|
| 1 | +from __future__ import annotations |
| 2 | + |
| 3 | +import asyncio |
| 4 | +import json |
| 5 | +import math |
| 6 | +from collections.abc import AsyncIterator |
| 7 | +from typing import Any |
| 8 | + |
| 9 | +import structlog |
| 10 | +import websockets |
| 11 | + |
| 12 | +from ai_server.voice.stt.base import TranscriptionResult, TranscriptionSegment |
| 13 | +from ai_server.voice.stt.live import LiveSttProvider, LiveSttSession, LiveTranscriptEvent |
| 14 | + |
| 15 | +log = structlog.get_logger(__name__) |
| 16 | + |
| 17 | + |
| 18 | +class _DeepgramLiveSession(LiveSttSession): |
| 19 | + def __init__(self, *, api_key: str, url: str, model: str, language: str, |
| 20 | + endpointing_ms: int, content_type: str) -> None: |
| 21 | + self._api_key = api_key |
| 22 | + self._url = url |
| 23 | + self._model = model |
| 24 | + self._language = language |
| 25 | + self._endpointing_ms = endpointing_ms |
| 26 | + self._content_type = content_type |
| 27 | + self._ws: Any | None = None |
| 28 | + self._queue: asyncio.Queue[LiveTranscriptEvent | None] = asyncio.Queue() |
| 29 | + self._recv_task: asyncio.Task[None] | None = None |
| 30 | + self._finals: list[str] = [] |
| 31 | + self._segments: list[TranscriptionSegment] = [] |
| 32 | + |
| 33 | + def _query(self) -> str: |
| 34 | + # encoding/sample_rate 는 컨테이너(webm/opus)면 Deepgram 이 자동 디코드. |
| 35 | + params = { |
| 36 | + "model": self._model, |
| 37 | + "language": self._language, |
| 38 | + "smart_format": "true", |
| 39 | + "interim_results": "true", |
| 40 | + # endpointing: N ms 무음 후 speech_final=true 로 턴 종료 신호 (Deepgram 공식). |
| 41 | + "endpointing": str(self._endpointing_ms), |
| 42 | + # utterance_end_ms: 별도 UtteranceEnd 메시지 backstop (interim_results 필요, 최소 1000). |
| 43 | + "utterance_end_ms": str(max(1000, self._endpointing_ms)), |
| 44 | + "vad_events": "true", |
| 45 | + } |
| 46 | + return self._url + "?" + "&".join(f"{k}={v}" for k, v in params.items()) |
| 47 | + |
| 48 | + async def start(self) -> None: |
| 49 | + self._ws = await websockets.connect( |
| 50 | + self._query(), |
| 51 | + additional_headers={"Authorization": f"Token {self._api_key}"}, |
| 52 | + ) |
| 53 | + self._recv_task = asyncio.create_task(self._recv_loop()) |
| 54 | + |
| 55 | + async def _recv_loop(self) -> None: |
| 56 | + assert self._ws is not None |
| 57 | + try: |
| 58 | + async for raw in self._ws: |
| 59 | + msg = json.loads(raw) |
| 60 | + mtype = msg.get("type") |
| 61 | + if mtype == "Results": |
| 62 | + alt = (((msg.get("channel") or {}).get("alternatives") or [{}])[0]) |
| 63 | + text = str(alt.get("transcript") or "") |
| 64 | + is_final = bool(msg.get("is_final")) |
| 65 | + speech_final = bool(msg.get("speech_final")) |
| 66 | + if text: |
| 67 | + await self._queue.put( |
| 68 | + LiveTranscriptEvent( |
| 69 | + text=text, is_final=is_final, speech_final=speech_final |
| 70 | + ) |
| 71 | + ) |
| 72 | + if is_final and text: |
| 73 | + self._finals.append(text) |
| 74 | + start = float(msg.get("start", 0.0)) |
| 75 | + dur = float(msg.get("duration", 0.0)) |
| 76 | + conf = alt.get("confidence") |
| 77 | + self._segments.append( |
| 78 | + TranscriptionSegment( |
| 79 | + start_sec=start, |
| 80 | + end_sec=start + dur, |
| 81 | + text=text, |
| 82 | + avg_logprob=_conf_to_logprob(conf), |
| 83 | + ) |
| 84 | + ) |
| 85 | + elif mtype == "UtteranceEnd": |
| 86 | + await self._queue.put( |
| 87 | + LiveTranscriptEvent(text="", is_final=True, speech_final=True) |
| 88 | + ) |
| 89 | + except Exception as exc: # noqa: BLE001 |
| 90 | + log.warn("deepgram_live.recv.closed", error=str(exc)) |
| 91 | + finally: |
| 92 | + await self._queue.put(None) |
| 93 | + |
| 94 | + async def push(self, chunk: bytes) -> None: |
| 95 | + if self._ws is not None: |
| 96 | + await self._ws.send(chunk) |
| 97 | + |
| 98 | + async def finish(self) -> None: |
| 99 | + if self._ws is not None: |
| 100 | + await self._ws.send(json.dumps({"type": "CloseStream"})) |
| 101 | + |
| 102 | + async def events(self) -> AsyncIterator[LiveTranscriptEvent]: |
| 103 | + while True: |
| 104 | + ev = await self._queue.get() |
| 105 | + if ev is None: |
| 106 | + return |
| 107 | + yield ev |
| 108 | + |
| 109 | + async def result(self) -> TranscriptionResult: |
| 110 | + text = " ".join(self._finals).strip() |
| 111 | + dur = self._segments[-1].end_sec if self._segments else None |
| 112 | + return TranscriptionResult( |
| 113 | + text=text, |
| 114 | + language=self._language, |
| 115 | + duration_sec=dur, |
| 116 | + segments=list(self._segments), |
| 117 | + ) |
| 118 | + |
| 119 | + async def close(self) -> None: |
| 120 | + if self._recv_task is not None: |
| 121 | + self._recv_task.cancel() |
| 122 | + if self._ws is not None: |
| 123 | + await self._ws.close() |
| 124 | + |
| 125 | + |
| 126 | +class DeepgramLiveSttProvider(LiveSttProvider): |
| 127 | + model_name = "deepgram-live" |
| 128 | + |
| 129 | + def __init__(self, *, api_key: str, url: str, model: str, language: str, |
| 130 | + endpointing_ms: int) -> None: |
| 131 | + if not api_key: |
| 132 | + raise ValueError("Deepgram API key 누락") |
| 133 | + self._api_key = api_key |
| 134 | + self._url = url |
| 135 | + self._model = model |
| 136 | + self._language = language |
| 137 | + self._endpointing_ms = endpointing_ms |
| 138 | + |
| 139 | + def open_session(self, *, content_type: str, language: str | None) -> LiveSttSession: |
| 140 | + return _DeepgramLiveSession( |
| 141 | + api_key=self._api_key, |
| 142 | + url=self._url, |
| 143 | + model=self._model, |
| 144 | + language=language or self._language, |
| 145 | + endpointing_ms=self._endpointing_ms, |
| 146 | + content_type=content_type, |
| 147 | + ) |
| 148 | + |
| 149 | + |
| 150 | +def _conf_to_logprob(confidence: Any) -> float | None: |
| 151 | + if confidence is None: |
| 152 | + return None |
| 153 | + try: |
| 154 | + c = float(confidence) |
| 155 | + except (TypeError, ValueError): |
| 156 | + return None |
| 157 | + return math.log(min(c, 1.0)) if c > 0 else None |
0 commit comments