Merge branch 'rhasspy:master' into bugfix-wav-volume
This commit is contained in:
Luis Andrade
+100
-12
@@ -1,4 +1,5 @@
|
||||
"""Satellite code."""
|
||||
import array
|
||||
import asyncio
|
||||
import logging
|
||||
import math
|
||||
@@ -6,14 +7,15 @@ import time
|
||||
import wave
|
||||
from enum import Enum, auto
|
||||
from pathlib import Path
|
||||
from typing import Callable, Dict, Final, Optional, Set, Union
|
||||
from typing import Callable, Dict, Final, List, Optional, Set, Union
|
||||
|
||||
from pyring_buffer import RingBuffer
|
||||
from wyoming.asr import Transcript
|
||||
from wyoming.audio import AudioChunk, AudioStart, AudioStop
|
||||
from wyoming.audio import AudioChunk, AudioFormat, AudioStart, AudioStop
|
||||
from wyoming.client import AsyncClient
|
||||
from wyoming.error import Error
|
||||
from wyoming.event import Event, async_write_event
|
||||
from wyoming.info import Describe, Info
|
||||
from wyoming.mic import MicProcessAsyncClient
|
||||
from wyoming.ping import Ping, Pong
|
||||
from wyoming.pipeline import PipelineStage, RunPipeline
|
||||
@@ -31,7 +33,13 @@ from wyoming.vad import VoiceStarted, VoiceStopped
|
||||
from wyoming.wake import Detect, Detection, WakeProcessAsyncClient
|
||||
|
||||
from .settings import SatelliteSettings
|
||||
from .utils import DebugAudioWriter, multiply_volume, run_event_command, wav_to_events
|
||||
from .utils import (
|
||||
DebugAudioWriter,
|
||||
multiply_volume,
|
||||
normalize_wake_word,
|
||||
run_event_command,
|
||||
wav_to_events,
|
||||
)
|
||||
from .vad import SileroVad
|
||||
from .webrtc import WebRtcAudio
|
||||
|
||||
@@ -39,6 +47,7 @@ _LOGGER = logging.getLogger()
|
||||
|
||||
_PONG_TIMEOUT: Final = 5
|
||||
_PING_SEND_DELAY: Final = 2
|
||||
_WAKE_INFO_TIMEOUT: Final = 2
|
||||
|
||||
|
||||
class State(Enum):
|
||||
@@ -285,7 +294,7 @@ class SatelliteBase:
|
||||
if not AudioChunk.is_type(event.type):
|
||||
await self.forward_event(event)
|
||||
|
||||
async def _send_run_pipeline(self) -> None:
|
||||
async def _send_run_pipeline(self, pipeline_name: Optional[str] = None) -> None:
|
||||
"""Sends a RunPipeline event with the correct stages."""
|
||||
if self.settings.wake.enabled:
|
||||
# Local wake word detection
|
||||
@@ -304,8 +313,17 @@ class SatelliteBase:
|
||||
end_stage = PipelineStage.HANDLE
|
||||
|
||||
run_pipeline = RunPipeline(
|
||||
start_stage=start_stage, end_stage=end_stage, restart_on_end=restart_on_end
|
||||
start_stage=start_stage,
|
||||
end_stage=end_stage,
|
||||
name=pipeline_name,
|
||||
restart_on_end=restart_on_end,
|
||||
snd_format=AudioFormat(
|
||||
rate=self.settings.snd.rate,
|
||||
width=self.settings.snd.width,
|
||||
channels=self.settings.snd.channels,
|
||||
),
|
||||
).event()
|
||||
_LOGGER.debug(run_pipeline)
|
||||
await self.event_to_server(run_pipeline)
|
||||
await self.forward_event(run_pipeline)
|
||||
|
||||
@@ -443,15 +461,36 @@ class SatelliteBase:
|
||||
continue
|
||||
|
||||
# Audio processing
|
||||
if self.settings.mic.needs_processing and AudioChunk.is_type(
|
||||
event.type
|
||||
if (
|
||||
self.settings.mic.needs_processing
|
||||
or (self.settings.mic.channel_index is not None)
|
||||
and AudioChunk.is_type(event.type)
|
||||
):
|
||||
chunk = AudioChunk.from_event(event)
|
||||
audio_bytes = self._process_mic_audio(chunk.audio)
|
||||
if self.settings.mic.channel_index is not None:
|
||||
if chunk.width != 2:
|
||||
raise ValueError(
|
||||
"Mic channel index selection requires 16-bit samples"
|
||||
)
|
||||
|
||||
# Convert to unsigned 16-bit array to make channel extraction easier
|
||||
audio_array = array.array("H", chunk.audio)
|
||||
audio_bytes = audio_array[
|
||||
self.settings.mic.channel_index :: chunk.channels
|
||||
].tobytes()
|
||||
|
||||
if self.settings.mic.needs_processing:
|
||||
if audio_bytes is None:
|
||||
audio_bytes = chunk.audio
|
||||
|
||||
audio_bytes = self._process_mic_audio(chunk.audio)
|
||||
|
||||
event = AudioChunk(
|
||||
rate=chunk.rate,
|
||||
width=chunk.width,
|
||||
channels=chunk.channels,
|
||||
channels=chunk.channels
|
||||
if (self.settings.mic.channel_index is None)
|
||||
else 1,
|
||||
audio=audio_bytes,
|
||||
).event()
|
||||
else:
|
||||
@@ -733,7 +772,11 @@ class SatelliteBase:
|
||||
|
||||
async def _send_wake_detect(self) -> None:
|
||||
"""Inform wake word service of which wake words to detect."""
|
||||
await self.event_to_wake(Detect(names=self.settings.wake.names).event())
|
||||
wake_names: Optional[List[str]] = None
|
||||
if self.settings.wake.names:
|
||||
wake_names = [w.name for w in self.settings.wake.names]
|
||||
|
||||
await self.event_to_wake(Detect(names=wake_names).event())
|
||||
await self.trigger_detect()
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
@@ -856,6 +899,13 @@ class SatelliteBase:
|
||||
|
||||
await _disconnect()
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
# Info
|
||||
# -------------------------------------------------------------------------
|
||||
|
||||
async def update_info(self, info: Info) -> None:
|
||||
pass
|
||||
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
|
||||
@@ -1108,6 +1158,9 @@ class WakeStreamingSatellite(SatelliteBase):
|
||||
|
||||
self._is_paused = False
|
||||
|
||||
self._wake_info: Optional[Info] = None
|
||||
self._wake_info_ready = asyncio.Event()
|
||||
|
||||
async def event_from_server(self, event: Event) -> None:
|
||||
# Only check event types once
|
||||
is_run_satellite = False
|
||||
@@ -1201,8 +1254,13 @@ class WakeStreamingSatellite(SatelliteBase):
|
||||
await self.event_to_wake(event)
|
||||
|
||||
async def event_from_wake(self, event: Event) -> None:
|
||||
if Info.is_type(event.type):
|
||||
self._wake_info = Info.from_event(event)
|
||||
self._wake_info_ready.set()
|
||||
return
|
||||
|
||||
if self.is_streaming or (self.server_id is None):
|
||||
# Not streaming or no server connected
|
||||
# Not detecting or no server connected
|
||||
return
|
||||
|
||||
if Detection.is_type(event.type):
|
||||
@@ -1224,6 +1282,8 @@ class WakeStreamingSatellite(SatelliteBase):
|
||||
if self.stt_audio_writer is not None:
|
||||
self.stt_audio_writer.start(timestamp=self._debug_recording_timestamp)
|
||||
|
||||
_LOGGER.debug(detection)
|
||||
|
||||
self.is_streaming = True
|
||||
_LOGGER.debug("Streaming audio")
|
||||
|
||||
@@ -1237,7 +1297,35 @@ class WakeStreamingSatellite(SatelliteBase):
|
||||
# No refractory period
|
||||
self.refractory_timestamp.pop(detection.name, None)
|
||||
|
||||
await self._send_run_pipeline()
|
||||
# Forward to the server
|
||||
await self.event_to_server(event)
|
||||
|
||||
# Match detected wake word name with pipeline name
|
||||
pipeline_name: Optional[str] = None
|
||||
if self.settings.wake.names:
|
||||
detection_name = normalize_wake_word(detection.name)
|
||||
for wake_name in self.settings.wake.names:
|
||||
if normalize_wake_word(wake_name.name) == detection_name:
|
||||
pipeline_name = wake_name.pipeline
|
||||
break
|
||||
|
||||
await self._send_run_pipeline(pipeline_name=pipeline_name)
|
||||
await self.forward_event(event) # forward to event service
|
||||
await self.trigger_detection(Detection.from_event(event))
|
||||
await self.trigger_streaming_start()
|
||||
|
||||
async def update_info(self, info: Info) -> None:
|
||||
self._wake_info = None
|
||||
self._wake_info_ready.clear()
|
||||
await self.event_to_wake(Describe().event())
|
||||
|
||||
try:
|
||||
await asyncio.wait_for(
|
||||
self._wake_info_ready.wait(), timeout=_WAKE_INFO_TIMEOUT
|
||||
)
|
||||
|
||||
if self._wake_info is not None:
|
||||
# Update wake info only
|
||||
info.wake = self._wake_info.wake
|
||||
except asyncio.TimeoutError:
|
||||
_LOGGER.warning("Failed to get info from wake service")
|
||||
|
||||
Reference in New Issue
Block a user