conversations come back as conversations
A probe on the torch stage worker (~/dockers/torch-worker) runs beside every transcription and decides what the recording is: solo dictation returns as paragraphs exactly as before, several voices return speaker-labeled with conversation: true. Nobody declares which — the caller cannot know. Transcription and the worker each get a serial FIFO queue on their own resource, so the probe costs a solo memo nothing and multi-user traffic stays fair. The worker is optional and best-effort throughout: unreachable or failing, everything still transcribes, just never labeled. Speaker attribution is segment-granularity by maximal turn overlap — whisper.cpp's own timestamps, no alignment stage. If boundaries prove sloppy, wav2vec2 alignment returns as a worker endpoint. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Claude Fable 5
+90
-11
@@ -3,6 +3,9 @@ import { createSidecarConnector } from '@@/sidecar/connect';
|
||||
import { API_URL } from '@@/officer-url.mjs';
|
||||
import { getConfig, setConfig, redactUrl, probeWhisper } from './config';
|
||||
import { transcribeAudio } from './transcribe';
|
||||
import { toConversation } from './conversation';
|
||||
import { whisperQueue, workerQueue } from './queue';
|
||||
import { diarizeAudio, probeAudio, probeWorker, type SpeakerTurn } from './worker';
|
||||
|
||||
// The officer-transcribe sidecar. Owns the whole whisper.cpp contract for Officer: the server URL and
|
||||
// the request tuning that makes it usable for a person talking into a phone (see transcribe.ts — moved
|
||||
@@ -13,10 +16,15 @@ import { transcribeAudio } from './transcribe';
|
||||
// ─────────────────────────────────────────────────────────────────────────────────────────────────
|
||||
// HTTP CONTRACT — the platform strips its /api/transcribe mount prefix before forwarding.
|
||||
//
|
||||
// GET /_health { ok, configured, url? }
|
||||
// GET /config { configured, url } — url has its userinfo stripped, never a secret
|
||||
// PUT /config { url } — validated against the server before storing
|
||||
// POST /transcribe multipart: file, spokenLanguages[] → { text, detectedLanguage }
|
||||
// GET /_health { ok, configured, url?, worker, queues }
|
||||
// GET /config { configured, url, workerUrl } — urls have userinfo stripped, never a secret
|
||||
// PUT /config { url, workerUrl? } — both validated against their servers first
|
||||
// POST /transcribe multipart: file, spokenLanguages[]
|
||||
// → { text, detectedLanguage, conversation: false }
|
||||
// → { text: "Speaker 1: …", detectedLanguage, conversation: true, speakers }
|
||||
// The conversation probe and diarization run on the torch worker (workerUrl,
|
||||
// ~/dockers/torch-worker) behind their own queue; any worker failure degrades
|
||||
// to the plain transcript rather than failing the request.
|
||||
//
|
||||
// anything else 404
|
||||
//
|
||||
@@ -38,7 +46,11 @@ const port = getFreePort();
|
||||
|
||||
async function handleConfigGet(): Promise<Response> {
|
||||
const cfg = await getConfig();
|
||||
return Response.json({ configured: !!cfg, url: cfg ? redactUrl(cfg.url) : null });
|
||||
return Response.json({
|
||||
configured: !!cfg,
|
||||
url: cfg ? redactUrl(cfg.url) : null,
|
||||
workerUrl: cfg?.workerUrl ? redactUrl(cfg.workerUrl) : null,
|
||||
});
|
||||
}
|
||||
|
||||
function isHttpUrl(url: string): boolean {
|
||||
@@ -46,7 +58,7 @@ function isHttpUrl(url: string): boolean {
|
||||
}
|
||||
|
||||
async function handleConfigPut(req: Request): Promise<Response> {
|
||||
const body = ((await req.json().catch(() => null)) as { url?: unknown } | null) ?? {};
|
||||
const body = ((await req.json().catch(() => null)) as { url?: unknown; workerUrl?: unknown } | null) ?? {};
|
||||
const url = typeof body.url === 'string' ? body.url.trim() : '';
|
||||
if (!url) return Response.json({ error: 'url is required' }, { status: 400 });
|
||||
if (!isHttpUrl(url)) return Response.json({ error: 'url must start with http:// or https://' }, { status: 400 });
|
||||
@@ -54,10 +66,31 @@ async function handleConfigPut(req: Request): Promise<Response> {
|
||||
const probe = await probeWhisper(url);
|
||||
if (!probe.ok) return Response.json({ error: probe.error }, { status: 400 });
|
||||
|
||||
await setConfig({ url });
|
||||
return Response.json({ configured: true, url: redactUrl(url) });
|
||||
// The worker is optional, but a URL that is GIVEN must answer — storing a dead URL silently
|
||||
// would turn every future conversation back into an unlabeled wall of text with no error.
|
||||
const workerUrl = typeof body.workerUrl === 'string' ? body.workerUrl.trim() : '';
|
||||
if (workerUrl) {
|
||||
if (!isHttpUrl(workerUrl)) {
|
||||
return Response.json({ error: 'workerUrl must start with http:// or https://' }, { status: 400 });
|
||||
}
|
||||
const workerProbe = await probeWorker(workerUrl);
|
||||
if (!workerProbe.ok) return Response.json({ error: `diarization worker: ${workerProbe.error}` }, { status: 400 });
|
||||
}
|
||||
|
||||
await setConfig({ url, ...(workerUrl ? { workerUrl } : {}) });
|
||||
return Response.json({
|
||||
configured: true,
|
||||
url: redactUrl(url),
|
||||
workerUrl: workerUrl ? redactUrl(workerUrl) : null,
|
||||
});
|
||||
}
|
||||
|
||||
// The pipeline. Transcription and the conversation probe run CONCURRENTLY on their own
|
||||
// resources (whisper.cpp on its GPU, the torch worker on CPU cores), each behind its own serial
|
||||
// queue, so the probe costs a solo memo nothing — it finishes long before the transcript does.
|
||||
//
|
||||
// The probe and diarization are strictly best-effort: any worker failure logs and degrades to
|
||||
// the plain transcript. A memo must never be lost to a speaker-labeling problem.
|
||||
async function handleTranscribe(req: Request): Promise<Response> {
|
||||
const cfg = await getConfig();
|
||||
if (!cfg) {
|
||||
@@ -69,10 +102,47 @@ async function handleTranscribe(req: Request): Promise<Response> {
|
||||
if (!file || !(file instanceof File)) return Response.json({ error: 'file is required' }, { status: 400 });
|
||||
|
||||
const spokenLanguages = (body?.getAll('spokenLanguages') ?? []).map(String);
|
||||
const workerUrl = cfg.workerUrl;
|
||||
|
||||
const probePromise = workerUrl
|
||||
? workerQueue.run(() => probeAudio(file, workerUrl)).catch((err) => {
|
||||
console.error('[transcribe] conversation probe failed — returning plain transcript', err);
|
||||
return null;
|
||||
})
|
||||
: Promise.resolve(null);
|
||||
|
||||
try {
|
||||
const result = await transcribeAudio({ file, whisperUrl: cfg.url, spokenLanguages });
|
||||
return Response.json(result);
|
||||
const result = await whisperQueue.run(() => transcribeAudio({ file, whisperUrl: cfg.url, spokenLanguages }));
|
||||
const probe = await probePromise;
|
||||
|
||||
if (probe && probe.verdict !== 'solo' && workerUrl) {
|
||||
// "unsure" diarizes too: a mislabeled monologue reads fine, a missed conversation is
|
||||
// information lost for good. Reuse the probe's turns when it already covered the file.
|
||||
const turns: SpeakerTurn[] | null = probe.turns
|
||||
?? (await workerQueue.run(() => diarizeAudio(file, workerUrl)).then(
|
||||
(d) => d.turns,
|
||||
(err) => {
|
||||
console.error('[transcribe] diarization failed — returning plain transcript', err);
|
||||
return null;
|
||||
},
|
||||
));
|
||||
|
||||
if (turns && turns.length > 0) {
|
||||
const conversation = toConversation(result.segments, turns);
|
||||
// A "conversation" that clusters into one voice end-to-end is a monologue after all —
|
||||
// the paragraph rendering reads better than a wall of "Speaker 1:" prefixes.
|
||||
if (conversation.speakerCount > 1) {
|
||||
return Response.json({
|
||||
text: conversation.text,
|
||||
detectedLanguage: result.detectedLanguage,
|
||||
conversation: true,
|
||||
speakers: conversation.speakerCount,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return Response.json({ text: result.text, detectedLanguage: result.detectedLanguage, conversation: false });
|
||||
} catch (err) {
|
||||
console.error('[transcribe] transcription failed', err);
|
||||
return Response.json(
|
||||
@@ -115,7 +185,16 @@ const server = Bun.serve({
|
||||
if (!cfg) return Response.json({ ok: false, configured: false }, { status: 503 });
|
||||
const probe = await probeWhisper(cfg.url);
|
||||
if (!probe.ok) return Response.json({ ok: false, configured: true, error: probe.error }, { status: 502 });
|
||||
return Response.json({ ok: true, configured: true, url: redactUrl(cfg.url) });
|
||||
// The worker degrades rather than fails: an unreachable worker is reported but does not
|
||||
// cost the health check — transcription still works without it.
|
||||
const worker = cfg.workerUrl ? await probeWorker(cfg.workerUrl) : null;
|
||||
return Response.json({
|
||||
ok: true,
|
||||
configured: true,
|
||||
url: redactUrl(cfg.url),
|
||||
worker: worker === null ? 'not configured' : worker.ok ? 'ok' : `unreachable: ${worker.error}`,
|
||||
queues: { whisper: whisperQueue.pending, worker: workerQueue.pending },
|
||||
});
|
||||
}
|
||||
|
||||
if (url.pathname === '/config') {
|
||||
|
||||
Reference in New Issue
Block a user