feat: diarisation des locuteurs en temps réel (ECAPA-TDNN + clustering incrémental)

- Nouveau module diarizer.py : EmbeddingModel (SpeechBrain ECAPA-TDNN) + SpeakerDiarizer par session
- Backend : chargement modèle au lifespan, migration DB (colonne speaker), worker enrichi, exports avec locuteur
- Frontend : badges locuteurs colorés (8 couleurs), toggle activation, copie avec [Locuteur X]
- Config : DIARIZATION=on/off, DIARIZATION_THRESHOLD=0.70, PyTorch CPU-only dans Dockerfile
- Rétrocompatible : désactivé par défaut (DIARIZATION=off)
This commit is contained in:
Michael committed 2026-06-12 16:03:43 +02:00
1 parent ca936255e8
commit 284011428a
10 files changed
+325 -20

No files matched your search

+33 -5
View File
@@ -15,6 +15,19 @@ const state = {
const BATCH_SAMPLES = 4096; // ~256 ms de PCM 16 kHz par message WebSocket
// --- Diarisation : palette de couleurs par locuteur ---
const SPEAKER_COLORS = 8; // nombre de classes CSS .speaker-0 à .speaker-7
const speakerMap = {}; // "Speaker 1" → 0, "Speaker 2" → 1, ...
let speakerCounter = 0;
function getSpeakerColorIndex(speaker) {
if (!(speaker in speakerMap)) {
speakerMap[speaker] = speakerCounter % SPEAKER_COLORS;
speakerCounter++;
}
return speakerMap[speaker];
}
// ----------------------------------------------------------- enregistrement
async function startRecording() {
@@ -35,7 +48,11 @@ async function startRecording() {
const proto = location.protocol === 'https:' ? 'wss' : 'ws';
state.ws = new WebSocket(`${proto}://${location.host}/ws`);
state.ws.onopen = () => state.ws.send(JSON.stringify({ type: 'start', title: $('title').value }));
state.ws.onopen = () => state.ws.send(JSON.stringify({
type: 'start',
title: $('title').value,
diarization: $('diarization-cb').checked,
}));
state.ws.onmessage = onServerMessage;
state.ws.onclose = () => { if (state.recording) stopRecording(true); };
@@ -136,12 +153,20 @@ function fmtTs(seconds) {
function clearTranscript() {
$('transcript').innerHTML = '';
// Reset le mapping locuteurs pour chaque nouvelle session
for (const key in speakerMap) delete speakerMap[key];
speakerCounter = 0;
}
function appendSegment(seg) {
const div = document.createElement('div');
div.className = 'segment';
div.innerHTML = `<span class="ts">${fmtTs(seg.t0)}</span><span class="text"></span>`;
let speakerHtml = '';
if (seg.speaker) {
const ci = getSpeakerColorIndex(seg.speaker);
speakerHtml = `<span class="speaker speaker-${ci}">${seg.speaker}</span>`;
}
div.innerHTML = `<span class="ts">${fmtTs(seg.t0)}</span>${speakerHtml}<span class="text"></span>`;
div.querySelector('.text').textContent = seg.text;
$('transcript').appendChild(div);
$('transcript').scrollTop = $('transcript').scrollHeight;
@@ -199,9 +224,12 @@ async function deleteCurrentMeeting() {
}
async function copyTranscript() {
const text = [...document.querySelectorAll('#transcript .segment .text')]
.map((el) => el.textContent).join('\n');
await navigator.clipboard.writeText(text);
const lines = [...document.querySelectorAll('#transcript .segment')].map((el) => {
const speaker = el.querySelector('.speaker');
const text = el.querySelector('.text').textContent;
return speaker ? `[${speaker.textContent}] ${text}` : text;
});
await navigator.clipboard.writeText(lines.join('\n'));
$('copy-btn').textContent = '✓ Copié';
setTimeout(() => ($('copy-btn').textContent = '📋 Copier'), 1500);
}
+4
View File
@@ -24,6 +24,10 @@
<input id="title" type="text" placeholder="Titre de la réunion (optionnel)">
<button id="record-btn" class="record">● Démarrer</button>
<span id="timer">00:00</span>
<label id="diarization-toggle" class="toggle" title="Identifier les locuteurs">
<input type="checkbox" id="diarization-cb">
<span>👥 Locuteurs</span>
</label>
</section>
<section id="transcript-panel">
+40
View File
@@ -133,6 +133,46 @@ button.record.recording { background: var(--rec); }
flex-shrink: 0;
}
/* --- Diarisation : badges locuteurs --- */
.speaker {
font-size: 0.78rem;
font-weight: 600;
padding: 2px 8px;
border-radius: 6px;
flex-shrink: 0;
white-space: nowrap;
}
.speaker-0 { background: #1a2440; color: #4f7cff; }
.speaker-1 { background: #3a181a; color: #e5484d; }
.speaker-2 { background: #132a1e; color: #30a46c; }
.speaker-3 { background: #2a2410; color: #f5a623; }
.speaker-4 { background: #2a1a3a; color: #8e4ec6; }
.speaker-5 { background: #0f2a28; color: #12a594; }
.speaker-6 { background: #3a1a2a; color: #e54666; }
.speaker-7 { background: #1e2024; color: #889096; }
/* Toggle diarisation */
.toggle {
display: flex;
align-items: center;
gap: 6px;
cursor: pointer;
font-size: 0.85rem;
color: var(--muted);
user-select: none;
padding: 6px 12px;
border-radius: 10px;
background: var(--panel-2);
border: 1px solid #2c3245;
transition: border-color 0.2s, color 0.2s;
}
.toggle:hover { border-color: var(--accent); }
.toggle input { display: none; }
.toggle:has(input:checked) {
border-color: var(--accent);
color: var(--text);
}
@media (max-width: 720px) {
.layout { flex-direction: column; }
aside { width: 100%; max-height: 30vh; border-right: none; border-bottom: 1px solid #262b3a; }