mkbk/Owner
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[播放平滑修复]：完成可打断播报平滑播放，包含单输出流分块播放和TTS采样率保真

Browse Source
This commit is contained in:
mkbk
2026-06-18 12:21:01 +08:00
parent 7519725321
commit d7dbec5c29
5 changed files with 142 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/owner_voice_pet/assistant_pipeline.py
+13 -38
View File
@@ -489,24 +489,22 @@ class TurnController:
)
def _play_interruptible(self, segment: AudioSegment, *, turn_id: int) -> bool:
elapsed_ms = 0
guard_cleared = False
self.vad_recorder.provider.reset()
realtime_session = self._start_realtime_transcript()
speech_ms = 0
partial_seen = False
pending_frames: list[AudioFrame] = []
for chunk in _audio_chunks(segment, chunk_ms=100):
playback = self.transport.play_pcm(chunk)
if playback.error:
raise playback.error
elapsed_ms += chunk.duration_ms
interrupted = False
def after_chunk(_chunk: AudioSegment, elapsed_ms: int) -> bool:
nonlocal guard_cleared, speech_ms, partial_seen, interrupted
if elapsed_ms < self.config.barge_in_echo_guard_ms:
continue
return False
if not guard_cleared:
self.transport.flush_input()
guard_cleared = True
continue
return False
detected, speech_ms, partial_seen, new_frames = self._detect_barge_in(
realtime_session,
turn_id=turn_id,
@@ -518,12 +516,16 @@ class TurnController:
self._pending_capture_frames.extend(pending_frames)
self._event(BARGE_IN_DETECTED, PipelineState.INTERRUPTED, "检测到用户打断", turn_id=turn_id)
self._event(PLAYBACK_INTERRUPTED, PipelineState.INTERRUPTED, "播报已打断", turn_id=turn_id)
if realtime_session is not None:
realtime_session.finish()
interrupted = True
return True
return False
playback = self.transport.play_pcm_chunks(segment, chunk_ms=100, after_chunk=after_chunk)
if playback.error:
raise playback.error
if realtime_session is not None:
realtime_session.finish()
return False
return interrupted
def _detect_barge_in(
self,
@@ -692,30 +694,3 @@ class VoiceAssistantPipeline:
handler(event)
return
dispatch_pipeline_event(self.reporter, event)
def _audio_chunks(segment: AudioSegment, *, chunk_ms: int) -> list[AudioSegment]:
if chunk_ms <= 0 or segment.duration_ms <= chunk_ms:
return [segment]
bytes_per_ms = max(1, int(segment.sample_rate * segment.channels * 2 / 1000))
chunk_bytes = max(2 * segment.channels, bytes_per_ms * chunk_ms)
chunk_bytes -= chunk_bytes % (2 * segment.channels)
chunks: list[AudioSegment] = []
offset = 0
start_ms = segment.start_time_ms
while offset < len(segment.pcm):
data = segment.pcm[offset : offset + chunk_bytes]
duration_ms = max(1, int(len(data) / bytes_per_ms))
chunks.append(
AudioSegment(
data,
segment.sample_rate,
segment.channels,
start_ms,
start_ms + duration_ms,
dict(segment.metadata),
)
)
offset += len(data)
start_ms += duration_ms
return chunks
src/owner_voice_pet/protocols.py
+10 -1
View File
@@ -1,6 +1,6 @@
from __future__ import annotations
from collections.abc import Iterable, Sequence
from collections.abc import Callable, Iterable, Sequence
from typing import Protocol
from .models import (
@@ -28,6 +28,15 @@ class AudioTransport(Protocol):
def play_pcm(self, segment: AudioSegment, interrupt: bool = False) -> PlaybackResult:
...
def play_pcm_chunks(
self,
segment: AudioSegment,
*,
chunk_ms: int,
after_chunk: Callable[[AudioSegment, int], bool] | None = None,
) -> PlaybackResult:
...
def flush_input(self) -> int:
...
src/owner_voice_pet/transport.py
+98
View File
@@ -6,6 +6,7 @@ import shutil
import subprocess
import tempfile
import time
from collections.abc import Callable
from collections import deque
from pathlib import Path
from typing import Any
@@ -106,6 +107,23 @@ class MemoryAudioTransport:
self.played_segments.append(segment)
return PlaybackResult(True, segment.duration_ms)
def play_pcm_chunks(
self,
segment: AudioSegment,
*,
chunk_ms: int,
after_chunk: Callable[[AudioSegment, int], bool] | None = None,
) -> PlaybackResult:
elapsed_ms = 0
for chunk in _raw_pcm_chunks(segment, chunk_ms=chunk_ms):
playback = self.play_pcm(chunk)
if playback.error:
return playback
elapsed_ms += chunk.duration_ms
if after_chunk is not None and after_chunk(chunk, elapsed_ms):
return PlaybackResult(True, elapsed_ms)
return PlaybackResult(True, elapsed_ms)
def flush_input(self) -> int:
self.flush_count += 1
if not self._flush_clears_input:
@@ -288,6 +306,59 @@ class SoundDeviceAudioTransport:
)
return PlaybackResult(True, segment.duration_ms)
def play_pcm_chunks(
self,
segment: AudioSegment,
*,
chunk_ms: int,
after_chunk: Callable[[AudioSegment, int], bool] | None = None,
) -> PlaybackResult:
if self._sd is None or segment.metadata.get("format") in {"aiff", "wav", "mp3", "m4a", "aac"}:
playback = self.play_pcm(segment)
if playback.error:
return playback
if after_chunk is not None:
after_chunk(segment, segment.duration_ms)
return playback
if not segment.pcm:
return PlaybackResult(
False,
0,
ProviderError(
ErrorCode.AUDIO_STREAM_UNDERRUN,
"cannot play empty audio segment",
True,
"sounddevice-transport",
"transport",
),
)
elapsed_ms = 0
try:
with self._sd.RawOutputStream(
samplerate=segment.sample_rate,
channels=segment.channels,
dtype="int16",
device=_coerce_device_id(self._output_device),
) as stream:
for chunk in _raw_pcm_chunks(segment, chunk_ms=chunk_ms):
stream.write(chunk.pcm)
elapsed_ms += chunk.duration_ms
if after_chunk is not None and after_chunk(chunk, elapsed_ms):
return PlaybackResult(True, elapsed_ms)
except Exception as exc:
return PlaybackResult(
False,
elapsed_ms,
ProviderError(
ErrorCode.AUDIO_OUTPUT_DEVICE_MISSING,
f"cannot play through sounddevice output stream: {exc}",
False,
"sounddevice-transport",
"transport",
),
)
return PlaybackResult(True, elapsed_ms)
def stop(self) -> None:
if self._stream is None:
return None
@@ -418,3 +489,30 @@ def _play_file_bytes_with_afplay(segment: AudioSegment) -> PlaybackResult:
),
)
return PlaybackResult(True, segment.duration_ms)
def _raw_pcm_chunks(segment: AudioSegment, *, chunk_ms: int) -> list[AudioSegment]:
if chunk_ms <= 0 or segment.duration_ms <= chunk_ms:
return [segment]
bytes_per_ms = max(1, int(segment.sample_rate * segment.channels * 2 / 1000))
chunk_bytes = max(2 * segment.channels, bytes_per_ms * chunk_ms)
chunk_bytes -= chunk_bytes % (2 * segment.channels)
chunks: list[AudioSegment] = []
offset = 0
start_ms = segment.start_time_ms
while offset < len(segment.pcm):
data = segment.pcm[offset : offset + chunk_bytes]
duration_ms = max(1, int(len(data) / bytes_per_ms))
chunks.append(
AudioSegment(
data,
segment.sample_rate,
segment.channels,
start_ms,
start_ms + duration_ms,
dict(segment.metadata),
)
)
offset += len(data)
start_ms += duration_ms
return chunks
src/owner_voice_pet/tts.py
+1 -1
View File
@@ -123,7 +123,7 @@ class MacSayTtsProvider:
) from exc
try:
subprocess.run(
["afconvert", "-f", "WAVE", "-d", "LEI16@16000", "-c", "1", str(aiff_output), str(wav_output)],
["afconvert", "-f", "WAVE", "-d", "LEI16", "-c", "1", str(aiff_output), str(wav_output)],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
tests/test_transport.py
+20
View File
@@ -114,6 +114,24 @@ class TransportTests(unittest.TestCase):
self.assertTrue(result.played)
self.assertEqual(fake.output_writes, [b"\x00\x00\x01\x00"])
self.assertEqual(fake.output_stream_open_count, 1)
def test_sounddevice_chunk_playback_keeps_one_output_stream_open(self) -> None:
fake = FakeSoundDevice()
transport = SoundDeviceAudioTransport(sounddevice_module=fake)
segment = AudioSegment(b"\x00\x00" * 1600, 16000, 1, 0, 100)
callbacks: list[int] = []
result = transport.play_pcm_chunks(
segment,
chunk_ms=20,
after_chunk=lambda _chunk, elapsed_ms: callbacks.append(elapsed_ms) is not None and False,
)
self.assertTrue(result.played)
self.assertEqual(fake.output_stream_open_count, 1)
self.assertGreater(len(fake.output_writes), 1)
self.assertEqual(callbacks[-1], result.duration_ms)
def test_sounddevice_device_report_uses_query_devices(self) -> None:
fake = FakeSoundDevice()
@@ -162,6 +180,7 @@ class FakeSoundDevice:
def __init__(self, callback_payloads: list[bytes] | None = None) -> None:
self.callback_payloads = callback_payloads
self.output_writes: list[bytes] = []
self.output_stream_open_count = 0
def RawInputStream(self, **kwargs):
if self.callback_payloads is not None:
@@ -169,6 +188,7 @@ class FakeSoundDevice:
return FakeInputStream(**kwargs)
def RawOutputStream(self, **kwargs):
self.output_stream_open_count += 1
return FakeOutputStream(self, **kwargs)
def query_devices(self):