kunthawat
e96498b67e
- C1: stop feeding the unconsumed barge-in TTSQueue in the reply path (deadlocked after 64 chunks on a real long reply) - C2: encode reply Opus at the TTS/codec sample rate (24 kHz), not hardcoded 16 kHz; encoder now rate-generic - M3: bound the mic PCM buffer to the 60 s max utterance - M4: tts_sentence_start per speakable sentence, not per LLM token - Minor: send tts.stop on a failed turn; constant-time token compare - Sec: untrack + gitignore config.yaml; add config.example.yaml with placeholder secrets - Tests: 23 pass (2 new regressions: long-reply deadlock, rate-generic encoder)
107 lines
4.2 KiB
Python
107 lines
4.2 KiB
Python
"""Conversation session — wires audio → STT → voice profile → TTS (REQ-001..008).
|
|
|
|
The session is the state machine for one connected device. It owns:
|
|
the PCM buffer, VAD end-of-speech, the TTS queue (for barge-in), and the
|
|
latency logger. It exposes :meth:`on_user_speech` which runs one spoken turn
|
|
end-to-end and yields assistant text chunks — the single seam the websocket
|
|
endpoint drives.
|
|
|
|
Cross-session recall (REQ-008): the session holds a ``session_search_fn``
|
|
injected by the caller (the Hermes layer) so "when did we do X?" questions
|
|
can pull a real session snippet, without the session module importing the
|
|
search implementation.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from dataclasses import dataclass
|
|
from typing import AsyncIterator, Awaitable, Callable
|
|
|
|
from ..audio.buffer import PCMBuffer
|
|
from ..audio.vad import VAD
|
|
from ..metrics.latency import LatencyLogger
|
|
from ..stt import STTEngine
|
|
from ..tts import TTSQueue, TTSEngine, chunk_text
|
|
from ..hermes import HermesClient
|
|
from . import messages
|
|
|
|
|
|
@dataclass
|
|
class Session:
|
|
client: HermesClient
|
|
stt: STTEngine
|
|
tts: TTSEngine
|
|
vad: VAD
|
|
logger: LatencyLogger
|
|
session_search_fn: Callable[[str], Awaitable[str]] | None = None
|
|
_queue: TTSQueue | None = None
|
|
_buffer: PCMBuffer | None = None
|
|
|
|
def __post_init__(self) -> None:
|
|
self._queue = TTSQueue()
|
|
# Bound the mic buffer to the 60 s max utterance so a quiet room
|
|
# that never latches speech cannot grow memory without limit
|
|
# (review Major 3). 60 s @ 16 kHz mono 16-bit = 1.92 MB.
|
|
self._buffer = PCMBuffer(max_bytes=60 * 16000 * 2)
|
|
|
|
# -- audio in (REQ-002) -------------------------------------------------
|
|
def feed_audio(self, pcm: bytes) -> None:
|
|
self._buffer.feed(pcm)
|
|
|
|
def end_of_speech(self) -> bytes:
|
|
"""Flush the utterance PCM when the VAD reports end-of-speech."""
|
|
self.logger.speech_end()
|
|
return self._buffer.get()
|
|
|
|
# -- barge-in (REQ-007) -------------------------------------------------
|
|
def barge_in(self) -> int:
|
|
"""User interrupted: cancel the in-flight TTS. Returns dropped chunks."""
|
|
assert self._queue is not None
|
|
return self._queue.cancel()
|
|
|
|
# -- one spoken turn (REQ-001..008) -------------------------------------
|
|
async def run_turn(
|
|
self, user_pcm: bytes
|
|
) -> AsyncIterator[tuple[str, str | bytes]]:
|
|
"""Run one turn; yield ``(kind, payload)`` events.
|
|
|
|
* ``("stt", str)`` — final transcript.
|
|
* ``("tts_text", str)`` — assistant text chunk (for display).
|
|
* ``("audio", bytes)`` — PCM chunk (for playback).
|
|
"""
|
|
self.logger.speech_start()
|
|
result = await self.stt.transcribe(user_pcm)
|
|
self.logger.stt_final()
|
|
yield ("stt", result.text)
|
|
|
|
self.logger.hermes_request()
|
|
full = ""
|
|
async for chunk in self.client.respond(result.text):
|
|
self.logger.qwen_first_token() # first chunk is the first token
|
|
full += chunk
|
|
# Display text streams per LLM token (REQ: live transcript).
|
|
yield ("tts_text", chunk)
|
|
# Stream TTS as the answer arrives (REQ-006): each speakable
|
|
# sentence (chunk_text piece) is announced once as
|
|
# ``tts_sentence`` — that is the unit the firmware displays as a
|
|
# sentence (review Major 4: NOT one per LLM token).
|
|
for piece in chunk_text(chunk):
|
|
yield ("tts_sentence", piece)
|
|
for audio in await self._synthesize(piece):
|
|
self.logger.first_audio_packet()
|
|
yield ("audio", audio)
|
|
self.client.session().push(result.text, full)
|
|
|
|
async def _synthesize(self, text: str) -> list[bytes]:
|
|
"""Synthesize one speakable sentence; collect its audio chunks.
|
|
|
|
The barge-in TTSQueue is deliberately NOT fed here: this PoC streams
|
|
the reply synchronously, and putting into the queue without a consumer
|
|
blocks forever once 64 chunks accumulated on a real (long) reply
|
|
(review Critical 1). ``barge_in()`` stays the documented interrupt.
|
|
"""
|
|
out: list[bytes] = []
|
|
async for audio in self.tts.synthesize(text):
|
|
out.append(audio)
|
|
return out
|