currentSpeaker) currentSpeaker = w.speaker; if (!currentSpeaker) currentSpeaker = w.speaker;
if (startTime === null) startTime = w.start; if (startTime === null) startTime = w.start;
endTime = w.end; endTime = w.end;
//speaker changing //speaker changing
if (currentSpeaker !== w.speaker && currentSentence) { if (currentSpeaker !== w.speaker && currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = w.start;
}
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending
if (ENDINGS.includes(lastChar) && !isAbbreviation) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = null;
endTime = null;
currentSpeaker = null;
}
}
// safe last sentence
if (currentSentence) {
const lastEntry = result[result.length - 1]; const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) { if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence; lastEntry.sentence += " " + currentSentence;
@@ -69,70 +116,30 @@ module.exports = {
end: endTime end: endTime
}); });
} }
currentSentence = "";
startTime = w.start;
} }
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending // Output as Text
if (ENDINGS.includes(lastChar) && !isAbbreviation) { const output = result.map(r =>
const lastEntry = result[result.length - 1]; `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
if (lastEntry && lastEntry.speaker === currentSpeaker) { );
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime; // Output on cosole
} else { //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
result.push({
speaker: currentSpeaker, try {
sentence: currentSentence, const jsonPath = path.join(outputDir, "transcription_result.json");
start: startTime, fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
end: endTime
}); const txtPath = path.join(outputDir, "transcription_result.txt");
} fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
currentSentence = "";
startTime = null; console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
endTime = null;
currentSpeaker = null; resolve(jsonPath);
} catch (err) {
console.error("Error saving Summary:", err);
reject(err);
} }
} })
// safe last sentence
if (currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
}
// Output as Text
const output = result.map(r =>
`Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
);
// Output on cosole
//console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
try {
const jsonPath = path.join(outputDir, "transcription_result.json");
fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
const txtPath = path.join(outputDir, "transcription_result.txt");
fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
} catch (err) {
console.error("Error saving Summary:", err);
}
} }
} }
services/modules/transcription-remote/assembly.js
+26 -20
View File
@@ -79,6 +79,8 @@ function saveTranscript(transcript, sessionId) {
fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2)); fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
console.log(`Transcript saved: ${outputPath}`); console.log(`Transcript saved: ${outputPath}`);
return outputPath;
} }
//---------------------------------------------------Modul--------------------------------------------------- //---------------------------------------------------Modul---------------------------------------------------
@@ -89,29 +91,33 @@ module.exports = {
displayname: 'AssemblyAI', displayname: 'AssemblyAI',
async function(audioFileName) { async function(audioFileName) {
try { return new Promise(async (resolve, reject) => {
// audioFileName ist nur "datei.mp3" try {
const audioPath = audioFileName; // audioFileName ist nur "datei.mp3"
const audioPath = audioFileName;
let audioUrl; let audioUrl;
if (/^https?:\/\//i.test(audioFileName)) { if (/^https?:\/\//i.test(audioFileName)) {
audioUrl = audioFileName; audioUrl = audioFileName;
} else { } else {
if (!fs.existsSync(audioPath)) { if (!fs.existsSync(audioPath)) {
throw new Error(`Audio file not found: ${audioPath}`); throw new Error(`Audio file not found: ${audioPath}`);
}
audioUrl = await uploadAudio(audioPath);
} }
audioUrl = await uploadAudio(audioPath);
const transcriptId = await createTranscript(audioUrl);
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioFileName);
resolve(saveTranscript(transcript, sessionId));
} catch (error) {
console.error('Transcription error:', error.message);
reject(error);
} }
})
const transcriptId = await createTranscript(audioUrl);
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioFileName);
saveTranscript(transcript, sessionId);
} catch (error) {
console.error('Transcription error:', error.message);
}
} }
}; };