diff --git a/README.md b/README.md index a5eb642ca..2cc053180 100644 --- a/README.md +++ b/README.md @@ -121,8 +121,8 @@ listed under [In progress](#in-progress), and what comes next under [Planned](#p assistant, which can also use that browser on the sites you allow (open, read, click, type), asking before anything that sends, deletes, buys or posts. ([Web clipper](docs/web-clipper.md), [the assistant in your browser](docs/browser-assistant.md); [checks](docs/requirements.md#clip-from-the-browser)) -- **Understand it.** Transcription, people recognised by voice (long recordings go to a speech provider in pieces that - fit its limits), text on screen and in scans, faces (off by default), NSFW pictures flagged by a model on your own +- **Understand it.** Transcription, which can expect the names your namespace knows (off by default), people + recognised by voice (long recordings go to a speech provider in pieces that fit its limits), text on screen and in scans, faces (off by default), NSFW pictures flagged by a model on your own server (off by default, per namespace), entities and topics in a knowledge graph you can explore, query with Cypher or SPARQL, and see as it was at any version. Every entity has its own page at a wiki address (`/wiki//`), and entities, topics and people are edited and merged from their lists, the graph or an @@ -137,6 +137,7 @@ listed under [In progress](#in-progress), and what comes next under [Planned](#p [similar content](docs/processing.md#similar-content), [graph history](docs/graph-history.md), [topics](docs/topics.md), [video](docs/video.md), [NSFW classification](docs/nsfw.md), [long recordings](docs/speech-providers.md#long-recordings), + [your own names](docs/processing.md#your-own-names-in-transcription), [cleaning up transcripts](docs/processing.md#cleaning-up-transcripts), [dates](docs/processing.md#dates); [checks](docs/requirements.md#understand-it)) - **Learn from it.** Make a two-host podcast episode about what you pick, every claim cited and checked against its diff --git a/changelog.d/vocabulary.md b/changelog.d/vocabulary.md new file mode 100644 index 000000000..9baa6faa6 --- /dev/null +++ b/changelog.d/vocabulary.md @@ -0,0 +1,5 @@ +- **Transcription expects your own names.** With Settings → Transcription → Expect your own names on (off by + default), each recording is transcribed knowing up to 60 words its namespace already knows: the custom vocabulary, + its named people, its defined entities and the names people fixed in its transcripts. Whisper and OpenAI-compatible + servers get them as the prompt, Deepgram as key terms or keywords, AssemblyAI as key terms or boosted words; SenseVoice + and ElevenLabs take no hints ([Your own names in transcription](docs/processing.md#your-own-names-in-transcription)). diff --git a/docs/processing.md b/docs/processing.md index ab26f2861..1f2fb999b 100644 --- a/docs/processing.md +++ b/docs/processing.md @@ -23,6 +23,24 @@ How assets move through Lens: where they come from, what each step does, and how Every step takes `--ns`, `--limit` and `--force`; `run` does them all, and a lock stops two runs overlapping. +### Your own names in transcription + +Speech-to-text gets wrong the names only you use: family, colleagues, places, projects. With `transcribe.vocabulary` +on (Settings → Transcription → Expect your own names; off by default), each recording is transcribed knowing up to 60 +words its namespace already knows, in this order: + +- the custom vocabulary in Settings → Analysis (`analysis.gazetteer`), as written there; +- the names of the namespace's named people; +- its defined entities ([Entity setup](#entity-setup)); +- the words people put in when they corrected its transcripts, the capitalised ones a line didn't have before (the + text cleanup's own changes don't count), most often first. + +Whisper (faster-whisper and mlx-whisper) and OpenAI-compatible servers get them as the prompt, a line of the names (the +diarizing models take none); Deepgram as key terms with Nova-3, or keywords with the models before it; AssemblyAI as +key terms with Universal-3 and Slam-1, or boosted words with the others. SenseVoice and ElevenLabs take no hints, so +they transcribe as before. The words go only to the engine the recording was going to anyway, and a provider's row in +the [activity ledger](activity.md) says how many it was given. Run Transcribe again on an asset to use new names. + ### Cleaning up transcripts Speech comes out of transcription as it was said, and the extractor, chapters, keywords and search all read it. With diff --git a/docs/requirements.md b/docs/requirements.md index a145a060d..1a8e99453 100644 --- a/docs/requirements.md +++ b/docs/requirements.md @@ -143,6 +143,7 @@ request, to another check that proves the same thing; loosening a requirement or | Requirement | Checks | |---|---| | Transcription | [test_speech.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_speech.py) `test_an_openai_compatible_server_transcribes`, `test_deepgram_transcribes_with_speakers_and_sentiment` | +| Transcription that expects the names the namespace knows (custom vocabulary, named people, defined entities, names people fixed), off by default | [test_speech.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_speech.py) `test_the_namespaces_own_names_go_to_the_engine` | | Transcription by a local engine (SenseVoice, Whisper), run in CI | No check yet ([#486](https://github.com/adeelahmad/lense/issues/486)) | | People recognised by voice; long recordings sent to a speech provider in pieces that fit its limits | [test_voices.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_voices.py) `test_match_suggest_merge_undo_link`; [test_speech.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_speech.py) `test_a_long_recording_goes_in_pieces_and_comes_back_whole`, `test_a_piece_too_large_to_send_is_halved` | | Text on screen and in scans | [test_video.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_video.py) `test_shots_text_search_chat_and_iiif`; [test_documents.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_documents.py) `test_scans_and_images_are_read_by_ocr`; [test_ocr.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_ocr.py) `test_a_video_read_by_doctr_and_without_it` | diff --git a/fastapi_backend/app/domain/ingest.py b/fastapi_backend/app/domain/ingest.py index 2eb1bf7c5..303257ef2 100644 --- a/fastapi_backend/app/domain/ingest.py +++ b/fastapi_backend/app/domain/ingest.py @@ -15,7 +15,7 @@ import numpy as np -from . import speech, store +from . import speech, store, vocabulary TAG_RX = re.compile(r"<\|([^|]*)\|>") SR = 16000 @@ -300,7 +300,7 @@ def _run(self, clips): except Exception: # noqa: BLE001 - older FunASR builds only take one input at a time return [self.asr.generate(input=c, cache={}, language=self.lang, use_itn=True)[0] for c in clips] - def transcribe(self, audio): + def transcribe(self, audio, terms=()): # SenseVoice takes no hints (vocabulary.py) spans = self.vad.generate(input=audio)[0]["value"] pieces = [(s, min(int(e), s + self.max_ms)) for b, e in spans for s in range(int(b), int(e), self.max_ms)] out = [] @@ -350,12 +350,14 @@ def __init__(self, cfg, mlx=False): name = "mlx-whisper" if mlx else "faster-whisper" raise EngineMissing(f"{name} isn't installed: uv sync --extra {'mlx' if mlx else 'whisper'}") from e - def transcribe(self, audio): + def transcribe(self, audio, terms=()): + """The segments; `terms` (vocabulary.py) go in as the prompt, the names Whisper should expect.""" + hint = {"initial_prompt": vocabulary.prompt(terms)} if terms else {} if self.mlx: - segs = self.m.transcribe(audio, path_or_hf_repo=self.repo, word_timestamps=True, language=self.lang)["segments"] + segs = self.m.transcribe(audio, path_or_hf_repo=self.repo, word_timestamps=True, language=self.lang, **hint)["segments"] rows = [(s["start"], s["end"], s["text"], [(w["word"], w["start"], w["end"]) for w in s.get("words") or []]) for s in segs] else: - segs, _ = self.m.transcribe(audio, vad_filter=True, word_timestamps=True, language=self.lang) + segs, _ = self.m.transcribe(audio, vad_filter=True, word_timestamps=True, language=self.lang, **hint) rows = [(s.start, s.end, s.text, [(w.word, w.start, w.end) for w in (s.words or [])]) for s in segs] return [ { @@ -501,7 +503,8 @@ def transcribe_one(db, cfg, rid, log=print, engine=None): r = db.one("SELECT record::id(id) AS id, space, path, title, remote FROM $r", r=store.R("recording", rid)) engine, t = engine or get_engine(cfg, log), time.time() audio = decode(audio_path(db, cfg, r)) - segs = engine.transcribe(audio) + words = vocabulary.terms(db, cfg, r["space"]) + segs = engine.transcribe(audio, terms=words) if words else engine.transcribe(audio) # an engine of a plugin may take no hints env = envelope(audio) del audio write_transcript( diff --git a/fastapi_backend/app/domain/speech.py b/fastapi_backend/app/domain/speech.py index b0646763a..417b99897 100644 --- a/fastapi_backend/app/domain/speech.py +++ b/fastapi_backend/app/domain/speech.py @@ -45,7 +45,7 @@ import numpy as np -from . import store +from . import store, vocabulary log = logging.getLogger("lens") SR = 16000 @@ -298,7 +298,7 @@ def _label(v): # ---------- providers ---------- -def _openai(cfg, clip, seconds): +def _openai(cfg, clip, seconds, terms=()): base, m, key = base_url(cfg, "openai"), model(cfg, "openai"), _key(cfg, "openai") data, name, ctype = clip lang = _language(cfg) @@ -311,6 +311,8 @@ def _openai(cfg, clip, seconds): ("timestamp_granularities[]", "word")] # fmt: skip if lang: fields.append(("language", lang)) + if terms and "diarize" not in m: # the diarizing models take no prompt + fields.append(("prompt", vocabulary.prompt(terms))) body, ctype_ = multipart(fields, [("file", name, data, ctype)]) headers = {"Content-Type": ctype_, **({"Authorization": f"Bearer {key}"} if key else {})} j = _json(base + "/audio/transcriptions", data=body, headers=headers, timeout=section(cfg)["timeout"]) @@ -350,7 +352,7 @@ def _short(lang): return names.get(lang) or lang.split("-")[0].split("_")[0][:3] -def _elevenlabs(cfg, clip, seconds): +def _elevenlabs(cfg, clip, seconds, terms=()): # Scribe takes no hints (vocabulary.py) data, name, ctype = clip fields = [("model_id", model(cfg, "elevenlabs")), ("diarize", "true"), ("tag_audio_events", "true"), ("timestamps_granularity", "word")] if _language(cfg): @@ -380,7 +382,7 @@ def _elevenlabs(cfg, clip, seconds): return group_words(words, _short(j.get("language_code"))) -def _assemblyai(cfg, clip, seconds): +def _assemblyai(cfg, clip, seconds, terms=()): base, key, t = base_url(cfg, "assemblyai"), _key(cfg, "assemblyai"), section(cfg)["timeout"] data, _, ctype = clip up = _json(base + "/v2/upload", data=data, headers={"Authorization": key, "Content-Type": "application/octet-stream"}, timeout=t) @@ -394,6 +396,11 @@ def _assemblyai(cfg, clip, seconds): ask["language_detection"] = True if section(cfg)["sentiment"]: ask["sentiment_analysis"] = True + if terms: # key terms for the models that take them, else boosted words (at most six words each) + if str(m or "").startswith(("slam", "universal-3")): + ask["keyterms_prompt"] = list(terms) + else: + ask["word_boost"] = [t for t in terms if len(t.split()) <= 6] d = cfg.get("diarize") or {} if d.get("min_speakers") or d.get("max_speakers"): ask["speaker_options"] = { @@ -420,17 +427,19 @@ def _assemblyai(cfg, clip, seconds): return add_sentiment(segs, spans) -def _deepgram(cfg, clip, seconds): +def _deepgram(cfg, clip, seconds, terms=()): data, _, ctype = clip - q = {"model": model(cfg, "deepgram"), "smart_format": "true", "punctuate": "true", "diarize": "true", "utterances": "true"} + q: dict = {"model": model(cfg, "deepgram"), "smart_format": "true", "punctuate": "true", "diarize": "true", "utterances": "true"} if _language(cfg): q["language"] = _language(cfg) else: q["detect_language"] = "true" if section(cfg)["sentiment"]: q["sentiment"] = "true" + if terms: # Nova-3 takes key terms; the models before it, keywords + q["keyterm" if str(q["model"]).startswith("nova-3") else "keywords"] = list(terms) j = _json( - base_url(cfg, "deepgram") + "/v1/listen?" + urllib.parse.urlencode(q), + base_url(cfg, "deepgram") + "/v1/listen?" + urllib.parse.urlencode(q, doseq=True), data=data, headers={"Authorization": f"Token {_key(cfg, 'deepgram')}", "Content-Type": ctype}, timeout=section(cfg)["timeout"], @@ -459,8 +468,8 @@ def _deepgram(cfg, clip, seconds): return add_sentiment(segs, spans) -# each takes (cfg, an encoded clip as (bytes, file name, media type), its seconds) and returns its segments, timed -# from the clip's start +# each takes (cfg, an encoded clip as (bytes, file name, media type), its seconds, the words to expect) and returns its +# segments, timed from the clip's start TRANSCRIBE = {"openai": _openai, "elevenlabs": _elevenlabs, "assemblyai": _assemblyai, "deepgram": _deepgram} @@ -529,15 +538,18 @@ def __init__(self, cfg, provider): _need(cfg, provider) self.cfg, self.provider, self.name = cfg, provider, provider - def transcribe(self, audio): - """The recording's transcript: in one request when it fits the provider's limits, else piece by piece.""" + def transcribe(self, audio, terms=()): + """The recording's transcript: in one request when it fits the provider's limits, else piece by piece; `terms` + are the words to expect (vocabulary.py).""" most, most_bytes = limits(self.cfg, self.provider) detail = {"seconds": round(len(audio) / SR, 2)} # the ledger row reads it when the call ends + if terms: + detail["vocabulary"] = len(terms) parts = [] with _ledger("speech.transcribe", self.cfg, f"{self.provider}:{model(self.cfg, self.provider)}", detail): for a, b in pieces(audio, most): for start, end, clip in clips(audio, a, b, most_bytes): - parts.append((start, TRANSCRIBE[self.provider](self.cfg, clip, round((end - start) / SR, 2)))) + parts.append((start, TRANSCRIBE[self.provider](self.cfg, clip, round((end - start) / SR, 2), terms))) if len(parts) > 1: detail["pieces"] = len(parts) log.info("speech: %s s of audio went to %s in %d pieces", detail["seconds"], LABELS[self.provider], len(parts)) diff --git a/fastapi_backend/app/domain/store.py b/fastapi_backend/app/domain/store.py index 028e3b017..decbb84da 100644 --- a/fastapi_backend/app/domain/store.py +++ b/fastapi_backend/app/domain/store.py @@ -137,6 +137,7 @@ def labels(): "sensevoice": {"model": "iic/SenseVoiceSmall", "hub": "ms", "vad_max_segment_ms": 30000, "batch_size": 16}, "whisper": {"model": "large-v3-turbo", "compute_type": "default"}, "mlx_whisper": {"model": "mlx-community/whisper-large-v3-turbo"}, + "vocabulary": False, # give each recording's engine the names its namespace knows (vocabulary.py) }, "diarize": { "engine": "auto", diff --git a/fastapi_backend/app/domain/vocabulary.py b/fastapi_backend/app/domain/vocabulary.py new file mode 100644 index 000000000..a5771dc6c --- /dev/null +++ b/fastapi_backend/app/domain/vocabulary.py @@ -0,0 +1,93 @@ +"""A namespace's own words for transcription (`transcribe.vocabulary`, off by default). + +The names speech-to-text gets wrong are the ones only you use: family, colleagues, places, projects. With the setting +on, each recording's transcription is given the words its namespace already knows, so the same mistakes stop coming +back: +- the custom vocabulary (`analysis.gazetteer`, Settings › Analysis), first, as you wrote it there; +- the names of the namespace's named speakers; +- its defined entities (entity_setup.py), however the setup writes them; +- words people put in when they corrected its transcripts (segment_edit, newest first), the ones with a capital + letter that weren't there before: the names they had to fix. + +How an engine takes them (`hints`): Whisper (faster-whisper, mlx-whisper) and OpenAI-compatible servers as the +prompt, a line of the names; Deepgram as key terms (Nova-3) or keywords; AssemblyAI as key terms (Universal-3 and +Slam-1) or boosted words. SenseVoice and ElevenLabs take no hints, so they transcribe as before. Nothing is sent +anywhere it wasn't going already: the words go only to the engine the recording goes to. +""" + +from __future__ import annotations + +import re +from collections import Counter + +from . import store + +MOST = 60 # terms per recording: Deepgram's key terms and Whisper's prompt both have room for about this many +PROMPT_CHARS = 600 # Whisper keeps the last 224 tokens of a prompt; a little more than that in characters +EDITS = 500 # the corrections read, newest first +WORD = re.compile(r"[^\W\d_][\w'’\-]*[^\W_]|[^\W\d_]", re.UNICODE) + + +def on(cfg): + return bool((cfg.get("transcribe") or {}).get("vocabulary")) + + +def _corrected(db, nid): + """Words people put in when they corrected the namespace's lines, most often first: the capitalised ones a line + didn't have before (a name the engine got wrong), not the text cleanup's.""" + from .cleanup import CLEANER + + rows = db.rows( + "SELECT before.text AS before, after.text AS after, at FROM segment_edit" + " WHERE recording IN (SELECT VALUE record::id(id) FROM recording WHERE space = $s)" + " AND after.text != NONE AND by != $c ORDER BY at DESC LIMIT $n", + s=int(nid), + c=CLEANER, + n=EDITS, + ) + seen: Counter[str] = Counter() + for r in rows: + had = {w.lower() for w in WORD.findall(str(r.get("before") or ""))} + for w in WORD.findall(str(r.get("after") or "")): + if len(w) >= 3 and any(ch.isupper() for ch in w) and w.lower() not in had: + seen[w] += 1 + return [w for w, _ in seen.most_common()] + + +def terms(db, cfg, nid): + """The words a recording of namespace `nid` is transcribed with, most wanted first; [] with the setting off.""" + if not on(cfg) or nid is None: + return [] + gaz = [str(line).partition("|")[0] for line in (cfg.get("analysis") or {}).get("gazetteer") or []] # "Name | TYPE" + spoken = db.values("SELECT VALUE name FROM speaker WHERE space = $s AND name != NONE AND name != '' ORDER BY name", s=int(nid)) + named = [str(n) for n in spoken if not str(n).strip().lower().startswith("speaker")] # not "Speaker 2" + defined = db.values("SELECT VALUE name FROM entity WHERE space = $s AND defined = true AND hidden != true ORDER BY name", s=int(nid)) + out, keys = [], set() + for t in [*gaz, *named, *(str(x) for x in defined), *_corrected(db, nid)]: + t = re.sub(r"\s+", " ", t).strip() + k = t.lower() + if t and k not in keys and len(t) <= 50: + keys.add(k) + out.append(t) + if len(out) >= MOST: + break + return out + + +def prompt(words): + """The words as a line for a Whisper-style prompt, cut at a whole word to fit PROMPT_CHARS; '' for none.""" + line = "" + for w in words: + nxt = f"{line}, {w}" if line else w + if len(nxt) + 1 > PROMPT_CHARS: + break + line = nxt + return f"{line}." if line else "" + + +def for_recording(db, cfg, rid): + """The words for recording `rid` (by its namespace).""" + if not on(cfg): + return [] + row = db.one("SELECT space FROM $r", r=store.R("recording", rid)) + return terms(db, cfg, (row or {}).get("space")) diff --git a/fastapi_backend/tests/domain/test_speech.py b/fastapi_backend/tests/domain/test_speech.py index 19287df60..06e36f7d2 100644 --- a/fastapi_backend/tests/domain/test_speech.py +++ b/fastapi_backend/tests/domain/test_speech.py @@ -566,3 +566,54 @@ def test_stuck_converters_are_stopped(tmp_path, monkeypatch): (tmp_path / "a.doc").write_bytes(b"x") with pytest.raises(SystemExit): # antiword gave up; no catdoc or LibreOffice here ingest.read_doc(tmp_path / "a.doc") + + +def test_the_namespaces_own_names_go_to_the_engine(db, cfg, fake, monkeypatch): + """With transcribe.vocabulary on, each recording is transcribed knowing its namespace's custom vocabulary, named + people, defined entities and the names people fixed in its lines; off (the default), nothing is sent.""" + from app.domain import vocabulary + + monkeypatch.setattr(speech, "POLL_SECONDS", 0) + nid = store.ns_id(db, "family") + db.q("CREATE speaker CONTENT {space: $s, name: 'Siobhan'}; CREATE speaker CONTENT {space: $s, name: 'Speaker 2'}", s=nid) + db.q("CREATE entity CONTENT {space: $s, name: 'Llanfair', key: 'llanfair', type: 'PLACE', defined: true}", s=nid) + rid = db.next_id("recording") + db.q("CREATE $r CONTENT {space: $s, title: 'call', status: 'transcribed'}", r=R("recording", rid), s=nid) + db.q( + "CREATE segment_edit CONTENT {recording: $r, idx: 0, before: {text: 'ask shiv on'}, after: {text: 'Ask Siobhan and Aoife on'}," + " by: 'a@example.com', at: time::now(), n: 1};" + "CREATE segment_edit CONTENT {recording: $r, idx: 1, before: {text: 'um hello'}, after: {text: 'Hello Cleaned'}," + " by: $c, at: time::now(), n: 2}", + r=rid, + c="text cleanup", + ) + assert vocabulary.terms(db, cfg, nid) == [] # off by default + settings.save(db, cfg, "transcribe", {"vocabulary": True}, "t") + settings.save(db, cfg, "analysis", {"gazetteer": ["Ffion | PERSON"]}, "t") + eff = provided(db, cfg, fake) + words = vocabulary.terms(db, eff, nid) + assert words == ["Ffion", "Siobhan", "Llanfair", "Aoife"] # not "Speaker 2", not the cleanup's "Cleaned" + assert vocabulary.prompt(words) == "Ffion, Siobhan, Llanfair, Aoife." + + speech.Engine(eff, "openai").transcribe(clip(), terms=words) + assert b'name="prompt"\r\n\r\nFfion, Siobhan, Llanfair, Aoife.' in Fake.seen[-1][3] + speech.Engine(eff, "deepgram").transcribe(clip(), terms=words) + q = urllib.parse.parse_qs(urllib.parse.urlsplit(Fake.seen[-1][1]).query) + assert q["keyterm"] == words and "keywords" not in q + Fake.seen.clear() + speech.Engine(eff, "assemblyai").transcribe(clip(), terms=words) + asked = next(json.loads(b) for m, p, h, b in Fake.seen if p == "/aai/v2/transcript" and m == "POST") + assert asked["word_boost"] == words + + class Hearing: + name = "fake" + heard = None + + def transcribe(self, audio, terms=()): + Hearing.heard = list(terms) + return [{"t0": 0, "t1": 900, "text": "Siobhan rang.", "lang": "en"}] + + monkeypatch.setattr(ingest, "audio_path", lambda *a, **k: "unused") + monkeypatch.setattr(ingest, "decode", lambda p: clip()) + ingest.transcribe_one(db, eff, rid, log=lambda *a: None, engine=Hearing()) + assert Hearing.heard == words diff --git a/nextjs-frontend/components/settings/bodies.tsx b/nextjs-frontend/components/settings/bodies.tsx index 029ca5715..e61601671 100644 --- a/nextjs-frontend/components/settings/bodies.tsx +++ b/nextjs-frontend/components/settings/bodies.tsx @@ -165,6 +165,7 @@ export function SectionBody({ ctx }: { ctx: BodyCtx }) { ({ value, label }))} /> +

Recordings are sent to {provider.label}, which also tells speakers apart. Its address, model and key are in Speech providers. SenseVoice and Whisper keep their @@ -187,6 +188,7 @@ export function SectionBody({ ctx }: { ctx: BodyCtx }) { ({ value, label }))} /> +

Each engine remembers its own model: {models.join(", ")}. Auto uses the fastest device each worker has.

diff --git a/nextjs-frontend/components/settings/model.ts b/nextjs-frontend/components/settings/model.ts index 16157dfb5..e50b4d6ac 100644 --- a/nextjs-frontend/components/settings/model.ts +++ b/nextjs-frontend/components/settings/model.ts @@ -643,6 +643,13 @@ export const FIELDS: FieldSpec[] = [ kind: "text", mono: true, }, + { + section: "transcribe", + key: "vocabulary", + label: "Expect your own names", + kind: "switch", + hint: "Each recording is transcribed knowing its namespace's named people, defined entities, custom vocabulary and the names you fixed in its transcripts, so the same mistakes stop coming back (Whisper, OpenAI-compatible, Deepgram and AssemblyAI; SenseVoice and ElevenLabs take no hints)", + }, // Speaker separation { section: "diarize",